Masking detected objects in a video stream

Abstract

To provide a method for masking an object in a video stream captured by a camera, a non-transitory computer-readable storage medium, and the camera.SOLUTION: In a camera system in which a camera is arranged and which includes at least a further apparatus, positions and fields of view of the further apparatus and the camera are known and their fields of view do not overlap. A method includes obtaining, by the camera, information indicating that an object is approaching the field of view of the camera. The information is determined based on information from the further apparatus indicating the position and a movement direction of the object and the known positions and fields of view of the camera and the further apparatus. The method also comprises, in response to the obtained information, lowering a threshold for detecting the object to be masked in a video stream captured by the camera, detecting the object to be masked in the video stream by using the threshold, and inserting the masking of the detected object in the video stream.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present invention relates to masking objects in a video stream captured by a camera, and in particular to masking objects when they first enter the field of view of the camera. [Background technology]

[0002] While video surveillance of a particular scene may improve overall security, it may be desirable to keep certain objects within the scene from being identifiable by a person viewing the recorded video footage capturing the scene from a camera, such as, for example, a surveillance camera. For example, for privacy reasons, it may be desirable that the identity of a person captured by the camera, or details of, for example, a vehicle's license plate, should not be directly inferable simply by viewing the recorded video footage. Such protection of certain objects may be achieved by masking the objects within the video stream prior to outputting the video stream, for example, to a display or storage device. Such masking may include, for example, covering the object with a solid color, blurring the object, pixelating the object, or even making the object more or less transparent within each image of the output video stream.

[0003] Before a masking for a particular object can be inserted, the location of the object in the image must first be estimated. This may be achieved, for example, by using an object detection algorithm that is trained / configured to detect a particular class of object (e.g., faces, people, license plates, etc.) in the image. Once the object's location has been detected, a masking can then be applied to the object.

[0004] However, it is important that even in situations where the object is difficult to detect, the object is masked in all images of the video stream. An object detection algorithm may not be able to accurately detect an object, for example, when the object first enters the camera's field of view because only a portion of the object is initially located within the camera's field of view. This may cause the masking of the object to fail. Summary of the Invention

[0005] To at least partially solve the above identified problem of masking untrustworthy objects when the object first enters the camera's field of view, the present disclosure provides an improved method for masking detected objects in a video stream captured by a camera, a corresponding camera, and a non-transitory computer-readable storage medium as defined in the accompanying independent claims.

[0006] According to a first aspect, a method for masking a detected object in a video stream captured by a camera is provided. The camera is arranged in a camera system including a camera and at least an additional device. For the additional device, a position and a field of view are known, and for the camera, a position and a field of view are known, and the field of view of the additional device and the field of view of the camera do not overlap. At the camera, information indicating that an object is approaching the field of view of the camera is acquired. The acquired information is determined from information from the additional device indicating the position and direction of movement of the object, and the known positions and fields of view of the camera and the additional device. In response to the acquired information, a threshold for detecting the object to be masked in the video stream captured by the camera is lowered. Then, the object to be masked in the video stream is detected using the lowered threshold, and a masking of the detected object is inserted in the video stream.

[0007] Because the position and field of view of the further device and the position and field of view of the camera are known, information can be received at the camera indicating that an object is approaching the field of view of the camera based on information from the further device indicating the object's position and direction of movement. The received information is used to lower a threshold for detecting an object to be masked in a video stream captured by the camera, thereby increasing the probability that the object has already been detected when it first enters the field of view of the camera.

[0008] The further device may for example be a sensor.

[0009] The threshold can be a threshold for what is detected as foreground and what is detected as background, so that in scenarios where object detection is based on foreground detection, the probability that the object is already detected when it first enters the camera's field of view is increased.

[0010] The threshold may specify a confidence level with which an object is determined to belong to an object class to be masked in the video stream, thereby increasing the probability that the object has already been detected when it first enters the camera's field of view in scenarios where object detection is based on a confidence level determination that the object belongs to an object class to be masked in the video stream.

