Noise camera, server for processing documentary evidence from noise cameras, and methods

Abstract

A noise camera for a noise monitoring system is provided that comprises a tracking camera for recording video within a field of view of the tracking camera, at least one audio detector configured to d

Description

BACKGROUND Field of Disclosure The present disclosure relates to noise cameras, servers for processing documentary evidence generated by noise cameras, systems for monitoring noise, and methods of processing documentary evidence and operating noise cameras. Description of Related Art The “background” description provided herein is for the purpose of generally presenting the context of the disclosure. Work of the presently named inventors, to the extent it is described m this background section, as well as aspects of the description which may not otherwise qualify as prior art at the time of filing, are neither expressly nor impliedly admitted as prior art against the present invention. Powered devices are known to emit noise; for example, as a result of engines which power such devices. In the case of motor vehicles, internal combustion engines - which powers such vehicles - emit noise mostly from exhausts. Motor vehicles also emit noise in other forms, such as horn honking and amplified music. Noise emitted by motor vehicles has been regulated for some years. New vehicles are required to comply with strict noise emission limits. In the United Kingdom (UK), for example, these have been progressively reduced from 82 dB in 1978 to a current limit of 72 dB established in 2016. However, whilst manufacturers of motor vehicles may introduce measures in order, as far as possible, to reduce noise emissions to comply with legal requirements, malfunction or adaptation from an original specification, particularly from older vehicles or other customisation, can result in a. motor vehicle exceeding an allowed legal limit. Furthermore, whilst some noise emissions can be regarded as legitimate, such as those emitted by a siren of emergency vehicles, noise emissions can be classified as nuisance noise. Such nuisance noise may for example be created by high-performance sports cars, motorbikes, or vehicles with tuned exhaust systems and the like, which exceed a legal limit. Such noise emissions can be considered to be nuisance noise especially in urban and residential areas, and are often considered to be anti-social. It is therefore desirable to identify vehicles and their drivers when such vehicles exceed the legal limit for noise emissions. Furthermore, the operation of vehicles is subject to legal restrictions on noise emissions, which may be addressed through a number of legal measures that differ depending on jurisdiction. For example, the UK Anti-social Behaviour, Crime and Policing Act 2014 provides in Section 59 for Public Spaces Protection Orders (PSPOs), which allows a local authority to impose restrictions on certain acts within a restricted area. As an example, in 2021 the Royal Borough of Kensington and Chelsea implemented a PSPO restricting, among other things, “[rjewing of engme(s)... [and s]udden and / or rapid acceleration” where it was likely to cause a public nuisance, with the ability to impose a fixed penalty notice or a fine on the driver of such a vehicle. Other jurisdictions have different legal measures. For example, in Nev>' Y ork, Senate Bill S9009 introduced limits on the “maximum allowable sound levels... measured at, or adjusted to, a distance of fifty feet” with different allowable sound levels defined for roads with different speed limits. So-called “noise cameras” have been developed to detect and identify vehicles which emit noise exceeding a legal limit. Such noise cameras are analogous to speed cameras in that they are located at a roadside, and are configured to detect when a threshold noise emission event occurs causing sound, video and / or images to be recorded of an infringing event. Documentary evidence, such as sound records, images and / or video can be automatically uploaded to a server which allows an investigating authority to review the evidence collected by the noise camera and to determine what action should be taken. However, on some occasions several vehicles may be present in the documentary' evidence resulting from a threshold noise event where only one of the vehicles may have caused the event. Improving a detection accuracy in noise camera systems is therefore desirable in order to separate vehicles which emit noise above a desired threshold / legal threshold from those which do not. Furthermore, in view of the legal measures in some jurisdictions - such as in New York as noted above -the allowed noise limit may be dependent on a distance at which it is measured. Therefore, it is desirable to enable determination of a di stance to vehicles which emit noise above a particular threshold. Embodiments of the present disclosure therefore seek to provide solutions to enable such a determination of distance in combination with noise detection. SUMMARY OF THE DISCLOSURE Ure present disclosure can help address or mitigate at least some of the issues discussed above. Some embodiments of the present technique can provide a noise camera for a noise monitoring system . The noise camera comprises a tracking camera for recording video within a field of view' of the tracking camera, at least one audio detector configured to detect noise from a noise source within tire field of view of the tracking camera, and processing circuitry. The processing circuitry is configured to determine a location of the noise source within the field of view' of the tracking camera from which the noise source can be identified, and to determine, based on a physical position (e.g. the height and / or angle) of the noise camera and a point at which a ray from the tracking camera intersects a pseudo-ground plane at the location of the noise source, a distance between the noise source and the noise camera. Further embodiments of the present technique can provide a server for processing documentary' evidence from a noise camera. The server comprises processing circuitry having program code, which when executed causes the processing circuitry to receive the documentary evidence from the noise camera following a trigger event, the documentary evidence comprising tracking video, noise source location values comprising, for each of one or more frames of the tracking video, and an indication of a location of a dominant noise source in the frame of the tracking video (and, optionally, a sound recording of sound associated with the trigger event), and to determine, based on a physical position (e.g. the height and / or angle) of the noise camera and a point at which a ray from the tracking camera intersects a pseudo-ground plane at the location of the noise source, a distance between the noise source and the noise camera. Such embodiments of the present technique, which, in addition to noise cameras and servers for processing documentary' evidence from noise cameras, relate to methods of operating noise cameras, methods of processing documentary' evidence from noise cameras, noise monitoring systems, computer programs, and computer-readable storage mediums, can allow for a distance between a noise camera and a detected noise source to be accurately measured and taken into account when determining whether vehicles emit noise above a desired or legal threshold. Respective aspects and features of the present disclosure are defined in the appended claims. It. is to be understood that both the foregoing general description and the following detailed description are exemplary, but are not restrictive, of the present technology. The described embodiments, together with further advantages, will be best understood by reference to the following detailed description taken in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS A more complete appreciation of the disclosure and many of the attendant advantages thereof will be readily obtained as the same becomes better understood by reference to the following detailed description when considered in connection with the accompanying drawings wherein like reference numerals designate identical or corresponding parts throughout the several views, and wherein: Figure 1 show's schematically an overview of a noise monitoring system, showing a plurality of noise cameras and road scenes; Figure 2A shows schematically a noise camera and component parts thereof; Figure 2B shows a view- of a noise camera and component parts thereof as installed in a roadside location; Figure 2C shows a graphical representation of a plot of volume against time for certain frequencies, illustrating aspects of a noise camera that may be configured to operate in accordance with embodiments of the present technique; Figure 3 show's schematically a noise camera and component parts thereof, in accordance wi th Figures 2 A and 2B, and a camera and microphone array connected to the noise camera that may be configured to operate in accordance with embodiments of the present technique; Figure 4 shows a flow diagram of processing steps in accordance with operation of a camera and microphone array such as that of Figure 3 in accordance with certain embodiments of the present technique; Figure 5 shows a schematic diagram of a source of noise emission and a camera and microphone array in accordance with certain embodiments of the present technique; Figure 6 also shows a schematic diagram of a source of noise emission and a camera and microphone array, displaying an incident angle of noise at the camera and microphone array in accordance with certain embodiments of the present technique; Figure 7A show s a representation of a field of view of a wide angle, specifically a fisheye lens, camera; Figure 7B show's a representation of an interpolation step, in accordance with certain embodiments of the present technique, Figure 8 show's a representation of a noise camera in accordance with certain embodiments of the present technique; Figure 9 shows a representati on of a road scene within a field of viewy as recorded by a noise camera configured in accordance with certain embodiments of the present technique; Figure 10A shows a representation of a part of the road scene of Figure 9 as recorded by the noise camera configured in accordance with certain embodiments of the present technique; Figure 10B shows a representation of a part of the road scene of Figure 9 as recorded by the noise camera configured in accordance with certain embodiments of the present technique; Figure 11A shows a representation of a part of the road scene of Figure 9 as recorded by the noise camera configured in accordance with certain embodiments of the present technique; Figure 1 IB shows a representation of a part of the road scene of Figure 9 as recorded by a noise camera configured m accordance with certain embodiments of the present technique; Figure 12 show's a representation of processing steps performed on documentary evidence generated by a noise camera according to certain embodiments of the present technique; Figure 13 illustrates a first example process in accordance with at least some arrangements of embodiments of the present technique; Figure 14 illustrates a second example process in accordance with at least some arrangements of embodiments of the present technique; Figure 15 illustrates a third example process in accordance with at least some arrangements of embodiments of the present technique; Figure 16 shows an example of how an estimated location of a noise source (and estimated distance between the noise camera and noise source) may depend on the assumed source height in accordance with embodiments of the present technique; and Figure 17 illustrates how uncorrected and corrected noise levels plotted against may change throughout a video recorded by a tracking camera in accordance with embodiments of the present technique. DETAILED DESCRIPTION OF THE EMBODIMENTS Figure 1 depicts an example system for monitoring noise, which can be used to detect sources of noise emissions exceeding a predetermined limit. For the example shown in Figure 1 the system is monitoring noise at three different locations. The predetermined limit on noise emissions being monitored may be a legal limit. Three microphone and camera apparatus 102, 104, 106, referred to as noise cameras are shown, each comprising a microphone 102a, a camera 102b, and processing circuitry 102c. Each noise camera 102, 104, 106 monitors sound at the different locations where they are disposed and when a trigger event occurs, noise camera 102, 104, 106 is configured to transmit information representing documentary evidence by a wired or wireless connection to a server 114. The information representing the documentary evidence may be stored at the server 114 for reviewing by an investigating authority. Noise cameras 102, 104, 106 respectively monitor road scenes 122, 124, 126 where motor vehicles may be observed, such as cars 132, 134, 136. Each of the noise cameras 102, 104, 106 is configured to monitor noise emitted by vehicles within a field of view of the camera. As indicated above, if a vehicle, such as a car 134, creates excessive noise, that is, in excess of the predetermined limit, as detected by a microphone 104a, then this causes a trigger event resulting in documentary evidence to be captured by the noise camera 104, such as a camera 104b which may record images or video as documentary evidence with a recording of the noise emitted by the vehicle so that the vehicle can be identified. Following the trigger event, the processing circuitry 104c may store information representing the documentary evidence such as a video feed from the camera 104b. In some examples the trigger event causes a processing apparatus 104c to store information representing sound and images and a video as the documentary' evidence of a predetermined duration, such as 5 seconds, which may follow in time the triggering event i.e. be later in time than the triggering event (after), or in other examples may precede the triggering event i.e. be earlier in time than the triggering event (before) or both. The processing circuitry 104c may access a rolling buffer of camera data, and transfer information from the rolling buffer of a predetermined duration to a permanent storage medium. In yet further examples, the processing apparatus may transfer to a permanent storage medium a duration of camera information and audio information that precedes and follows the triggering event of the camera. That is, the processing apparatus may record permanently in some examples information that covers an occasion of the triggering event, beginning before the triggering event and ceasing after the triggering event. This may form part of the documentary' evidence transferred to the server 114 for processing. The trigger event may be that noise exceeding the predetermined limit or threshold has been detected by a microphone (audio detector) such as the microphone 104a. This limit or threshold, the breach of which indicates a trigger event for the noise camera and resulting in recording and / or transmission of information, will be referred to below as a trigger threshold. This trigger may be predetermined, and may be alterable as to the specific level of noise at which the system is triggered. In some instances, the microphone 104a, or processing circuitry' 104c, may perform “A-weigh ting” of recorded noise levels to account for a perceived loudness to human hearing of different frequencies before comparison of noise levels with the predetermined trigger threshold. In some scenarios audio signals input to the trigger system may be recorded across a wide range of frequencies, or only over a narrow range of frequencies. In some scenarios, it may be set as a fractional octave band or narrow band, for example a one third octave band for triggering of the camera 102, 104, 106 and transmission of the information to the server 114. A band pass filter, or in other examples a plurality of band pass filters, may be used to select a range of frequencies for monitoring and / or recording. Embodiments of the present technique can provide a noise or sound camera comprising a plurality of audio detectors such as microphones which are spatially disposed with respect to an imaging device such as a camera, preferably a video camera. Although the imaging device in some embodiments is a video camera, in some examples, the imaging device may be a stills camera. Tire imaging device / video camera is referred to in the following description as a tracking camera, because according to example embodiments the plurality of audio detectors of the microphone array are arranged to detect a location of a sound source within a field of view of the tracking camera. The sound source may be a noise source such as a noisy vehicle, which is emitting sound, which exceeds a predetermined limit such as a legal threshold for noise emissions from a vehicle. The tracking camera may therefore be different from a detection camera, which captures an image of the noise or sound source for identifying the noise or sound source from images captured by the detection camera. For the example of detecting a vehicle emitting noise which exceeds a threshold, the image captured by the detection camera may be used for number plate recognition (AX PR) As will be appreciated in the following description the terms sound and noise may be used interchangeably. Embodiments of the present technique can provide a system for detection and processing of information (documentary evidence) related to a