[0011] The acquired information may further indicate a sub-region of the camera's field of view where the object is expected to first appear. In a lowering operation, the threshold is then lowered only in the indicated sub-region, thereby increasing the probability that the object has already been detected when it first enters the camera's field of view, while at the same time reducing the risk of false detection of the object in regions other than the sub-region.

[0012] The acquired information may further indicate when the object will first appear in the camera's field of view. Knowing the time when the object is estimated to appear in the camera's field of view provides a better timing for lowering the threshold. Thus, the risk of false detection of an object before it enters the camera's field of view is reduced.

[0013] The obtained information from the further device may further indicate that the object is masked by the further device.

[0014] The acquired information from the further device may further indicate the object class of the object.

[0015] Information obtained from further devices may further indicate a confidence level regarding the object class.

[0016] In the lowering operation, the threshold is lowered in a region along the periphery of the field of view, thereby increasing the probability that an object is already detected when it first enters the camera's field of view, while at the same time reducing the risk of false detection of objects in regions other than the periphery of the field of view.

[0017] The further device may be one of a further camera, an IR camera, a thermal camera, a radar, a sonar, and a lidar.

[0018] The method may further include increasing the threshold after detecting that an object is detected within the field of view of the camera. Thereafter, masking of the detected object in the video stream is maintained, provided that the object is detected using the increased threshold. Masking of the detected object in the video stream is discontinued, provided that the object is not detected using the increased threshold. This may reduce the risk of false detection of an object after it is fully within the field of view of the camera.

[0019] The threshold increase may be performed at a predetermined time after the object is detected, thereby reducing the risk of false detection of an object after it is fully within the camera's field of view.

[0020] According to a second aspect, there is provided a non-transitory computer readable storage medium storing instructions for performing the method according to the first aspect when executed in a camera having at least a processor.

[0021] According to a third aspect, a camera for masking a detected object in a video stream captured by the camera is provided. The camera comprises a circuit configured to execute when placed in a camera system including the camera and at least a further device, the further device having a known position and field of view, the camera having a known position and field of view, and the further device's field of view and the camera's field of view do not overlap, an acquisition function, a reduction function, a detection function, and an insertion function. The acquisition function is configured to acquire information indicating that an object is approaching the field of view of the camera, the acquired information being determined from information from the further device indicating the object's position and direction of movement, and the known positions and fields of view of the camera and the further device. The reduction function is configured to reduce a threshold for detecting the object to be masked in the video stream captured by the camera in response to the acquired information. The detection function is configured to detect the object to be masked in the video stream using the reduced threshold, and the insertion function is configured to insert a masking of the detected moving object in the video stream.

[0022] The above-mentioned optional additional features of the method according to the first aspect, where applicable, apply analogously to the camera according to the third aspect, reference being made thereto in order to avoid undue repetition.

[0023] Further scope of applicability of the present invention will become apparent from the detailed description given hereinafter. It should be understood, however, that the detailed description and specific examples, while indicating preferred embodiments of the invention, are given by way of illustration only, since various changes and modifications within the scope of the present invention will become apparent to those skilled in the art from this detailed description.

[0024] Therefore, it is to be understood that the present invention is not limited to the specific components of the described apparatus or the operation of the described method, and thus such apparatus and methods may vary. It is also to be understood that the terminology used herein is merely for the purpose of describing particular embodiments, and is not intended to be limiting. It is noted that, as used in this specification and the appended claims, the articles "a", "an", "the", and "said" are intended to mean that there are one or more of an element, unless the context clearly dictates otherwise. Thus, for example, reference to "a unit" or "the unit" may include several apparatuses, etc. Furthermore, the words "comprising", "including", "comprising", and similar phrases do not exclude other elements or steps.

[0025] These and other aspects of the invention will now be described in more detail with reference to the accompanying figures, which should not be considered limiting but are used for explanation and understanding. [Brief description of the drawings]

[0026] [Figure 1] 1 shows a schematic diagram of an embodiment of a camera for masking detected objects in a video stream captured by the camera. [Diagram 2] 2 shows a flow chart of an embodiment of a method for masking detected objects in a video stream captured by a camera. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0027] The present invention will now be described with reference to the accompanying drawings, in which a presently preferred embodiment of the invention is shown. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein.