dominant noise source for more accurate detection and identification of the dominant noise source, including a distance between the identified dominant noise source and the noise camera, as will be apparent, from the description below. However, the present technique is not limited by the examples given to an application in the field of detecting vehicle noise, and applications of the example embodiments for other purposes may be possible. For example, the present technique may be adapted for use in a security capacity to detect an intruder for example from sound emissions. By using a detection camera for identifying the noise source, which is separate from the tracking camera, the field of view of the tracking camera may be adapted for tracking the sound / noise source across a scene, such as a section of road in the case of a vehicle and so configured to capture a wider angle view. In some examples, the tracking camera may have a fisheye lens or form a fisheye view. In contrast, the detection camera may have a narrower field of view and focus on a region within the scene such as a section of the road in order to have a greater possibility of identifying the vehicle from its number plate for example. The detection camera may be positioned such that a field of view of the detection camera overlaps, at least in part, with a field of view' of the tracking camera. As will be explained m the following paragraphs, the audio detecting array, for example a plurality of microphones, may be disposed with respect to a position of the tracking camera so as to be spatially-separated with respect to a position of the tracking camera, so that a location of the noise source may be detected from a time difference of arrival of sounds emitted by the noise source. The microphone array for identifying and tracking the noise source as a dominant noise source within a scene will be referred to as a Halo device, because a mounting of the microphone array can be on an elliptical structure, so that the microphones can be positioned on orthogonal axes with respect to the tracking camera. As such, an audio detector such as a microphone for detecting that noise emitted by the noise source has exceeded a predetermined threshold, may be separate from the Halo device. For this reason, a higher quality / more expensive microphone can be deployed for accurately detecting an infringing noise source. In the following description, the microphone, which is used to detect an infringing noise source will be referred to as a detection microphone. This detection microphone may be of sufficient quality such that, together with the processing circuitry; it meets the Class 1 performance specification of the international standard, IEC 61672-1. In other examples, the audio detector may be equipment employing a laser or radar technology to detect sound at a distance. Ilie term audio detector can be any detector for converting sound or vibration into an electrical signal representative of the sound. As indicated above, embodiments of the present technique can provide an improvement in generating documentary' evidence which can be used to identify more accurately a vehicle which is emitting noise above a predetermined limit such as a legal limit (infringing noise source), or which is emitting noise likely to cause a public nuisance. The predetermined detection threshold may therefore be the legal limit. Furthermore, embodiments of the present technique can provide an additional improvement in enabling the determination of a distance of the vehicle which is emitting noise above the predetermined limit (i.e. a distance from the noise camera at which a particular noise level is measured). Such embodiments address the problem of determining vehicles which infringe limits set out by legislation (e.g. such as that in New York) which requires measured noise levels to be adjusted to a fixed distance as described above. In United Kingdom Patent No. 2628675 [1], the contents of which are hereby incoq^orated by’ reference, the presently' named inventors described a noise monitoring system which includes one or more noise cameras, each of the noise cameras comprising a tracking camera / imaging devices for recording images and / or video within a field of view of the tracking camera, an audio detector array comprising a plurality of tracking audio detectors, each of the plurality of tracking audio detectors being spatially separately disposed with respect to the tracking camera and each being configured to detect noise from a noise source within a field of view of the tracking camera, and a processing circuitry'. The processing circuitry of the noise camera defined in [1] is configured to receive signals representative of the noise detected by each of the tracking microphones of the microphone array, to determine based on a time difference of arrival of the noise received by each of the tracking microphones, from the received signals representative of the noise, a location of the noise source within the field of view' of the tracking camera, and to map the determined location of the noise source in the field of view' of the tracking camera into images and / or video captured within the field of view of the tracking camera from which the noise source can be tracked. According to some examples in [1], for each of a sequence of image frames of tracking video, a pixel location value identifies one or more pixels. The pixel location values may therefore identify’ the noise source in successive frames, although there may be some discontinuity' in that some frames may not have a pixel location value because there is no noise source which exceeds a minimum value. The discussion below with reference to Figures 2Ato 12 broadly corresponds to that which is disclosed in [ 1], While the contribution defined by embodiments of the present disclosure includes solutions and techniques not disclosed in [1], those skilled in the art would appreciate that, nevertheless, in some examples and arrangements of embodiments of the present disclosure, at least some of the techniques described in [1] may also be utilised. Discussion of the subject-matter defined in [1] is therefore included below with reference to Figures 2A to 12, although this is not intended to be limiting to the further discussion of embodiments of the present technique, nor essential to the operation thereof. Certain embodiments of [ 1] - to which embodiments of the present technique may also correspond - can track a location of a noise source within a field of view' of a tracking camera, which may be considered as a noise space. This allows an observer to track a noise source in both a noise space and a corresponding image of a tracking camera simultaneously, which may’ assist in identifying a source of noise in excess of a predetermined threshold. For example, embodiments of [1] may assist in a scenario such as two vehicles passing a noise camera at the same time, when at least one of them is producing noise in excess of a predetermined threshold, since the tracking of location of a noise source in noise space overlapping with or corresponding to a field of view of a tracking camera may enable an investigating authority to distinguish between the two different vehicles in this scenario. Such a noise source exceeding a threshold in the field of view can be referred to as a dominant noise source. Figure 2A depicts schematically a noise camera 202 similar to the noise cameras 102, 104, 106 of Figure 1, according to example embodiments with Figure 2B representing an example implementation. The noise camera 202 is depicted comprising a microphone 204, two detection cameras 206, 208, processing circuitry 210, antenna 212, communications circuitry 214, and a power supply 216. This is an example of the noise camera of Figure 1 employing a different method of communication with the server 114, as can be seen by the inclusion of the communications circuitry’ elements that are present in Figure 2 but not present in Figure 1. Figure 2B shows an example implementation of the schematic noise camera of Figure 2A, showing the noise camera as installed at a roadside location. Figure 2C shows an example of recorded noise by a microphone such as a detection microphone 204. This noise is detected by the microphone and, in the example shown, sound is filtered by three bandpass filters, generating data for a volume with respect to time of an electrical signal representing sound of each frequency, frequency 1, frequency 2, frequency 3. These are plotted here as frequency 1, frequency 2 and frequency 3, but in other examples a different number of bandpass filters may be used, and hence a different corresponding number of plots of volume or amplitude against time may be generated. In some examples, a single bandpass filter may be used to filter the noise / sound, and a single plot of volume or amplitude against time generated, such as a bandpass filter passing frequencies in a narrow band centred on 400 Hz. In yet further examples, other types of filter may be used, such as low pass or high pass filters but it may be preferable to employ a bandpass filter. Dotted lines 221 and 222 designate boundaries of a start and an end of a region around a peak of volume for the frequencies plotted in Figure 2C, The volume peak for frequencies may be determined by reference to a threshold volume. For example, a peak may be determined by the highest volume of a first frequency, and there may also be a condition that a second frequency is above a threshold volume in addition to the highest volume of the first frequency. This may be extended to multiple frequency plots, as in Figure 2C. In Figure 2C, a peak volume may be determined as a long dashed line 223. This may be determined by the processing circuitry 2.10 as the highest volume recorded in frequency band 1, while frequency band 2 and frequency band 3 are above a predetermined volume threshold. A region around the volume peak may then be determined by identify ing time resources for which the volume of one of, more than one of, or all of, the frequency bands is greater than a threshold, where the threshold may be the same threshold that was used as a precondition for determining the peak volume. Alternatively, a region around a peak volume may be determined as a preset amount of time resources to either side of the peak volume, for example 5 seconds. In some implementations, the region around a peak volume may be determined as an offset preset amount of time resources to either side of the peak volume, that is, the amount of time resources included in the region around a peak volume may be different before the peak as opposed to after the peak. For example, it may be decided that a period of 3 seconds before a peak volume and 7 seconds after a peak volume should be designated as the region around a peak volume. In yet another example, a region around a volume peak may be determined with reference to a volume peak, for example the region being defined as time resources for which the volume of a particular frequency band is -within a certain offset from the volume peak. For example, with reference to Figure 2C, the volume peak 223 may register a volume of 80 dB, as indicated by a first volume reading 224. The region around a volume peak may then be determined as continuous (or in other instances, non-continuous) time resources which are within a certain offset of the volume peak. In the example of Figure 2C, the certain offset is 3dB, as indicated by arrow 226, and the corresponding time resources are those indicated by second volume reading 225. In some examples, a single bandpass filter is used, which may pass frequencies between 300 and 500Hz. Samples may be taken at different rates. In some examples, a volume sample may be taken at a rate of one sample per second, or a sample rate may be more or less frequent such as ten times per second. In some examples, such as where a Class-1 microphone is used to record the sound, it may be that a sy stem is triggered not across a wide spectrum such as between 300-500Hz, but at a specific fractional octave band frequency of 400Hz. Other frequencies may be chosen, but it may be preferable to select a frequency of 400Hz to use as a trigger frequency, since this may correspond to a dominant frequency emitted by an exhaust system of a vehicle. In one example, the processing circuitry may implement a counter to determine whether two exceedances of a threshold are to be considered as a single trigger event or as two separate trigger events. In this example, a sample rate of volume is one sample per second. A counter increments for each sample where the volume is recorded as below the threshold, i.e. one integer increment per sample recorded below the threshold. If a sample is recorded and the volume is greater than the threshold, then the counter may be reset to zero. For a sample volume recorded as greater than the threshold, the processing circuitry 210 may check a value of the counter, and determine whether the sample should be classified as a separate trigger event or a continuation of a previous trigger event. In this example, the processing circuitry' checks whether the value of the counter is greater than or equal to a value of two. If the value of the counter is greater than or equal to the value of two, then the processing circuitry may determine that the sample belongs to a separate trigger event and not classify it as a continuation of a previous trigger event. However, if the value of the counter is equal to zero or one, that is, the value of the counter is not greater than or equal to a value of two, then the processing circuitry may determine that the sample indicates a continuation of a previous trigger event. In this example, there may be a gap of up to two seconds between exceedances of a threshold that may still be considered to be part of tire same trigger event. If two exceedances are separated by a gap of three or more seconds, the processing circuitry may determine that these correspond to different trigger events. It should be noted that the time values of the above example may be adapted. For instance, it may be determined that in some cases two trigger events are being recorded for a single vehicle passing the noise camera in a single pass, and a value which the processing circuitry' compares the value of the counter to may be increased, for example to three. This may result in exceedances of up to three seconds being classified as a single trigger event, hi other examples, the value which the processing circuitry uses to compare with the value of the counter may be reduced to one, which may result in exceedances separated by two seconds being classified as separate trigger events. Camera and Microphone Array System (Halo) Figure 3 depicts schematically' a noise camera of Figures 2 A and 2B, according to an example arrangement which is described in [1], and which may also configured to operate in accordance with certain arrangements of the present technique. Similar features shown in Figure 2A are identified with the same references and so an explanation of these features will not be repeated for the sake of brevity. As shown in Figure 3, the noise camera includes an audio detector array, such as microphone array 320. The microphone array 320 includes a plurality of tracking microphones (tracking audio detectors), which are spatially separately disposed with respect to the tracking camera 322. For the example shown in Figure 3 there are four tracking microphones m the microphone array Xi, X -. Yi, and Y?. In this example, each of respective pairs of tracking microphones Xi, X and Yi, Y2 are arranged respectively on axes 324 and 326 which, in this example, are perpendicular to each other so that each respective pair of tracking microphones Xi, X2 and Yi, Y2 is configured to detect sound with respect to a plane formed with respect to each of the orthogonal axes. In one example the first plane formed by the first pair of tracking microphones Xi, X2 is a horizontal plane and the second plane formed by the second pair of tracking microphones Yi, Y2 is a vertical plane. It will be apparent to the skilled person that the same technical effect of a determination of a noise source location in a noise space corresponding to the field of view of a tracking camera may be achieved by a different number of tracking microphones arranged in an array. For example, in some arrangements, 3, 6, or 8 tracking microphones may be used, and tracking microphones may be grouped in different ways than set out in the present disclosure. For example, three microphones may be arranged in a triangular arrangement, with a microphone situated at each vertex of the triangle, while in other examples the microphones may be situated in self-contained pairs. In these and other examples, the planes formed by a pair of tracking microphones may be intersecting but not orthogonal. In the example of Figure 3, tracking microphones X, and X2 are arranged on a first, horizontal axis of an array structure, and tracking microphones Yi and Y2 are arranged on a second, vertical axis of an array structure. The audio detectors, in tins case tracking microphones, are configured to detect sound / noise in a noise space corresponding to a field of view of the tracking camera, the noise originating at a dominant noise source such as a vehicle. According to the example arrangement shown in Figure 3, the tracking camera 322 and the microphone array 320 are arranged to provide additional signals from which a noise source can be tracked within a fi eld of view of a tracking camera determined with respect to a time difference