[0028] 1 shows a schematic block diagram of an embodiment of a camera 100 for masking detected objects in a video stream captured by the camera 100. The camera 100 may be any type of camera, such as a security camera, a security camera, or a surveillance camera, and may be arranged in a camera system including the camera 100 and at least a further device, for which the position and field of view are known, and for which the position and field of view are known. The further device may for example be a further camera. The camera 100 captures a sequence of image frames, for example in the form of a video, each image frame depicting a scene defined by the field of view of the camera 100.

[0029] Camera 100 includes circuitry 130, and may include receiver 110. Camera 100 typically also includes an encoder (not shown), an image sensor (not shown), and an image processor (not shown).

[0030] The circuitry 130 is configured to perform the functions of the camera 100. The circuitry 130 may include a processor 132, such as a central processing unit (CPU), a microcontroller, or a microprocessor. The processor 132 is configured to execute program code. The program code may be configured to perform the functions of the camera 100, for example.

[0031] The camera 100 may further comprise a memory 140. The memory 140 may be one or more of a buffer, a flash memory, a hard drive, a removable media, a volatile memory, a non-volatile memory, a random access memory (RAM), or another suitable device. In a typical configuration, the memory 140 may include a non-volatile memory for long-term data storage and a volatile memory that serves as a system memory for the circuit 130. The memory 140 may communicate data with the circuit 130 via a data bus. There may also be associated control lines and an address bus between the memory 140 and the circuit 130.

[0032] The functionality of the camera 100 may be embodied in the form of executable logic routines (e.g., lines of code, software programs, etc.) stored on a non-transitory computer-readable medium (e.g., memory 140) of the camera 100 and executed by the circuitry 130 (e.g., using the processor 132). Furthermore, the functionality of the camera 100 may be a standalone software application or may form part of a software application that performs additional tasks related to the camera 100. The described functions may be considered as methods that a processing unit, e.g., the processor 132 of the circuitry 130, is configured to execute. Also, while the described functions may be implemented in software, such functionality may likewise be performed via dedicated hardware or firmware, or some combination of hardware, firmware, and / or software.

[0033] The circuitry 130 of the camera 100 is configured to perform an acquisition function 141, a degradation function 142, a detection function 143, and an insertion function.

[0034] The acquisition function 141 is configured to acquire information indicative of an object approaching the field of view of the camera, the acquired information being determined from the position and direction of movement of the object and information from the further device indicating the known position and field of view of the camera. The acquired information may be received at the receiver 110.

[0035] The lowering function 142 is configured to lower a threshold for detecting an object to be masked in the video stream captured by the camera in response to the obtained information;

[0036] The detection function 143 is configured to detect the object to be masked in the video stream using a lowered threshold.

[0037] The insertion function 144 is configured to insert a masking of a detected moving object in the video stream.

[0038] Masking as contemplated herein may, for example, be a solid / opaque color, may be semi-transparent, may include applying motion blur to the object so that it is no longer easily identifiable, and / or, for example, forcing pixelation and / or obfuscation of the object in the output image stream so that it is no longer easily identifiable, or the like. In other contemplated embodiments, masking may include making the object itself at least partially transparent in the output image stream so that the background can be seen through the object. This may be possible, for example, when an image of the background without the object in front is available (e.g., from a previous time instance).

[0039] Herein, detection may be performed using one or more commonly available algorithms for object detection already available in various fields of computer technology, such as, for example, computer vision and / or image processing. Such algorithms may include both non-neural and neural network approaches. However, a minimum requirement is that the algorithm (or combination of algorithms) used is able to determine, at least in ideal conditions, whether a particular object (e.g., face, body, license plate, etc.) that is to be masked is present in the image. It is not important whether the algorithm used is, for example, feature-based, template-based, and / or motion-based, as long as the above requirements are met. The detector may be implemented, for example, using one or more neural networks specially trained for that purpose. For the purposes of the present disclosure, it is also assumed that such algorithms used may struggle to accurately detect an object when it first enters the field of view of the camera 100 because the object is only partially within the field of view of the camera 100.

[0040] The camera 100 is configured to be placed in a camera system including the camera 100 and at least the further device. In particular, the camera system including the camera 100 and the further device should be placed and configured such that the position and field of view of the further device and the position and field of view of the camera 100 are known and information indicating the position and direction of movement of an object can be provided from the further device. Information indicating that an object is approaching the field of view of the camera 100 and received at the camera 100 can then be prepared either in a centralized solution using a central server or in a distributed solution using the further device and the camera 100. In a centralized solution, only the central server needs to know the position and field of view of the further device and the position and field of view of the camera 100. After receiving information indicating the position and direction of movement of the object from the further device, the central server can prepare information indicating that an object is approaching the field of view of the camera 100 and provide this information to the camera 100. In a distributed solution, the further device may transmit information indicative of the object's position and direction of movement directly to the camera 100, which may then be aware of its own position and field of view to determine whether an object is approaching the field of view of the camera 100 and, if so, trigger one or more of three actions. In the latter case, the information indicating that an object is approaching the field of view of the camera 100 may be information indicative of the object's position and direction of movement received from the further device.

[0041] To determine the position and direction of movement of an object, it may typically require an additional device to provide at least a two-dimensional representation over time. The additional device may thus be one of, but not limited to, an additional camera, an IR camera, a thermal camera, a radar, a lidar, and a sonar. In such a scenario, in a centralized solution, the additional device may determine its position and relative direction of movement relative to the field of view by detecting the object over a series of image frames. The centralized server may then know the absolute or relative positions and fields of view of both the additional device and the camera 100, determine whether an object is approaching the field of view of the camera 100, and if so, provide such information to the camera 100. In a distributed solution, knowledge of the position and field of view of the additional device and the camera 100 relative to a common coordinate system may be located within the additional device and the camera 100, respectively. Alternatively, each of the additional device and the camera 100 may be aware of its relative position with respect to the other. The position and direction of movement of the object may then be determined in the further device by detecting the object over a series of image frames, and information indicative of the position and direction of movement of the object may be provided to the camera 100. The camera 100 may then determine, knowing its own position and field of view, whether an object is approaching the field of view of the camera 100, and if so, trigger one or more of three actions. In the latter case, the information indicative of the approach of an object to the field of view of the camera 100 may be information indicative of the position and direction of movement of the object received from the further device. From the detection of the object over a series of image frames of the further device, an estimated time when the object will enter the field of view of the camera 100 may be determined. Furthermore, from the position and direction of movement, a sub-area of ​​the field of view of the camera 100 in which the object will appear may be determined.

[0042] In general, how the position and field of view of the further device and the position and field of view of the camera 100 are determined is not essential, as long as the camera 100 can receive information indicating that an object is approaching its field of view, and the information is based on information from the further device indicating the position and direction of movement of the object and the position and field of view of the further device and the position and field of view of the camera 100. For example, the position and field of view of the further device and the position and field of view of the camera 100 may be determined at the time of setup of the camera system, for example, using a mounting position and direction based on a GPS and / or a map or manually entered into a system connected to the camera system. Alternatively, the position and field of view of the further device and the position and field of view of the camera 100 may be determined using a self-learning system that receives information of detection and movement of objects in the further device and the camera, and over time determines whether the position and field of view of the further device and the position and field of view of a second device and / or an object having a particular position and direction of movement by the further device is approaching the field of view of the camera 100.

[0043] Optional additional features of the method 200 described below in relation to FIG. 2 also apply, where applicable, to the camera 100 described in relation to FIG.