of arri val of sound detected by the respective tracking microphones in the array. Together the tracking camera and microphone array may be referred to as a Halo system in the disclosure since the pairs of tracking microphones are disposed with respect to a supporting frame around the tracking camera in the form of an oval or Halo. The tracking camera 322 captures within a field of view of the tracking camera a part of the road scene, similar to road scene 122, 124, or 126, which allows for correlation of audio information related to a road scene detected by the tracking microphones Xi, X2, Yi, and Y2 with image and / or video information of the same scene. A separation of two tracking microphones (audio detectors) acting as a pair of tracking microphones may be between 0.1m and 1.5m, preferably between 0.4m and 0.6m, and may differ depending on an orientation of the pair of tracking microphones. For example, a separation of a first pair of tracking microphones in a first direction, such as a horizontal direction, may be greater than a separation of a second pair of tracking mi crophones in a second direction, such as a vertical direction. In one example, a separation of a first pair of tracking microphones in a horizontal direction is 0.6m and a separation of a second pair of tracking microphones in a vertical direction is 0.4m. As will be explained, sound signals detected by the tracking microphones are used to identify a location of a noise source within the field of view' of the tracking camera. Accordingly, in some arrangements the tracking camera may include a wide angled lens such as a fisheye lens so that a field of view' of the tracking camera can include an entire section of a road within which a noise source can be tracked in order to provide additional evidence of an infringing activity. Ilie tracking camera may therefore differ from detection cameras 313,314 which may be positioned and configured to capture a narrower view within the road scene and within the field of view of tire tracking camera in order to identify for example a number plate / licence plate of the vehicle which may be infringing a noise restriction. However, as will be appreciated, advantageously a detection point of a noise source can be within a tracking path identified by the tracking camera field of view and a noise space corresponding to the field of view-’ of the tracking camera and tracked by the tracking audio detector (tracking microphone) array. Processing steps in relation to the tracking camera and microphone array are performed by processing circuitry 330, formed as part of the tracking camera and microphone array (Halo). Also shown in the example of Figure 3 are two lookup tables 331 and 332, which are respectively lookup tables associating time differences of arrival with a pair of angles and associating a pair of angles with a pixel in a view' of the tracking camera. These processing steps will now be described with relation to Figure 4, Figure 4 shows a flow' diagram of processing steps carried out by the processing circuitry 330 on information gathered by the microphone array, although it will be apparent to the skilled person that certain steps of the process described below may be omitted or performed in a different order without departing from the subject of the disclosure. A process depicted in Figure 4 begins with step 400 before processing passes to step 402. During operation, a step 402 includes a tracking camera and a microphone array sending information including, but not limited to, audio information and video information gathered by tracking microphones and the tracking camera 322 to the processing circuitry 330. That is, signals representative of the noise detected by the tracking audio detectors Xj, X? and Y], ¥2 are sent by the audio detector array 320 and tracking camera 322, and received by the processing circuitry' 330. The sent information is received by the processing circuitry’ 330, before processing passes to step 404. In step 404 the processing circuitry performs filtering of audio, for example using a bandpass filter or plurality of bandpass filters, thereby excluding certain frequencies of the audio information and passing other frequencies. In other examples, different filters may be used, such as a high-pass filter, or a low-pass filter. In some examples, a plurality of filters may be used so that a wide range of frequencies are passed through the filter, which may give a greater sense of the character of the noise received by the tracking microphones. For example, noise created by’ a large vehicle such as a bus, HGV or the like may have a particular profile of volume with respect to frequency, and a vehicle such as an emergency vehicle with a siren enabled may have a different profile of volume with respect to frequency, for example being dominated by a peak in volume at the frequency of the siren in use. In contrast, a noise received by the tracking microphones generated by a motorbike, sports car, a tuned exhaust system and so on may have a different profile of volume with respect to frequency. Using multiple filters may enable a more precise profile of the noise to be collected, and consequently a more accurate determination of the source of the noise to be made as it allows the tracking to be focussed toward a source of a particular type of noise. For example, filtering of the noise may allow? selection of frequencies not including a frequency of an emergency vehicle siren, with the result that emergency vehicle sirens are not registered as a dominant noise source in a part of a road scene, since it may not be an object of an investigating authority to investigate such events. In step 406, the processing circuitry' 330 performs processing on the audio signals received in order to determine a time difference of arrival (TDOA) of the audio signals at the tracking microphones of the microphone array. This may be done by processing audio signals containing a volume peak with a generalised cross correlation using Fourier Transforms betw een pairs of the audio signals, for example comparing two tracking microphones arranged on a horizontal axis of the microphone array, and separately comparing two tracking microphones arranged on the vertical axis of the microphone array. This produces a TDOA for a first (horizontal) plane and for a second (vertical) plane, which define intersecting planes in a noise space, and hence a single line of points in noise space w'here the source of the noise may be located. It is envisaged that the microphone array herein described will be mounted at a height above the vehicles of the road, in some examples at a height of between 4m and 8m, for example approximately 6m, to allow for identification of vehicles on the road from images within the field of view' of the tracking camera and within a noise or sound space corresponding to the field of view of the tracking camera. A greater height allows for a larger section of road to be covered by the field of view of the tracking camera, but results in a greater length of road being covered by an edge of a view of the tracking camera, where distortion caused by the lens may be greatest. Following the processing of the TDOA of audio signals in step 406, processing proceeds to step 408 wherein angles of the noise source are obtained from the TDOA of the noise generated by the noise source. As part of reception of noise by the tracking microphones, analogue sound is sampled at a certain rate, for example 48,000 times per second. When a single noise source produces sound that is received at two spatially separated microphones, a difference in path length between the noise source and individual tracking microphones leads to a TDOA, which may be expressed in terms of a number of samples. For example, if a volume peak is found to have been received at one microphone a certain peri od of time before it is received at a second microphone, the certain period of time, based on the digital recording of it, is always expressible as an integer number of samples. In one example this may be 5 samples, which would correspond, in the above example of 48,000 samples per second, to a TDOA of approximately l / 10000th of a second. As part of a setup and calibration procedure (described below), the processing circuitry 330 may be provided with a lookup table 331 for each of the planes in which the microphone array records a TDOA; a first vertical TDOA lookup table and a first horizontal TDOA lookup table (collectively referred to as a first lookup table), in the example of Figures 3, 4 and 5. This lookup table may have associated with a particular value of TDOA for each of the planes an incident angle of dominant noise at the microphone array. For example, it may be that a TDOA of 5 samples corresponds to an incident angle of 10° from a coordinate axis centred on the microphone array. It should be noted that the first lookup table has values for TDOA with respect to a first and a second plane, which are interdependent. Tire two TDOA values for the two planes are related to each other by a location of the noise source when considered in the first (horizontal) and second (vertical) planes, because they are generated from sampling the same noise source. This may be more readily understood with reference to Figures 5 and 6. As will be appreciated, implementing a conversion of the TDOA values for the two planes into a pair of angles and a pair of angles into a pixel values can be implemented using other techniques. Using a lookup table provides a computationally efficient technique for implementing the conversion, although in some embodiments of the present disclosure, a direct calculation may be performed mathematically for each sample of the TDOA values. For each image recorded by the tracking camera, an angle is determined for each plane from the camera to the noise source. Figure 5 shows the Halo array 320 of Figure 3, and a noise source represented by the car 510. From the car 510 there are depicted dashed lines, 521, 522, 523, 524, indicating a direct path between the car 510 and each of the tracking microphones of the Halo array 320. These direct paths are indicative of, for example, a path traversed by sound from the car 510 to the tracking microphones of the Halo array. Figure 6 shows a similar view of the microphone array to Figures 3 and 5, but with a set of axes imposed. That is, there is imposed on the view of the Halo array and the source of the noise, the car 510, a set of axes defined as a first axis, x-axis 608, a second axis, y-axis 609, and a third axis, z-axis 607. These axes are mutually orthogonal and define a three dimensional noise space centred on the origin of the axes, which in this example is chosen to correspond to the location of the tracking camera 322. The x-axis 608 lies in the plane of a Halo array 320, and both .Xi and X2 tracking microphones lie on the axis. Similarly, the y-axis 609 also lies in tire plane of the Halo array 320, with tracking microphones Yi and ¥2 on the axis. The Halo array 320 therefore lies on the x and y axes 608, 609 of the set of axes. The z-axis 607 lies directly out of the plane of the Halo array 320 toward the source of the noise, the car 510. The direction of the car 510 from the centre of the Halo array 320 is indicated by arrow 602. Since the car 510 in this example is a source of noise detected at the Halo array 320, the arrow 602 is an incident direction of the noise produced by the dominant noise source at the Halo array 320. The direction of the arrow 602 with respect to the axes can be defined m a number of ways, as the skilled person would appreciate. In the example of Figure 6, the direction of the noise source 510 is defined with respect to the z-axis 607. That is, the direction is defined by two angles represented by arrows 621 and 622 defining tire displacement from the z-axis 607. A first azimuth angle in the direction of the x-axis 608, also represented in Figure 6 by the quantity, a, is represented by the first arrow 621, and the result of the transformation by this angle is the dashed line of 620. A second vertical angle in the direction of the y-axis 609 is represented in Figure 6 by the quantity p and by the second arrow 622, and the transformation from the dashed line of 620 to the arrow 602 in the direction of the noise source 510 is defined by the second angle. In other words, in an example where the first arrow 621 represents an angle of 20° and the second arrow 622 represents an angle of 10°, the direction of the dashed line 621 is defined by being displaced 20° in the positive x direction from the z axis 607, and 10° in the positive y direction from the z axis 607, That is, in the example of Figure 6, a = 20° and p = 10°. As described above, there are other methods of defining these angles that could be implemented by the skilled person. For example, the angles might be defined from the y axis or from the x axis, or from another predetermined line, which may be set with respect to a road scene as viewed by the tracking camera, for example centred on the middle of a road observed by the system. Reluming to Figure 4, and processing step 408, an incident angle of the noise source at the microphone array with respect to a predetermined reference line is determined. In the example of Figure 6, z-axis 607 is tire predetermined reference line. This determination is performed by the processing circuitry 330 of the microphone array, or in some examples, by the processing circuitry of the noise camera, with reference to the above-mentioned first lookup table 331. This gives a measurement for the angles of, in this case, an azimuth angle and a vertical angle defining the direction of the noise source with respect to the predetermined reference angle, which as described above in the example of Figure 6 may be the z-axis. Following this processing step 408, the processing proceeds to a mapping step 410, in which an incident angle, that is, angles determined in the previous step 408, of a noise source in a noise space corresponding to a field of view of the tracking camera is mapped to a pixel of a scene captured by the tracking camera. This step of mapping a pair of angles to a pixel may be computed for each pair of angles, or it may comprise use of a lookup table such as second lookup table 332. This step may be altered and simplified in certain scenarios, for example if the output of the tracking camera is a rectilinear image. However, this mapping step may be necessary in this form if the output of the camera is a distorted image, such as the output of a wide angle camera, one which uses a fishey e lens or equivalent. The mapping step 410 may map the angles determined in step 408 to a pixel of an image captured by the tracking camera 32.2, within a field of view of the tracking camera 322, which corresponds to a noise space, which is a space formed by possible values of the pairs of angles determined by the microphone array. The image captured by the tracking camera may be, for example a frame of a video such as that recorded from the tracking camera 322 situated as part of the Halo (tracking camera and microphone array). In other examples more than two angles may be determined, one for each of more than two planes which map a noise source into a noise / sound space. Thus the angles may be a group of angles, a pair being one example. As will be explained below, the second lookup table 332 may be preconfigured with a mapping between pairs or groups of angles and pixels in the field of view of the tracking camera 322. This preconfiguration of tire second lookup table 332 may be performed by a calibration process explained below which involves positioning the tracking camera 322 so that within the field of view of the tracking camera 322 is calibration image (for example, an image of a checkerboard) which is a grid of lines such as in Figure 7 A, with marked grid intersections, providing intersections between the lines of the grid. For each intersection, a pixel representing that intersection is identified and added to the lookup table 332. Further detail on a calibration and setup process are outlined below. During the mapping step 410, the processing circuitry 330 may perform a search of the marked intersections for the four intersections closest in angle to the angles determined in step 408 of Figure 4 and thus the surrounding area of line 602 can be determined. In the representation of Figure 7B, a black dot 720 represents the line 602 as seen from the camera 322 of the camera and microphone array, and white dots 721a-d represent the intersections of the grid lines. Following the determination of the four closest intersections of the grid to the line 602 as represented in Figure 7B by the four white dots, the processing circuitry 330 may perform a step of linear interpolation between the four grid points to provide an accurate determination of the location of the line 602 represented by the black dot 720 in terms of the pixel representing the direction of the line 602, and henc* of the direction of the noise source from the noise camera. A calibration process for the tracking camera 322. and microphone array 320, performed by the processing circuitry 330, may be performed once for each a specific arrangement and values for microphone separation and position, audio sample rate, and video resolution. The calibration process may be broadly thought of as the creation of one or two lookup tables; one associating time differences of arrival with incident angles, and a second associating incident angles with a pixel of a camera such as the tracking camera 322. Following the mapping