[0044] FIG. 2 shows a flow chart for an embodiment of a method 200 for masking a detected object in a video stream captured by a camera. The camera is arranged in a camera system including a camera and at least a further device, as described in more detail in relation to FIG. 1. For the further device, the position and field of view are known, and for the camera, the position and field of view are known. The method 200 includes acquiring S210, at the camera, information indicating that an object is approaching the field of view of the camera, the acquired information being determined from the position and direction of movement of the object and information from the further device indicating the known position and field of view of the camera and the further device. This is described in more detail in relation to FIG. 1. The method 200 further includes, in response to the acquired information, lowering S220 a threshold for detecting an object to be masked in the video stream captured by the camera, detecting the object to be masked in the video stream using the lowered threshold S230, and inserting S240 a masking of the detected object in the video stream.

[0045] Using information from the further device indicating the position and direction of movement of the object, as well as the known positions and fields of view of the camera and the further device, information indicating that the object is approaching the field of view of the camera is obtained, so that the camera knows that the object will appear in its field of view before it actually does so. Furthermore, when the object first appears in the field of view of the camera, typically only a portion of the object will be visible in one or more images of the video stream captured by the camera. Depending on the type of detection used, the object may not be detected until all or at least a significant portion of the object is in the field of view of the camera. Therefore, based on the obtained information, the sensitivity of the detection is increased to increase the probability that the object will be detected even when only a portion of the object is in the field of view of the camera when the object first appears in the field of view. Specifically, this is done by lowering the threshold for detecting the object to be masked in the video stream captured by the camera S220.

[0046] Lowering the threshold for detecting the object to be masked in the video stream captured by the camera will increase the sensitivity in all regions of the camera's field of view, so the acquired information may further indicate a sub-region of the camera's field of view where the object is expected to appear first. The threshold is then lowered only in the indicated sub-region S220. In all other regions of the camera's field of view, the threshold is not lowered. This will increase the sensitivity of detection only in the sub-region of the image where the object is expected to appear first, thus reducing the risk of false detection and masking of the object in other regions of the field of view. Additionally or alternatively, the threshold may instead be lowered in regions along the periphery of the field of view S220. This will achieve a similar effect, since an object approaching the camera's field of view will appear somewhere along the periphery first.

[0047] Before an object appears within the field of view of the camera, information that an object is approaching the field of view of the camera is acquired in the camera S210.

[0048] The acquired information may further indicate when an object will appear within the field of view of the camera. The threshold is then lowered S220 from the indicated time point. This increases the sensitivity of detection from the indicated time point, thus reducing the risk of false detection and masking of the object before the indicated time point.

[0049] The acquired information from the further device, e.g., the further camera, may further indicate that the object is being masked by the further device. The indication that the object is being masked by the further device may increase the probability that the object should be masked by the camera, and thus the threshold for detecting the object to be masked may be further lowered.

[0050] The acquired information from the further device camera may further indicate the object class of the object. The camera may then use this information to determine whether the object should also be masked by the camera. If it is determined that it should not be masked, the reducing operation S220 may be disabled.

[0051] The acquired information from the further device camera may further indicate a confidence level regarding the object class. If the further device indicates a high confidence level for the object class and the class is one that should be masked in the camera, the threshold for detecting objects to be masked may be further lowered for that object class.

[0052] In an embodiment, the threshold may be a threshold for what is detected as foreground and what is detected as background. For example, the background model may define for each spatial region of a plurality of spatial regions in an image frame of the video stream whether the spatial region belongs to the background or foreground in the video sequence. A spatial region may be determined to belong to the background on condition that no significant changes have occurred in the image data of the spatial region of the image frame relative to the image data of the spatial region of the previous image frame in the video stream before a certain time limit, and may be determined to belong to the foreground otherwise. Lowering the threshold for what is detected as foreground and what is detected as background may be to lower the amount of change that is considered to be a significant change in that case, or to increase the time limit within which no significant changes should occur for a spatial region considered to belong to the background.

[0053] In other embodiments, the threshold specifies the confidence level with which an object is determined to belong to an object class to be masked in the video stream. The threshold is then lowered S220 such that the confidence level required for an object to be determined to belong to an object class to be masked is lowered. For example, if all faces are to be masked, the threshold for identifying faces is lowered, for example, from 80% to 30%, such that masking is performed on objects that are faces with a 30% probability.