step of 410, processing passes to step 412. In this step 412, the processing circuitiy 330 of the tracking camera 322 and microphone array 320 may apply a threshold to determine whether an indication of an incident direction of noise from a dominant noise source should be added to information recorded by the tracking camera before the information is transmitted to the processing circuitry 210, 315. That is, noise levels of the tracking microphones may be averaged, or in some examples, noise levels of only some of the tracking microphones may be averaged, to give a general noise level. Uris may be compared to a threshold, such as, for example, a threshold corresponding to approximately 45 decibels (dB). The processing circuitry' 330 may determine that if the noise level exceeds the threshold, that a pixel location value should be added to information collected by the tracking camera and the information then transmitted to the processing circuitiy 315,210, and processing proceeds to step 414. However, the processing circuitry- 330 may determine that, if the noise level does not exceed the threshold, the pixel location value should not be added to information collected by the tracking camera and only information collected by the tracking camera should be transmitted to the processing circuitry- 210, 315, processing proceeding to step 416 directly as indicated by arrow' 413. Tire level of the threshold applied may be predetermined during a setup procedure, and may be adapted based on an average volume of a period of recorded noise by the tracking microphones. As described above, if the processing circuitry 330 determines that a pixel location value should be added to the information recorded by the tracking camera, processing proceeds to step 414, where the indication is added. In this step 414 an indication of a location of a pixel representing a direction of the noise source may be provided in combination with an image, which may be a frame of a video. For example, the indication of a pixel may be a representation of a marker overlaid on the pixel, such as a red dot to indicate the noise source, and the image may be a frame of a video captured by the camera 322 of the noise camera. In this example, a single output is produced combining the information of the microphone array and the tracking camera (Halo system), which can be subsequently used for further processing (explained below). In other examples, a pixel coordinate may be provided instead of a visual marker, such as pixel (100, 100) of the image, or a pixel number may be provided. This could be displayed or not displayed on the image, as the case may be, and the information may be added to the image file forming the documentary evidence associated with a trigger event. In an example arrangement the image to which the indicated pixel belongs is an image from the tracking camera forming one frame of a video recorded by the tracking camera. In this example, the process of Figure 4 may be performed with respect to each frame of the video, providing an indication of the dominant noise source in a noise space corresponding to the field of view of the tracking camera for each frame of a video recorded by the tracking camera 322. In some examples, it may be that not every frame of a video has an individually calculated marker. In the case where the image is a frame of the video captured by the camera 322, a single marker may be used for multiple frames. For example, a marker may be calculated for every second frame of the video captured, or every third frame of the video, or so on. This has obvious benefits in reducing an amount of processing required by the processing circuitry 330 and may still allow the noise source to be identified from the image, as necessary. Following processing step 414, processing proceeds to processing step 416, where the process terminates. In other examples, processing may proceed to step 416 and terminate without performing and passing through step 414, as shown in Figure 4 by arrow 413. The example arrangements described in [1] and described above with reference to Figures 3 to 7 provide a process by which audio information may be used to provide information as to a dominant noise source in a scene, which may be concurrently imaged by a camera, thereby providing both visual and auditory information, collectively referred to as documentary evidence, as to a dominant noise source in a scene such as a road scene. This has benefits in enabling the identification of a dominant source of noise if noise in excess of a predetermined threshold is recorded in a scene, which may assist an investigating authority in determining if action needs to be taken against the controller of the dominant source of the noise. Certain steps in the process performed by the processing circuitry 330 may be performed in an order other than the order presented above, may include certain steps omitted above, and / or may include certain altered steps of the process, such as the mapping step 410. For example, the mapping step 410 may be altered if an incident angle of a dominant noise source does not require mapping to correct for distortion of a tracking camera, such as if the tracking camera uses a wide angle, but not a fisheye, lens. In other example arrangements, step 404 of the process representing a filtering of audio information may be omitted, for example if audio information received by the processing circuitry 330 in step 402 has already been filtered by the tracking microphones. According to the above example two separate lookup tables 331, 332 are used in the steps of mapping the TDOA measurement to the pairs or groups of angles and a separate step of mapping the groups of angles into one or more pixels identifying the dominant noise source in each video frame. This corresponds to the operations performed above in the flow diagram of Figure 4 with reference to steps 408, 410. However, as will be appreciated, other implementations are possible. For example instead of using two lookup tables, a single lookup table can be used to map the TDOA values into the one or more pixel values identifying the location of the dominant noise source in each tracking image, which may be video frames. In some arrangements of the above process, the tracking camera may be an internet protocol (IP) camera, and there may be a latency associated with such a tracking camera. In this example, the latency may be approximately 2.5 seconds, whereas a latency associated with audio information may be significantly less. In this example, the processing circuitry 330 may add blocks of audio information received from the tracking microphones to a buffer, and associate each block of audio information with a timestamp according to a time of a recording of the audio information. Then, the processing circuitry 330 may perform processing on the audio information in accordance with the above-described process. At a time when the latency associated with the information recorded by the tracking camera has elapsed, the processing circuitry 330 may receive the information recorded by the tracking camera, which may also have a timestamp associated with it. The processing circuitry 330 may then call from a buffer audio information with an associated timestamp, which may, in between being recorded by the tracking microphones and calling by the processing circuitry 330, have been processed by the processing circuitry 330. Thus, the audio information may be in a number of different forms. It may be in the form of raw audio information as recorded by the tracking microphones, or it may be in the form of a number of samples denoting a TDOA for each pair / group of tracking microphones, or it may be in the form of a pair of angles associated with the corresponding TDOAs, or it may be in the form of an indication of a location of a pixel of a view as recorded by the tracking camera, or another form. Following calling of the audio information, the processing circuitry 330 may proceed to complete processing of the audio information, if processing has not already completed, and a resulting, or called, pixel location value may then proceed to be added or not added to the information recorded by the tracking camera. That is, the processing circuitry 330 may receive the information recorded by the tracking camera before step 414 of Figure 4. If the information recorded by the tracking camera is received by the processing circuitry 330 before completing step 412, then the processing circuitry 330 may proceed to complete steps up to step 412 before adding or not adding a pixel location value to the information recorded by the tracking camera. Example Deployment of Noise Camera The processing circuitry 315 of the system is capable of receiving information from a tracking camera 322 and a microphone array 320 as a single information input, similar to inputs from detection cameras 313 and 314, or microphone 312. As described above, the processing circuitry 315 may then transmit tins information, along with information from the detection cameras 313 and 314 or detection microphone 312 as documentary evidence to a server, such as server 114. As explained above, packages of information generated by the noise camera, including tracking and detection cameras and microphones may be referred to as documentary evidence, for example, where there has been a possible infringement of noise emission limits. An example arrangement of a noise camera which may be configured to operate in accordance with embodiments of the present technique is shown in Figure 8. Figure 8 shows a system 800 mounted on a piece of road furniture 801, with a detection microphone 802, detection camera housings 804, 806, processing circuitry 808, and a Halo system 810 made up of a tracking camera 812 and four tracking microphones 814, 816, 818, 820 forming a microphone array. This system, in transmitting information to the server 114 of Figure 1, may report multiple pieces of information as documentary evidence at the same time. For example, the system 800 might report video information gathered from cameras housed within one or both of the detection camera housings 804 and 806. In addition, the system 800 could report information gathered from the tracking camera 812 and microphone array 810, and / or information gathered from the microphone 802. As indicated above, following a trigger event, information is generated as part of the documentary' evidence and sent to the server for processing. Although detection camera housings 804 and 806 are each pictured in Figure 8 as a single camera housing, there may be instances where a single detection camera housing contains a plurality of cameras, for example, two detection cameras. That is, the detection camera housing 804 may contain two detection cameras, providing two views of a same area of road scene. In a similar manner, the detection camera housing 806 may also provide for housing a plurality of cameras, for example two detection cameras providing a view of a different part of a road scene to detection camera housing 804. In some scenarios, two cameras within the same housing may image the same section of the road scene. The cameras contained within the same housing may be differentiated by having a different purpose, for which they may have set different physical parameters. For example, a first camera within the housing may provide a magnified version of the same view provided by a second camera, or a view with a restricted field of view in comparison to the second camera. In other examples, the first camera may also have a filter applied to it, or may have different processing applied to data that it collects. In an example depicted in Figure 9, a view of a road scene 900 is shown as imaged by a wide angle lens on a camera, such as may be achieved by tracking camera 322 described above if fitted with a wide angle lens. This imaging process causes a distortion of the image, and a road 902 in the road scene 900 is seen to be wider at the centre of an image than at the edges of the image. As part of the road scene, vehicles such as cars 904, 906 and 908 are imaged and depicted as part of the scene and background elements such as trees 910 and 912 are visible. One of the vehicles imaged in the road scene may be producing noise in excess of a predetermined limit or threshold and it may be an object of a. noise camera installation to identify which of the vehicles is producing such noise. As described abo ve, an installation of a noise camera, tracking camera and microphone array may assist in identifying which of the cars is producing noise in excess of a threshold. 'The installation may be similar to the system described above in relation to Figure 8, and may include several cameras in each of the camera housings 804 and 806 to image the road scene 900. The view of these cameras may be separated from each other and they may be directed at different parts of the road scene to provide greater detail on particular areas of the road scene 900. As shown in Figures 10 and 11, two such views are depicted. Figures 10A and 10B depict a view of the road scene similar to that viewed from a camera within camera housing 804, while Figures 11A and 1 IB may depict a view of the road scene similar to that viewed by a camera within camera housing 806, where each of the camera housings 804 and 806 comprise two cameras as shown in Figure 10A and 10B, and 11A and 1 IB. Figure 10A shows a first view from a first camera within camera housing 804, As will be seen from a simple comparison of Figures 9 and 10A, camera housing 804 and the cameras therein are directed toward a left hand portion 1001 of road scene 900. This is apparent due to the inclusion of the image of the car 1004 and a front portion of car 1008 which correspond to cars 904 and 908 on tire left hand side of the road scene 900 as well as tree 1010 corresponding to tree 910 of Figure 9. In addition to this view depicted in Figure 10A, Figure 10B also shows a magnified version 1020 of the same view, as captured by a second camera within camera housing 804, with a reduced field of view still showing cars 1004, now' 1024, but without showing the front half of car 1008, due to the reduced field of view?. Road 1002 is shown in Figure 10B, but less of the surroundings, such as tree 1010, is visible. In addition, in some examples, as shown here, a filter may be applied to the image by the camera, as can be seen by the darker colour of the image. Other features, such as additional processing, may be applied to the information captured by the second camera within camera housing 804, such as Automatic Number Plate Recognition (ANPR). Similar to the views presented in Figures 10A and 10B are the views presented in Figures 11A and 11B. In terms of the road installation of Figure 9, these two views may be taken from the view of a camera situated within camera housing 806. Camera housing 806 may contain two cameras, as camera 804 detailed above has in this example, and may therefore provide two views of a same region of the road scene. It will be apparent from a comparison of Figure 9 and 11A that the view of camera within camera housing 806 depicted in Figure 11A is a right hand portion of the view' of the road scene of Figure 9, and contains road 1102, car 1106, car 1108, and tree 1110, each of which correspond to features of the former Figure 9. Furthermore, Figure 1 IB shows a magnified and filtered version of the same view as Figure 11 A, as may be captured by a second camera situated within camera housing 806, where the field of view of the camera is restricted to showing only car 1126, corresponding to car 1106 and 906, but not car 908 or 1108, and background elements of the view of Figure 11A are therefore removed from the image, for example tree 1110. In Figures 10B and 1 IB there arc also several predetermined detection points 1030, 1031, 1130 and 1131 as indicated in Figures 10B and 1 IB by spots. These detection points may be predetermined during a setup process of an example of the current system m such a way that they are, as per the example of Figures 10B and 1 IB, in an approximate position occupied by a number plate of a vehicle as it enters or exits a field of view of a camera of the present system. As will be apparent from a comparison of the Figures 10A - 1 IB, locations of the detection points are within a field of view' of the detection cameras, and within a field of view? of the tracking camera. Processing to Identify a Dominant Noise Source As explained above, example embodiments of tire present disclosure can provide a noise camera, which generates documentary evidence after detecting a trigger event. In response to detecting a trigger event, the documentary evidence generated by the noise camera may be transmitted to a server, for example the server 114 shown in Figure 1. According to example embodiments, the documentary evidence generated by a noise camera according to the present technique may comprise video generated by the tracking camera, pixel identification information identifying for frames of the video a location of a dominant noise source (pixel location values), representation of the noise signal as detected by the detection microphone, and video from the detection cameras. In [1], a server and processing methods were defined for receiving documentary evidence from the noise camera following a trigger event, the documentary evidence comprising tracking video, noise source pixel location values comprising, for each of one or more frames of the tracking video, and an indication of at least one pixel of a location of a dominant noise source in the frame of the tracking video (and, optionally, a sound recording of sound associated with the trigger event). The method defined in [1] then proceeds to identify a path of a dominant noise source in the tracking video from the noise source pixel location values, determine a detection time at which the path of the dominant noise source in the tracking video is closest to a detection point in a field of view of a camera which captured the tracking video, and identify the dominant noise source from one or more image frames corresponding to the detection time. According to example arrangements a dominant noise source is identified by a process, which is carried out by processing circuitry such as by a server 114 on received documentary evidence gathered from a noise camera, which includes detection cameras 206 and 208, and tracking camera 322, and microphones such as microphone 204, or 312, or tracking microphones Xi, Xz, Yi, Yz. This process will now be described. As explained, the server 114, with noise cameras 102, 104, 106 form a system as described above. The server 114 may perform a process according to example embodiments of the present technique which can be used in the identification of a dominant source of noise exceeding a predetermined threshold (where such a noise exceeding a predetermined threshold may be deemed to have done so at a particular reference distance), such as a vehicle. This may be readily understood with reference to Figure 12, which shows a flow diagram defining a method described in [1] which comprises processing steps carried out by processing circuitry such as server 114 of Figure 1, with the aim of identifying vehicles, in combination with the further description in [1], The process begins at step 1200, before processing passes to step 1202. In step 1202, an indication of a dominant noise source location may be identified in each of a plurality of successive image frames of the tracking video for display. The indication may, m some examples, be a dot overlaid on the image, centred on the pixel indicated by the pixel location value for that image frame of the tracking video. As such, when a sequence of the tracking video is displayed, the dominant noise source, which triggered the events which generated the documentary evidence may be presented to a viewer. However, the pixel location values are also used to identify the noise source as explained below. In other examples, the indication may be a pixel number or coordinates of a pixel forming part of the image frame, or other appropriate indication of a pixel. Processing then proceeds to step 1204. In step 1204, processing is performed to identify a path of the dominant noise source which triggered the event associated with the documentary evidence from which the noise source can be identified. The path of the pixel location, representative of a path of a dominant noise source is identified from the received pixel location values forming part of the documentary evidence. The path of the pixel location is represented by movement of an indicated pixel across a plurality of image frames of the tracking video captured by a tracking camera such as tracking camera 322. As explained in step 1202, the pixel location of the dominant noise source may be represented as a dot overlaid on a sequence of successive image frames of the tracking video. In this example, the path of the pixel location can be represented as a path traced by the dot in successive frames of the tracking video captured by the tracking camera. However, as well as providing a visual presentation of a path of the dominant noise source, the pixel location values of the noise source are also used to verify that the noise source identified is the noise source which was the cause of the trigger event caused by noise exceeding a predetermined threshold. Following step 1204, processing passes to step 1206. In step 1206, the identified path is compared to one or more detection points, which are within a field of view' of the tracking camera and a detection camera. That is, tire identified path, which may extend to the edge of the viewed scene, may be compared to detection points such as 1030 and 1031 of Figure 10B and 1130 and 1131 of Figure 1 IB. A determination may be made of a detection point that is closest to the identified path of the dominant noise source within the scene. This may be performed by determining a detection point to which the identified path of the indication of the pixel is close to a point or closest to at any point in the identified path. Using the example of Figures 9 and 10, vehicle 904, which was in a previous image to the right of its present location and has travelled along the road from right to left, has a path substantially following a middle line of an upper lane of Figure 9. It may be determined, as seen in Figure 10, that the detection point that this path approaches nearest is detection point 1030, as seen in Figure 10B in an upper portion of the Figure. Processing then passes to step 1208. In step 1208, a detection time is determined which is a time (or image number, or frame number etc.) at wh ich the identified path of the dominant noise source passes closest to the determined detection point. The detection time may be an absolute time, or correspond to an image / frame number. Processing then passes to step 1210. In the processing as explained with reference to Figure 12, up until step 1210, the processing has involved primarily the input as received from the tracking camera and microphone array, and processing data thereof. In step 1210, a corresponding time (or image number or frame number) of a view from a different camera may be identified. For example, an identified view in the above example may be a view as depicted in Figure 10B, recorded by a second camera housed within camera housing 804 (detection camera). It should be noted that the determined time, frame or image is not restricted to only the nearest image, time, or frame of the corresponding camera. In some examples a number of images either side of the closest image / frame / time are recorded and processed. That is, having identified a time at which a vehicle that is a dominant source of noise passes a detection point, the system may retrieve information corresponding to that image / frame / time and its neighbouring images captured by the detection camera in order to identify a vehicle acting as a dominant noise source and an owner of the vehicle. In some arrangements, a single camera is used, which may be the tracking camera 322, and so the identification of a detection time may be the identification of tracking image / video frame where the identified path of the dominant noise source passes closest to the detection point. Processing then passes to step 1212. In step 1212, processing, such as optical character recognition, OCR, may be performed on the images identified in step 1210 to identify the vehicle acting as a dominant noise source, That is, OCR may be performed in order to identify and process a licence or number plate of the vehicle, which may assist an investigating authority in directing an investigation into use of the vehicle to a person responsible for the vehicle. This OCR may be part of, or replaced by a step of performing automatic number plate recognition on one or more images corresponding to the detection time. Generally, however the process step 1212 involves performing a computer vision processing on an image to identify the location of a licence plate within the image. In a second part of the process, OCR is performed on the licence plate to identify characters on the licence plate to identify the vehicle. Processing may then pass to step 1214 where the process terminates. As would be apparent to the skilled person, certain steps of the above technique described with reference to Figure 12 may be performed in a different order to the order presented as above, or certain steps may be omitted from the present technique as described above. Determining Distance from Noise Source to Noise Camera As described above, in some jurisdictions, the relevant legislation defines limits on the allowed noise levels measured with respect to a threshold distance from the noise source. Furthermore, such noise limits may be dependent on a speed limit of the road upon which the noise source (e.g. a car or other vehicle) is travelling. For example, as noted above, in New' York, Senate Bill S9009 introduced limits on the “maximum allowable sound levels... measured at, or adjusted to, a distance of fifty feet” with different allowable sound levels defined for roads with different speed limits. As such, it is recognised by the present inventors that providing methods of determining distances of noise sources from noise cameras, in combination with the above-described methods (also described in [1]) of determining dominant noise sources which emit noise over an allowed limit, would enable appropriate documentary evidence to be produced (e.g. noise levels measured with respect to a threshold distance from the noise camera to the noise source) when such noise limits are exceeded. It is also recognised that estimating a speed of the noise source (e.g. car) which may be indicated as part of the documentary' evidence may be useful as another reference by which the captured noisy vehicle event may be assessed. Arrangements of embodiments of the present technique described hereafter may provide such solutions. Enabling the determination of the distance between the noise camera and noise source by either a server or the noise camera itself, without requiring any further sensors than those of the noise camera itself, may provide advantages such as reduction in power consumption of the required sensors, a reduction in complexity of the synchronisation between sensors, a reduction in installation time, and a reduction in cost of the overall system. Embodiments of the present technique may provide a noise camera 800 such as that shown in the example of Figure 8. The noise camera 800 may be mounted on a piece of road furniture 801 (e.g. a lamppost) and may comprise a tracking camera 812 for recording video within a field of view' of the tracking camera and at least one audio detector 814,816,818, 820 (which may form part of a microphone array) which are configured to detect noise from a noise source within the field of view of the tracking camera 812. The tracking camera 812 and audio detectors 814, 816, 818, 820 may together form a Halo system 810. The noise camera 800 may further comprise processing circuitry 808 configured to determine a location of the noise source within the field of view' of the tracking camera 812 from which the noise source can be identified, and to determine, based on a physical position of the noise camera 800 ( which may include one or both of a heigh t of the noise camera 800 and an angle of the noise camera with respect to a pseudoground plane at the location of the noise source) and a point at which a ray from the tracking camera 812 intersects the pseudo-ground plane at the location of the noise source, a distance between the noise source and the noise camera 800. Here, the pseudo-ground plane at the location of the noise source may be understood as being a plane positioned parallel to the ground but positioned at a height of the noise source. For example, considering that the noise source may be an exhaust of a vehicle elevated slightly from ground level, then this height above ground level may be taken into account when determining the distance of the noise source from the noise camera. The pseudo-ground plane may be a horizontal plane (i.e. when the ground is flat), but those skilled in the art would appreciate that this will not be the case if the ground is sloped. Figure 13 illustrates a first example process in accordance with at least some arrangements of embodiments of the present technique. Such a process defines an example of the operation of the noise camera where it is the noise camera itself that determines the distance between the noise camera and noise source. The process starts in step S I 1. In step S12, the process comprises recording video within a field of Hew of a tracking camera of the noise camera. Then, in step SI 3, the process involves detecting noise from a noise source within the field of view' of the tracking camera. Following this, in step SI 4, the process involves determining a location of a noise source within the field of view of the tracking camera from which the noise source can be identified. Next, in step S15, the method comprises determining, based on a physical position of the noise camera and a point at which a ray from the tracking camera intersects a pseudo-ground plane at the location of the noise source, a distance between the noise source and the noise camera. The method ends in step SI6, though those skilled in the art would appreciate that the noise camera may be configured to send documentary evidence (including the determined distance from the noise camera to the noise source) to a server following performance of step S15. As shown in the arrangement of Figure 13, it may be the noise camera itself w'hich determines the distance between the noise camera and noise source, and this may subsequently be included in documentary evidence which the noise camera may then send to the server for further processing, including determination of the dominant noise source in a particular video, and determination of whether any vehicle(s) in the video exceed an allowable noise limit (w'here such an exceeded noise limit may be adjusted in respect of the determined distance). In other arrangements however, it may be the server which performs the determination of the distance between the noise camera and noise source based on the received documentary' evidence. Figure 14 illustrates a second example process in accordance with at least some arrangements of embodiments of the present technique. Such a process defines an example of the operation of the server in arrangements where it is the server which performs the determination of tire distance between the noise camera and noise source based on the received documentary' evidence. The process starts in step S21. In step S22, the method involves receiving the documentary' evidence from the noise camera following a trigger event (such as the detection of a noise being emitted which is above a predefined desired or legal threshold), the documentary evidence comprising tracking video, noise source location values comprising, for each of one or more frames of the tracking video, and an indication of a location of a dominant noise source in the frame of the tracking video (and, optionally, a sound recording of sound associated with the trigger event). In step S23, the method comprises determining, based on a physical position of the noise camera and a point at which a ray from the tracking camera intersects a pseudo-ground plane at the location of the noise source, a distance between the noise source and the noise camera. The process ends in step S24. Figure 15 illustrates a third example process in accordance with at least some arrangements of embodiments of the present technique. Such a process defines an example of the operation of the tracking camera specifically . The process starts in step S31. In step S32, the method comprises recording video within a field of view of the tracking camera. Then, in step S33, the method comprises determining a location of a detected noise source within the field of view of the tracking camera from which the noise source can be identified. Following this, in step S34, the process comprises determining, based on a physical position of the noise camera and a point at which a ray from the tracking camera intersects a pseudo-ground plane at the location of the noise source, a distance between the noise source and the noise camera. The process ends in step S35. In arrangements of embodiments of the present technique as exemplified by Figures 13, 14, and 15, and as described in more detail below, the physical position of the noise camera may comprise one (or preferably both) of a height of the noise camera and an angle of the noise camera with respect to the ground / pseudo-ground plane. Here, the height of the noise camera may be the height of the tracking camera above the ground, or may the height of the at least one audio detector (e.g. a microphone) above the ground (where the height of the at least one audio detector may be relative to the tracking camera). Furthermore, an estimated or assumed height of the noise source may be taken into consideration when determining the distance between the noise camera and noise source, as described in more detail below. Similarly to the height, the angle of the noise camera with respect to the ground / pseudo-ground plane may in at least some arrangements be thought of specifically as being an angle of the tracking camera with respect to the ground / pseudo-ground plane. Essentially, arrangements of embodiments of the present technique enable the distance of a noise source from the noise camera which detects the noise it emits to be accurately measured. Further arrangements of embodiments of the present technique, as described in further detail below, can enable the calculation of an acoustic correction to the noise level based on the measured distance. As is described in [ 1], the noise camera may comprise an audio detector array which comprises a plurality of tracking audio detectors (i.e. microphones), where each of the plurality of tracking audio detectors are spatially separately disposed with respect to the tracking camera and are each