[0054] The method may further include, after detecting the object using the lowered threshold S230, raising the threshold again S250. Conditional on the object being detected using the raised threshold, masking the detected object in the video stream is maintained S260. Conditional on the object not being detected using the raised threshold, masking the detected object in the video stream is discontinued S270. For example, the threshold may be raised S250 a predetermined time after detecting the object S230. The predetermined time may be selected such that it is likely that the entire object is within the field of view of the camera.

[0055] The above-mentioned optional additional features of the camera 100 described in relation to FIG. 1 also apply to the method 200 described in relation to FIG. 2, where applicable.

[0056] In an alternative example, a method is provided for masking a detected object in a video stream captured by a camera, similar to the method 200 described above in relation to FIG. 2. The camera is arranged in a camera system including a camera and at least an additional device similar to the camera system described in relation to FIG. 1. For the additional device, the position and field of view are known, and for the camera, the position and field of view are known. The difference in this alternative method is that, due to some features of the camera system, it is sufficient for an object to be detected by the additional device to determine that the object is approaching the field of view of the camera. This may be, for example, because the camera and the additional device are arranged in a particular manner relative to each other. For example, the additional device may be arranged along a corridor or road such that the additional device has a field of view covering a portion of the corridor or road in front of the portion covered by the field of view of the camera, such that an object detected by the additional device moving along the road or corridor is likely to be approaching the field of view of the camera and enter the field of view of the camera within a period of time that depends on the distance between the additional device and the camera and the speed of the detected object. The alternative method includes acquiring S210 at the camera information indicating that an object is approaching the field of view of the camera, the acquired information being determined from information from the further device indicating that an object has been detected and knowledge indicating that an object being detected by the further device is approaching the field of view of the camera. The alternative method further includes, in response to the acquired information, lowering a threshold for detecting an object to be masked in a video stream captured by the camera, detecting the object to be masked in the video stream using the lowered threshold S230, and inserting S240 a masking of the detected object in the video stream.

[0057] By using information from the further device indicating the detection of an object, and knowledge that the object being detected by the further device indicates that the object is approaching the field of view of the camera, it becomes known at the camera that the object is about to appear in its field of view before it actually does so. Furthermore, when the object first appears in the field of view of the camera, typically only a part of the object will be visible in one or more images of the video stream captured by the camera. Depending on the type of detection used, the object may not be detected until all or at least a significant part of the object is in the field of view of the camera. Therefore, based on the obtained information, the sensitivity of the detection is increased in order to increase the probability that the object will be detected even when only a part of the object is in the field of view of the camera when the object first appears in the field of view. In particular, this is done by lowering the threshold for detecting an object to be masked in the video stream captured by the camera.

[0058] Since lowering the threshold for detecting the object to be masked in the video stream captured by the camera will increase the sensitivity in all areas of the camera's field of view, the obtained information may further indicate a sub-area of ​​the camera's field of view where the object is expected to appear first. This information may be obtained based on prior knowledge of where the object will first appear after being detected by the further device. For example, if the further device is positioned along a road or corridor in front of the camera, the object detected by the further device will appear in the sub-area of ​​the camera that includes the part of the road or corridor closest to the field of view of the further device. The threshold is then lowered only in the indicated sub-area. In all other areas of the camera's field of view, the threshold is not lowered. This will increase the sensitivity of detection only in the sub-area of ​​the image where the object is expected to appear first, thus reducing the risk of false detection and masking of the object in other areas of the field of view. Additionally or alternatively, the threshold may instead be lowered in areas along the periphery of the field of view. This will achieve a similar effect, since an object approaching the camera's field of view will first appear somewhere along the periphery.

[0059] Information that an object is approaching the field of view of the camera is acquired at the camera before the object appears within the field of view of the camera.