configured to detect the noise from the noise source within the field of view of the tracking camera. The tracking camera may itself form part of the microphone array, e.g. as part of a Halo system as shown in the example of Figure 8. Here, each of the tracking audio detectors of the audio detector array may be configured to generate a signal representative of the detected noise, and the processing circuitry of the noise camera may be configured to receive the signals representative of the detected noise from each of the tracking audio detectors of the audio detector array and to determine the location of the noise source based on a time difference of arrival of the noise detected by each of the tracking audio detectors, from the received signals representative of the detected noise, the location of the noise source. Here, while the audio detector array may be configured to use TDOA to determine locations of noise sources which are subsequently used to determine distances between noise sources and the noise camera (e.g. as described above with reference to Figures 3 and 4), any appropriate microphone array processing technique (e.g. beamforming) may be used to determine such locations and distances of noise sources. Additionally, as is described above and in [1], the noise camera may further comprise one or more detection cameras (such as detection cameras 804 and 806 as shown in the example of Figure 8) which are disposed to capture one or more detection images captured within a field of view of the one or more detection cameras including at least part of the field of view of the tracking camera. Here, the noise camera may also include a detection microphone configured to detect noise from the noise source, wherein the processing circuitry of the noise camera, may be configured to receive signals representative of the detected noise of the noise source from the detection microphone, to identify a trigger event in which noise from the noise source exceeds a predetermined threshold, and to record, m response to the trigger event, the one or more detection images from the one or more detection cameras and the video recorded by the tracking camera and to form documentary evidence from which a location of the noise source in the field of view of the tracking camera and the detection camera can be determined as a dominant noise source. Here, the one or more detection images may be one or more image frames of detection video captured by the detection camera. In accordance with some arrangements of embodiments of the present technique, the lens of the tracking camera - which may be a wide-angle fisheye lens, for example -- may be calibrated (for example using known methods) in order to obtain intrinsic camera and distortion parameters. For example, such calibration may be performed in addition to the calibration described above with respect to Figures 7A and 7B. Such calibration may be performed once for each lens at installation of the noise camera, and may be adjusted or updated if needed, either at regular intervals, on demand, or when the camera model is changed to a different camera model. As those skilled in the art would understand, a 2D image point can be calculated from a 3D world point using forward projection: PX (1) where x is a 2D homogenous image point [u, v, 1], X is a 3D homogenous world point [X, Y, Z, 1], and P is the projection matrix: P = K[R\t] (2) where K is the intrinsic camera matrix, and and t represent rotation and translation from world to camera coordinates. In accordance with embodiments of the present technique, the noise camera or processing server may determine the distance between the noise source and the noise camera through application of the inverse of the forward projection, i.e. starting with a 2D image point and trying to obtain a 3D world coordinate. An issue arises as, in the inverse problem, a ray can only be defined in a direction from the camera, rather than defining a specific three-dimensional point. However, once a ray is defined, an intersection point between the ray and a known surface, e.g. the ground at Z = 0, can be determined to obtain real-world coordinates (provided the true height and angle of the camera are known). The discussion below, encompassing Equations (3) to (13), describe how to obtain a 3D ray from a 2D image point. Such processing to obtain the 3D ray requires the use of parameters K and D, which may be obtained from the calibration process. It will be appreciated that such processing is an example of how the 3D ray may be obtained, and is not intended to be limiting on the operation of the noise camera or server in determining the distance between the noise camera and noise source. Processing starts with a 2D image point [u, v], First, these points are normalised using intrinsic camera parameters of the tracking camera: where cx and cy are the principal point (image centre), and fx and fy are the focal length in each dimension. These parameters are obtained from the intrinsic camera matrix K. Lens distortion can then be accounted for using the distortion coefficients, D, obtained from the calibration process: D k2,pr>p2,k3] (4) r2 — x^ + y2 (5) xc ” + kAr2 + k2rA + k3rb) + 2pxxnyn + p2(r2 + 2x2) (6) yc — + k-.r2 + + k3rb") + pr(r2 + 2y2) + 2p2xnyn (7) where xc and yc represent the 2D image point after it has been normalised and corrected for distortion. kr, k2 and k3 represent the radial distortion, and py and p2 represent the tangential distortion. In other words, as described above in respect of Equations (3) to (7), the processing circuitry (of the noise camera or the server) may be configured to determine the ray from the tracking camera by normalising the point in the video corresponding to the location of the noise source using one or more parameters of the tracking camera. It should be noted that the distortion coefficient k3 is sometimes omitted. If this is the case, k3 can be assumed to be 0 in Equations (6) and (7), and the r6 terms can be ignored. Now the 2D image point coordinates xc and yc have been obtained, a 3D ray (i.e, a unitless direction vector from the tracking camera, centre) can be defined as: (8) The 3D ray, ^camera-, can be rotated into the world space using the rotation matrix Rpitch: Rpitch (®p) T 0 0 cos(0p) 0 sln(3') 0 -sin(ep) cos(dp) world Rpitch ' camera (9) (10) where 9p is the angle at which the tracking camera is pointing down towards the ground. For cases where the road is not flat, i.e. it slopes from left to right or vice versa, an additional rotation matrix can be specified: ■ cos(0r) 0 _—sin(0r) 0 sin(0r) 1 0 0 cos(0r). where 9r is the slope angle of the road. The two rotation matrices can be combined to form a single matrix to use in Equation (10): lx£otai Rroll ' Rpitch 1 world — ^total ' camera (11) (12) (13) In other words, as described above in respect of Equations (8) to (13), the processing circuitry (of the noise camera or the server) may be configured to rotate the ray from the tracking camera in respect of an angle (0p) of the tracking camera with respect to the pseudo-ground plane and / or an angle (0r) of a slope of the pseudo-ground plane. The transpose of the rotation matrix is used because the rotation matrix is defined in the forward projection model, and the inverse is being performed here. As the rotation matrix is orthonormal, the inverse is its transpose. If the tracking camera is not aligned perpendicular to the road, it is also possible to include a rotational matrix tor yaw (i.e. 0y) in the same way as for roll, combining all rotational matrices into a single rotation matrix to convert the rays from the tracking camera coordinate system to the world coordinate system. That is, the processing circuitry (of the noise camera or the server) may (alternatively or additionally) be configured to rotate the ray from the tracking camera in respect of an angle (0y) of the tracking camera with respect to a vertical axis (i.e. perpendicular to the ground / pseudo-ground plane) of the tracking camera. To obtain the 3-dimensional point at which the ray from the tracking camera intersects with the pseudoground plane at the location of the noise source (which herein may also be referred to as the ground point), the 3D ray may be expressed in standard parametric form: (14) where r0 is the origin point of the ray (the tracking camera centre), t is the scalar parameter (i .e. how far along the ray to travel), and d is the direction of the ray (referred to as f'worid in Equations (10) and (13)). Now the tracking camera centre may be defined, in world coordinates, with a height, h, above ground level: 0' 0 Ji. (15) Those skilled in the art would appreciate that the height h of the tracking camera (and / or a height of the audio detector / microphone), along with a tilt (i.e. 9p) of the tracking camera, will generally be defined at installation of the noise camera, and will be fixed parameters. In some implementations, one or more of these parameters may be adjusted after installation. Equation (14) then becomes: Camera (0 = 0 + t "dy tdy h + tdz (16) Next, the processing may involve finding the value for scalar parameter, t, when the ray intersects a defined pseudo-ground (e.g. horizontal) plane, for example, the ground defined at Z = 0. In this case, the z component of Equation (16) is set to 0, and the processing involves solving for t : h + tdz — 0 (17) (18) It should be noted that solving for Z = 0 assumes the noise source is at ground level. It can be advantageous to assume the noise source is elevated slightly (e.g. 0.3 m in the case of a car / motorbike exhaust) or significantly (e.g. 4 m in tire case of a US truck exhaust stack). This is easily accounted for by adjusting the camera height, h, relative to the source height. For example, if the tracking camera is installed at 6 m height and the noise source height is 4 m, h can be adjusted from 6 to 2, i.e. the difference between the two heights. In other words, and as mentioned above, the processing circuitry (of the noise camera or the server) may further be configured to determine the point at which the ray from the tracking camera intersects the ground at the location of the noise source based on an estimated height of the noise source. This value is used for t to find the real-world x and y coordinates of the point at which the ray intersects the ground plane: In other words, as described above in respect of Equations (14) to (21), the processing circuitry (of the noise camera or the server) may be configured to determine the point at which the ray from the tracking camera intersects the ground at the location of the noise source based on an origin point of the ray (i.e. r0), a direction of the ray (i.e. d), a distance of the ray from the tracking camera to the ground (i.e. the scalar parameter t), and the height of the noise camera (i.e. h). Now the real-world x and y coordinates for the ground point (i.e. the 3D point at which the ray from the tracking camera intersects with the pseudo-ground plane at the location of the noise so urce) have been obtained, the distance between the noise camera and the noise source may be determined. Furthermore, in some arrangements of embodiments of the present technique, the speed of the noise source may also now be estimated. The processing circuitry’ of the noise camera or the server may determine the distance between the noise camera and the noise source using the 3D Euclidean distance formula: & ^xworld + y world + (22) In some arrangements, it may be more usefill to calculate the distance from the source to the audio detector (e.g. microphone) rather than to the tracking camera or to the noise camera generally. This is easily done by substituting the tracking camera height, A, for the microphone height, hmic, in Equation (22). This assumes the microphone is mounted directly beneath the tracking camera. If tins is not the case, the x and y coordinates of the microphone relative to the tracking camera can be taken into account in Equation (22). As noted above, in some implementations of the present technique, the speed of the noise source may’ be determined (either by the noise camera and included in the documentary’ evidence, or by the server). If the noise source is tracked through a video, the real-world location of the source, [xwor?rf,ywor?rf], can be calculated for each frame of the video. Given the frame rate of the video is known, i.e. the time between each frame, it is straightforward to calculate an estimate for the speed using: speed distance time (22) In other words, the processing circuitry (of the noise camera or the server) may be configured to determine, based on the determined distance between the noise source and the noise camera for at least two frames of the video and a frame rate of the video, a speed of the noise source, In Equation (23), the distance can be the distance between each ground point or the total distance between a number of ground points, and the time can be the time between each individual frame, or the total time between a number of frames. The processing circuitry of the noise camera or tire server may perform the above calculations for multiple (and in some cases every) frame of a video. For each frame, the location of the noise source in the 2D image is known by tracking the red dot microphone array output (as described above, and described in more detail in [ 1]). The precise noise level at the time of each video frame is also known. In some arrangements of embodiments of the present technique therefore, knowing the above, for each video frame, the distance from the noise source to the microphone may be calculated by the processing circuitry of tire noise camera or server and used to correct the measured noise level to a standardised distance. As described above, and in [1], the purpose is to align with legislation that requires measured noise levels to be adjusted to a fixed distance, e.g. 50 ft. Often, noise will be measured by a noise camera from a vehicle at a distance closer than 50 ft, and therefore it will be required to correct (i .e. reduce, in the case of the measuring being performed closer than the fixed distance) the noise level accordingly. In other words, the processing circuitry (of the noise camera or the server) may be configured to adjust, based on the determined distance between the noise source and the noise camera, a noise level of the detected noise with respect to a reference distance (e.g. a fixed distance according to legislation in a particular j urisdiction). The output of the calculation is a series of corrected noise levels as the vehicle passes the camera system, i.e. the noise level for each frame of the video has been corrected to a standardised distance (e.g. 50 ft). From this, it is possible to find the frame in which the vehicle is generating the highest corrected noise level, and use that in a comparison with legislated noise limits to see if enforcement action should be taken. In other words, the processing circuitry (of the noise camera or the server) may be configured to perform the adjustment of the noise level of the detected noise for a plurality of frames of the video, and to determine, from among the plurality of frames of the video for which the adjustment of the noise level of the detected noise was performed, the one of the plurality of frames with a highest adjusted noise level of the detected noise. Figure 16 shows an example of how an assumed (i.e. estimated) source height may be used when determining a distance from the noise source to the noise camera in accordance with embodiments of the present technique. As can be seen in Figure 16, a source height of 0.3 m may be assumed for a vehicle 1601 which is tracked through the video captured by the tracking camera. In this instance, given the vehicle 1601 is a motorbike, it may be assumed that the source of the noise it produces (which may be considered to be its exhaust 1602) is fairly close to the ground, and so a known typical height from the ground of a motorcycle’s exhaust of 0.3 m may be assumed. In the example of Figure 16, the pseudo-ground plane used to determine distance may therefore be considered as being parallel to the ground at this assumed height of 0.3 m, and so the distance bciweea the noise source 1602 and the noise camera is estimated as being 7.31 m. If the noise source 1602 were considered as being at a different height, e.g. 4 rn, then the determined distance would be shorter (assuming the height of the noise camera, or specifically, the height of the microphone) is closer to 4 m than it is to 0.3 m, and so the corrected noise level (that at an example reference distance of 7.5 m) would be lower than the corrected 90.3 dB noise level determined m the example of Figure 16. Figure 17 illustrates how uncorrected and corrected noise levels plotted against time (e.g. against frame number) may change throughout a video recorded by a tracking camera in accordance with embodiments of the present technique. As can be seen in the example of Figure 7, while the highest noise may be recorded in around the 200th frame, this may be at a time when the noise source is passing close by the camera. When adjusting and correcting for distance, for both low and high assumed source heights, it may be determined by the noise camera or server that the highest noise level at a fixed reference distance may have occurred a number of frames later. Figure 17 also shows the impact of the assumed height of the noise source on the calculated distance and therefore the corrected noise level. The following numbered paragraphs provide further example aspects and features of the present technique: Paragraph 1. A noise camera for a. noise monitoring system, comprising a tracking camera for recording video within a field of view of the tracking camera, at least one audio detector configured to detect noise from a noise source within the field of view of the tracking camera, and processing circuitry configured to determine a location of the noise source within the field of view' of the tracking camera from which the noise source can be identified, and to determine, based on a physical position of the noise camera and a point at which a ray from the tracking camera intersects a pseudo-ground plane at the location of the noise source, a distance between the noise source and the noise camera. Paragraph 2. The noise camera according to Paragraph 1, wherein the noise camera comprises an audio detector array comprising the at least one audio detector, and wherein the audio detector array comprises a plurality of tracking audio detectors including the at least one audio detector, each of the plurality of tracking audio detectors being spatially separately disposed with respect to the tracking camera and each being configured to detect the noise from the noise source within the field of view of the tracking camera. Paragraph 3. The noise camera according to Paragraph 2, wherein each of the tracking audio detectors of the audio detector array are configured to generate a signal representative of the detected noise, and the processing circiuiiy is configured to receive the signals representative of the detected noise from each of the tracking audio detectors of the audio detector array and to determine the location of the noise source based on a time difference of arrival of the noise detected by each of the tracking audio detectors, from the received signals representative of the detected noise, the location of the noise source. Paragraph 4. The noise camera according to Paragraph 2 or Paragraph 3, wherein the audio detector array comprises the tracking camera. Paragraph 5. The noise camera according to any of Paragraphs 1 to 4, wherein the processing circuitry is configured to determine, based on the determined distance between the noise source and the noise camera for at least two frames of the video and a frame rate of the video, a speed of the noise source. Paragraph 6. The noise camera according to any of Paragraphs 1 to 5, wherein the pseudo-ground plane at the location of the noise source is a plane located parallel to the ground and at a height of the noise source. Paragraph 7. The noise camera according to any of Paragraphs 1 to 6, wherein the physical position of the noise camera comprises a height of the noise camera and / or an angle of the noise camera with respect to the horizontal. Paragraph 8. The noise camera according to Paragraph 7, wherein the height of the noise camera is the height of the tracking camera above the ground. Paragraph 9. The noise camera according to Paragraph 7 or Paragraph 8, wherein the height of the noise camera is the height of the at least one audio detector above the ground. Paragraph 10. The noise camera according to any of Paragraphs 7 to 9, wherein the angle of the noise camera with respect to the horizontal is an angle of the tracking camera with respect to the horizontal. Paragraph 11. The noise camera according to any of Paragraphs 1 to 10, wherein the processing circuitry is configured to adjust, based on the determined distance between the noise source and the noise camera, a noise level of the detected noise with respect to a reference distance. Paragraph 12. The noise camera according to Paragraph 11, wherein the processing circuitry is configured to perform the adjustment of the noise level of the detected noise for a plurality of frames of the video, and to determine, from among the plurality of frames of the video for which the adjustment of the noise level of the detected noise was performed, the one of the plurality of frames with a highest adjusted noise level of the detected noise. Paragraph 13. The noise camera according to any of Paragraphs 1 to 12, wherein the tracking camera comprises a wide-angle fisheye lens. Paragraph 14. The noise camera according to any of Paragraphs 1 to 13, wherein the processing circuitry is configured to determine the ray from the tracking camera by normalising the point in the video corresponding to the location of the noise source using one or more parameters of the tracking camera. Paragraph 15. The noise camera according to any of Paragraph 14, wherein the one or more parameters of the tracking camera comprise a principal point, a focal length in each dimension, and a lens distortion. Paragraph 16. The noise camera according to any of Paragraphs 1 to 15, wherein the processing circuitry is configured to rotate the ray from the tracking camera in respect of one or more of: an angle of the tracking camera with respect to the pseudo-ground plane, an angle of a slope of the pseudo-ground plane, and an angle of the tracking camera with respect to a vertical axis of the tracking camera. Paragraph 17. The noise camera according to Paragraph 16, wherein the processing circuitry is configured to determine the point at which the ray from the tracking camera intersects the pseudo-ground plane at the location of the noise source based on an origin point of the ray, a direction of the ray, a distance of the ray from the tracking camera to the pseudo-ground plane, and the height of the noise camera. Paragraph 18. The noise camera according to Paragraph 17, wherein the processing circuitry is further configured to determine the point at which the ray from the tracking camera intersects the pseudo-ground plane at the location of the noise source based on an estimated height of the noise source. Paragraph 19. The noise camera according to any of Paragraphs 1 to 18, comprising one or more detection cameras disposed to capture one or more detection images captured within a field of view of the one or more detection cameras including at least part of the field of view of the tracking camera. Paragraph 20. The noise camera according to Paragraph 19, comprising a detection microphone configured to detect noise from the noise source, wherein the processing circuitry is configured to receive signals representative of the detected noise of the noise source from the detection microphone, to identify a trigger event in which noise from the noise source exceeds a predetermined threshold, and to record, in response to the trigger event, the one or more detection images from the one or more detection cameras and the video recorded by the tracking camera and to form documentary evidence from which a location of the noise source in the field of view of the tracking camera and the detection camera can be determined as a dominant noise source. Paragraph 21. The noise camera according to Paragraph 19 or Paragraph 20, wherein the one or more detection images are one or more image frames of detection video captured by the detection camera. Paragraph 22. A tracking camera forming part of a noise camera for a noise monitoring sy stem, wherein the tracking camera is configured to record video within a field of view of the tracking camera, to determine a location of a detected noise source within the field of view' of the tracking camera from which the noise source can be identified, and to determine, based on a physical position of the noise camera and a point at which a ray from the tracking camera, intersects a pseudo-ground plane at the location of the noise source, a distance between the noise source and the noise camera. Paragraph 23. A server for processing documentary evidence from a noise camera, the server comprising processing circuitry having program code, which when executed causes the processing circuitry to receive the documentary' evidence from the noise camera following a trigger event, the documentary evidence comprising tracking video, noise source location values comprising, for each of one or more frames of the tracking video, and an indication of a location of a dominant noise source in the frame of the tracking video, and to determine, based on a physical position of the noise camera and a point at which a ray from the tracking camera intersects a pseudo-ground plane at the location of the noise source, a distance between the noise source and the noise camera. Paragraph 24. The server according to Paragraph 23, wherein the documentary'- evidence further comprises a speed of the noise source. Paragraph 25. The server according to Paragraph 23, wherein the processing circuitry' is configured to determine, based on the determined distance between the noise source and the noise camera for at least two frames of the video and a frame rate of the video, a speed of the noise source. Paragraph 26. The server according to any of Paragraphs 23 to 25, wherein the pseudo-ground plane at the location of the noise source is a plane located parallel to the ground and at a height of the noise source. Paragraph 27. The server according to any of Paragraphs 23 to 26, wherein the physical position of the noise camera comprises a height of the noise camera and / or an angle of the noise camera with respect to the horizontal. Paragraph 28. The server according to Paragraph 27, wherein the height of the noise camera is the height of the tracking camera above the ground. Paragraph 29. The server according to Paragraph 27 or Paragraph 28, wherein the height of the noise camera is the height of at least one audio detector of the noise camera above the ground. Paragraph 30. The server according to any of Paragraphs 27 to 29, wherein the angle of the noise camera with respect to the horizontal is an angle of the tracking camera with respect to the horizontal. Paragraph 31. The noise camera according to any of Paragraphs 23 to 30, wherein tire processing circuitry is configured to adjust, based on the determined distance between the noise source and the noise camera, a noise level of the detected noise with respect to a reference distance. Paragraph 32. The noise camera according to Paragraph 31, wherein the processing circuitry- is configured to perform the adjustment of the noise level of the detected noise for a plurality of frames of the video, and to determine, from among the plurality of frames of the video for which the adjustment of the noise level of the detected noise was performed, the one of the plurality of frames with a highest adjusted noise level of the detected noise. Paragraph 33. The noise camera according to any of Paragraphs 23 to 32, wherein the processing circuitry' is configured to determine the ray from the tracking camera by normalising the point in the video corresponding to the location of the noise source using one or more parameters of the tracking camera. Paragraph 34. The noise camera according to Paragraph 33, wherein the one or more parameters of tire tracking camera comprise a principal point, a focal length in each dimension, and a lens distortion. Paragraph 35. The noise camera according to any of Paragraphs 23 to 34, wherein the processing circuitry' is configured to rotate the ray from the tracking camera in respect of one or more of: an angle of the tracking camera with respect to the pseudo-ground plane, an angle of a slope of the pseudo-ground plane, and an angle of the tracking camera with respect to a vertical axis of the tracking camera. Paragraph 36. The noise camera according to Paragraph 35, wherein the processing circuitry is configured to determine the point at which the ray from the tracking camera intersects the pseudo-ground plane at the location of the noise source based on an origin point of the ray, a direction of the ray, a distance of the ray from the tracking camera to the pseudo-ground plane, and the height of the noise camera. Paragraph 37. The noise camera according to Paragraph 36, wherein tire processing circuitry is further configured to determine the point at which the ray from the tracking camera intersects the pseudo-ground plane at the location of the noise source based on an estimated height of the noise source. Paragraph 38. A noise monitoring system comprising a noise camera comprising a tracking camera for recording video within a field of view of the tracking camera, at least one audio detector configured to detect noise from a noise source -within the field of view of the tracking camera, and processing circuitry, and a. server for processing documentary evidence from a. noise camera comprising processing circuitry, wherein the processing circuitry of the noise camera is configured to determine a location of the noise source within the field of view of the tracking camera from which the noise source can be identified, and wherein the processing circuitry of the noise camera or the processing circuitry of the server is configured to determine, based on a physical position of the noise camera and a point at which a ray from the tracking camera intersects a. pseudo-ground plane at the location of the noise source, a distance between the noise source and the noise camera. Paragraph 39. A method of operating a noise camera for a noise monitoring sy stem, the method comprising recording video within a field of view of a tracking camera of the noise camera, detecting noise from a noise source within the field of view' of the tracking camera, determining a location of a noise source within the field of view? of the tracking camera from wInch the noise source can be identified, and determining, based on a phy sical position of the noise camera and a point at which a ray from the tracking camera intersects a pseudo-gro und plane at the location of the noise source, a distance betw een the noise source and the noise camera. Paragraph 40. A method of processing documentary evidence from a noise camera comprising receiving the documentary evidence from the noise camera following a trigger event, the documentary' evidence comprising tracking video, noise source location values comprising, tor each of one or more frames of the tracking video, and an indication of a location of a dominant noise source in the frame of the tracking video, and determining, based on a physical position of the noise camera and a point at which a ray from the tracking camera intersects a pseudo-ground plane at the location of the noise source, a distance between the noise source and the noise camera. Paragraph 41. A computer program comprising executable instructions which when executed by processing circuity performs the method according to Paragraph 39 or Paragraph 40. Paragraph 42. A computer readable storage medium storing the computer program of Paragraph 41. It will be appreciated that the above description for clarity has described embodiments with reference to different functional units, circuitry and / or processors. However, it will be apparent that any suitable distribution of functionality between different functional units, circuitry and / or processors may be used without detracting from the embodiments. Those skilled in the art would appreciate that the methods shown by Figure 13, 14, and 15 may be adapted in accordance with embodiments of the present technique. For example, other intermediate steps may be included in such methods, or the steps may be performed in any logical order. As used herein, the terms “a” or “an” shall mean one or more than one. The term “plurality” shall mean two or more than two. Hie term “another” is defined as a second or more. The terms “including” and / or “having” are open ended (e.g., comprising). Reference throughout this document to “one embodiment”, “some embodiments”, “certain embodiments”, “an embodiment” or similar term means that a particular feature, structure, or characteristic described m connection with the embodiment is included in at least one embodiment. Thus, the appearances of such phrases in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner on one or more embodiments without limitation. The term “or” as used herein is to be interpreted as inclusive or meaning any one or any combination. Therefore, “A, B or C” means “any of the following: A; B; C; A and B; A and C; B and C; A, B and C”. An exception to this definition will occur only when a combination of elements, functions, steps or acts are in some way inherently mutually exclusive. While the invention has been described in connection with specific examples and various embodiments, with reference to different functional units and apparatus, it should be readily understood by those skilled in the art that many modifications and adaptations of the embodiments described herein are possible without departure from the spirit and scope of the invention as claimed hereinafter. It will be apparent to those skilled in the art therefore that any suitable distribution of functionality between different functional units or apparatus may be used without detracting from the embodiments. Thus, it is to be clearly understood that this application is made only by way of example and not as a limitation on the scope of the invention claimed below. The description is intended to cover any variations, uses or adaptation of the invention following, in general, the principles of the invention, and including such departures from the present disclosure as come within the known and customary practice within the art to which the invention pertains, within the scope of the appended claims. V arious further aspects and features of the present, technique are defined in the appended claims. Various modifications may be made to the embodiments hereinbefore described within the scope of the appended claims. REFERENCES [ 1] United Kingdom Patent No. 2628675