[0060] The acquired information may further indicate when an object will appear in the field of view of the camera. The threshold is then lowered from the indicated time point. This increases the sensitivity of detection from the indicated time point, thus reducing the risk of false detection and masking of the object before the indicated time point.

[0061] The above-mentioned optional additional features of the camera 100 described in relation to FIG. 1 also apply, where applicable, to the alternative methods described in relation to the figures.

[0062] Those skilled in the art will recognize that the present invention is not limited to the above-described embodiments. On the contrary, many modifications and variations are possible within the scope of the appended claims. Such modifications and variations can be understood and effected by those skilled in the art in practicing the claimed invention, from a study of the drawings, the disclosure, and the appended claims.

Claims

1. 1. A method for masking detected objects in a video stream captured by a camera, the camera being arranged in a camera system comprising the camera and at least a further device, a position and a field of view of the further device being known, a position and a field of view of the camera being known, and the field of view of the further device and the field of view of the camera do not overlap, the method comprising: acquiring, at the camera, information indicative of an object approaching the field of view of the camera, the acquired information being determined from information from the further device indicative of a position and direction of movement of the object and the known positions and fields of view of the camera and the further device; lowering a threshold for detecting an object to be masked in the video stream captured by the camera in response to the acquired information, the threshold specifying a confidence level with which an object is determined to belong to a class of objects to be masked in the video stream, or the threshold is a threshold for what is detected as foreground and what is detected as background and specifies an amount of change in image data in an image frame relative to image data in a previous image frame in which an object is determined to belong to the foreground; detecting an object to be masked in the video stream using the reduced threshold; inserting a masking of the detected object into the video stream; A method comprising:

2. 2. The method of claim 1, wherein the acquired information further indicates a sub-region of the field of view of the camera in which the object is expected to initially appear, and in the lowering operation, the threshold is lowered only in the indicated sub-region.

3. The method of claim 1 , wherein the acquired information further indicates a time point at which the object will first appear in the field of view of the camera, and the threshold is lowered from the indicated time point.

4. The method of claim 1 , wherein the obtained information from the further device further indicates that the object is masked by the further device.

5. The method of claim 1 , wherein the obtained information from the further device further indicates an object class of the object.

6. The method of claim 5 , wherein the obtained information from the further device further indicates a confidence level regarding the object class.

7. The method of claim 1 , wherein in the act of lowering, the threshold is lowered in a region along a periphery of the field of view.

8. The further device comprises: More cameras, IR camera, Thermal camera, Radar, Sonar, and Rider The method of claim 1 , wherein the first and second electrodes are one of:

9. increasing the threshold after detecting the object within the field of view of the camera; and If the object is detected using the increased threshold, maintaining a masking of the detected object in the video stream; If the object is not detected using the increased threshold, Ceasing masking of the detected object in the video stream. The method of claim 1 further comprising:

10. The method of claim 9 , wherein the act of increasing the threshold is performed a predetermined time after detecting the object.

11. 13. A non-transitory computer readable storage medium having stored thereon instructions for performing the method of claim 1 when executed within a camera having a processor.

12. 1. A camera for masking detected objects in a video stream captured by the camera, the camera comprising: a circuit configured to execute when the camera is disposed in a camera system including the camera and at least a further device, the further device having a known position and field of view, the camera having a known position and field of view, and the field of view of the further device and the field of view of the camera do not overlap; an acquisition function configured to acquire information indicative of an object approaching the field of view of the camera, the acquired information being determined from information from the further device indicative of a position and direction of movement of the object, and the known positions and fields of view of the camera and the further device; a reduction function configured to reduce a threshold for detecting an object to be masked in the video stream captured by the camera in response to the acquired information, the threshold specifying a confidence level with which an object is determined to belong to a class of objects to be masked in the video stream, or the threshold is a threshold for what is detected as foreground and what is detected as background and specifies an amount of change in image data in an image frame relative to image data in a previous image frame in which an object is determined to belong to the foreground; a detection function configured to detect an object to be masked in the video stream using the lowered threshold; an insertion function configured to insert a masking of the detected object in the video stream; Equipped with a camera.

Images