Claims

What is claimed is:

1. A noise camera for a noise monitoring system, comprising5 a tracking camera for recording video within a field of view of the tracking camera,at least one audio detector configured to detect noise from a noise source within the field of view of the tracking camera, andprocessing circuitry configuredto determine a location of the noise source within the field of view of the tracking camera 10 from which the noise source can be identified,to determine, based on a physical position of the noise camera and a point at which a ray from the tracking camera intersects a pseudo-ground plane at the location of the noise source, a distance between the noise source and the noise camera,to adjust, based on the determined distance between the noise source and the noise15 camera, a noise level of the detected noise with respect to a reference distance for a plurality offrames of the video, andto determine, from among the plurality of frames of the video for which the adjustment of the noise level of the detected noise was performed, the one of the plurality of frames with a highest adjusted noise level of the detected noise.

202. The noise camera according to Claim 1, wherein the noise camera comprises an audio detector array comprising the at least one audio detector, and wherein the audio detector array comprises a plurality of tracking audio detectors including the at least one audio detector, each of the plurality of tracking audio detectors being spatially separately disposed with respect to the tracking camera and each 25 being configured to detect the noise from the noise source within the field of view of the tracking camera.

3. The noise camera according to Claim 2, whereineach of the tracking audio detectors of the audio detector array are configured to generate a signal representative of the detected noise, and30 the processing circuitry is configured to receive the signals representative of the detected noisefrom each of the tracking audio detectors of the audio detector array and to determine the location of the noise source based on a time difference of arrival of the noise detected by each of the tracking audio detectors, from the received signals representative of the detected noise, the location of the noise source.35 4. The noise camera according to Claim 2, wherein the audio detector array comprises the trackingcamera.

5. The noise camera according to Claim 1, wherein the processing circuitry is configured to determine, based on the determined distance between the noise source and the noise camera for 40 at least two frames of the video and a frame rate of the video, a speed of the noise source.

6. The noise camera according to Claim 1, wherein the pseudo-ground plane at the location of the noise source is a plane located parallel to the ground and at a height of the noise source.45 7. The noise camera according to Claim 1, wherein the physical position of the noise cameracomprises a height of the noise camera and / or an angle of the noise camera with respect to the horizontal.

8. The noise camera according to Claim 7, wherein the height of the noise camera is the height of the tracking camera above the ground.23 12 259. The noise camera according to Claim 7, wherein the height of the noise camera is the height of the at least one audio detector above the ground.5 10. The noise camera according to Claim 7, wherein the angle of the noise camera with respect to thehorizontal is an angle of the tracking camera with respect to the horizontal.

11. The noise camera according to Claim 1, wherein the tracking camera comprises a wide-angle fisheye lens.1012. The noise camera according to Claim 1, wherein the processing circuitry is configured to determine the ray from the tracking camera by normalising the point in the video corresponding to the location of the noise source using one or more parameters of the tracking camera.15 13. The noise camera according to Claim 12, wherein the one or more parameters of the trackingcamera comprise a principal point, a focal length in each dimension, and a lens distortion.

14. The noise camera according to Claim 1, wherein the processing circuitry is configured to rotate the ray from the tracking camera in respect of one or more of:20 an angle of the tracking camera with respect to the pseudo-ground plane,an angle of a slope of the pseudo-ground plane, andan angle of the tracking camera with respect to a vertical axis of the tracking camera.

15. The noise camera according to Claim 14, wherein the processing circuitry is configured to 25 determine the point at which the ray from the tracking camera intersects the pseudo-ground plane at the location of the noise source based on an origin point of the ray, a direction of the ray, a distance of the ray from the tracking camera to the pseudo-ground plane, and the height of the noise camera.

16. The noise camera according to Claim 15, wherein the processing circuitry is further configured to 30 determine the point at which the ray from the tracking camera intersects the pseudo-ground plane at the location of the noise source based on an estimated height of the noise source.

17. A server for processing documentary evidence from a noise camera, the server comprising processing circuitry having program code, which when executed causes the processing circuitry 35 to receive the documentary evidence from the noise camera following a trigger event, thedocumentary evidence comprising tracking video, noise source location values comprising, for each of one or more frames of the tracking video, and an indication of a location of a dominant noise source in the frame of the tracking video,to determine, based on a physical position of the noise camera and a point at which a ray from the 40 tracking camera intersects a pseudo-ground plane at the location of the noise source, a distance between the noise source and the noise camera,to adjust, based on the determined distance between the noise source and the noise camera, a noise level of the detected noise with respect to a reference distance for a plurality of frames of the video, and45 to determine, from among the plurality of frames of the video for which the adjustment of thenoise level of the detected noise was performed, the one of the plurality of frames with a highest adjusted noise level of the detected noise.

18. A noise monitoring system comprising23 12 25a noise camera comprising a tracking camera for recording video within a field of view of the tracking camera, at least one audio detector configured to detect noise from a noise source within the field of view of the tracking camera, and processing circuitry, anda server for processing documentary evidence from a noise camera comprising processing5 circuitry, wherein the processing circuitry of the noise camera is configuredto determine a location of the noise source within the field of view of the tracking camera from which the noise source can be identified, and wherein the processing circuitry of the noise camera or the processing circuitry of the server is configuredto determine, based on a physical position of the noise camera and a point at which a ray from the 10 tracking camera intersects a pseudo-ground plane at the location of the noise source, a distance between the noise source and the noise camera,to adjust, based on the determined distance between the noise source and the noise camera, a noise level of the detected noise with respect to a reference distance for a plurality of frames of the video, and15 to determine, from among the plurality of frames of the video for which the adjustment of thenoise level of the detected noise was performed, the one of the plurality of frames with a highest adjusted noise level of the detected noise.

19. A method of operating a noise camera for a noise monitoring system, the method comprising20 recording video within a field of view of a tracking camera of the noise camera,detecting noise from a noise source within the field of view of the tracking camera, determining a location of a noise source within the field of view of the tracking camera from which the noise source can be identified,determining, based on a physical position of the noise camera and a point at which a ray from the 25 tracking camera intersects a pseudo-ground plane at the location of the noise source, a distance between the noise source and the noise camera,adjusting, based on the determined distance between the noise source and the noise camera, a noise level of the detected noise with respect to a reference distance for a plurality of frames of the video, and30 determining, from among the plurality of frames of the video for which the adjustment of thenoise level of the detected noise was performed, the one of the plurality of frames with a highest adjusted noise level of the detected noise.

20. A method of processing documentary evidence from a noise camera comprising35 receiving the documentary evidence from the noise camera following a trigger event, thedocumentary evidence comprising tracking video, noise source location values comprising, for each of one or more frames of the tracking video, and an indication of a location of a dominant noise source in the frame of the tracking video,determining, based on a physical position of the noise camera and a point at which a ray from the 40 tracking camera intersects a pseudo-ground plane at the location of the noise source, a distance between the noise source and the noise camera,adjusting, based on the determined distance between the noise source and the noise camera, a noise level of the detected noise with respect to a reference distance for a plurality of frames of the video, and45 determining, from among the plurality of frames of the video for which the adjustment of thenoise level of the detected noise was performed, the one of the plurality of frames with a highest adjusted noise level of the detected noise.

21. A computer program comprising executable instructions which when executed by processing circuity performs the method according to Claim 19 or Claim 20.

22. A computer readable storage medium storing the computer program of Claim 21.23 12 25

Images