Method for operating a traffic monitoring apparatus for a road user, and traffic monitoring apparatus

Abstract

The invention relates to a method for operating a traffic monitoring apparatus (110) for a road user (100), the traffic monitoring apparatus (110) comprising a sensor device (130) and / or a spectrometer (120), the method comprising a step in which a sensor signal is read in via an interface from the sensor device (130) and / or the spectrometer (120), the sensor signal representing an image of a road user (100) detected in an area surrounding the traffic monitoring apparatus (110). The method also comprises a step in which spectral colour components are evaluated at different positions in the image in order to obtain an evaluation signal using the sensor signal. Furthermore, the method comprises a step in which a road user signal is determined using the evaluation signal, the road user signal representing road user data of the detected road user (100).

Description

[0001] Method for operating a traffic monitoring device for a road user and traffic monitoring device

[0002] State of the art

[0003] The invention is based on a method for operating a traffic monitoring device for a road user and a traffic monitoring device according to the preamble of the independent claims. The present invention also relates to a computer program.

[0004] DE102021000323 A1 discloses a stationary traffic monitoring system for monitoring a detection area of ​​a traffic surface. EP2557412 A1 discloses a spectrometer, for example, for color recognition.

[0005] Against this background, the approach presented here presents a method for operating a traffic monitoring device for a road user, a traffic monitoring device, a device using this method, and finally a corresponding computer program according to the main claims. The measures listed in the dependent claims enable advantageous refinements and improvements of the device specified in the independent claim.

[0006] The advantages that can be achieved with the approach presented here consist in particular in the creation of a method that can reliably and quickly determine road user data of a recorded road user.

[0007] A method for operating a traffic monitoring device for a road user, wherein the traffic monitoring device has a sensor device and / or a spectrometer, comprises a step of reading in a sensor signal via an interface from the sensor device and / or the spectrometer, wherein the sensor signal represents an image of a road user detected in an environmental area of ​​the traffic monitoring device. The method further comprises a step of evaluating spectral color components at different positions of the image in order to obtain an evaluation signal using the sensor signal. In addition, the method comprises a step of determining a road user signal using the evaluation signal, wherein the road user signal represents road user data of the detected road user.

[0008] The traffic monitoring device can, for example, be a device for monitoring traffic, for identifying individual road users, for monitoring the speeds of road users, or for monitoring a toll obligation. For this purpose, the traffic monitoring device can be arranged, for example, adjacent to a traffic route, a road, or a carriageway. A road user can be understood, for example, as a vehicle, a pedestrian, a cyclist, a wheelchair user, or the like, whereby such a road user is generally understood here as a person or object participating in traffic. The road user can have unique characteristics, for example the arrangement and number of emitters and / or sensors in relation to one another, which can be detected using a combination of spectrometry and video image analysis.Using the approach presented here, reflections from headlights, passive radiators, active radiators, and / or laser sensors of the detected road user can be measured. Based on this, the model, make, and color of the detected road user, for example, can be determined as road user data, even in the dark. The approach presented here can therefore also be understood as a Make - Model - Color - Spectrum. Furthermore, the road user's license plate number can be recorded and evaluated.

[0009] During the reading step, an image of the surrounding area of ​​the detected road user can be read in as an image in an optically visible range and additionally or alternatively in an infrared range. This allows, for example, the positions of laser or infrared sensors on the road user to be reliably detected. In other words, the approach presented here can be implemented in both visible and non-visible light.

[0010] In the determination step, a distance and, additionally or alternatively, a relative arrangement between at least two positions in the image at which spectral color components were determined can be determined. Distances and / or arrangements of the positions with spectral color components relative to one another can represent unique characteristics of a road user. Thus, in the determination step, a specific model of the road user and / or a make of the road user can be determined.

[0011] In the detection step, the evaluation signal at different positions can be compared with expected color components read from a database at corresponding positions in the image to obtain the road user data. This allows the detected road user to be reliably identified, for example, by comparing the detected positions within the road user with the positions of laser or infrared sources that are installed and known at different positions on different road user types or models.

[0012] The method can comprise a step of outputting an illumination signal to the road user, carried out before the reading step. In this case, in the output step, a different illumination signal with different illumination spectral components can be output at different times. In this way, the method presented here can also be carried out in the dark. Furthermore, the influence of stray light on the evaluation of the spectral analysis can be avoided by taking measurements at two different times. This can be advantageous, for example, if a spotlight is shone on the road user at one time and this spotlight is switched off at a second time. A differential measurement can be advantageous here. Under certain circumstances, the spectrometer can be switched on automatically.

[0013] In the step of determining the road user signal, a make of the road user, a model of the road user, vehicle owner information, and additionally or alternatively a color of the road user can be represented as road user data. Advantageously, a precise identification of the road user detected by the traffic monitoring device can be achieved. The method can include a step of providing the road user signal to an interface to an external storage device in order to compare the determined road user data of the detected road user with road user data of a reference road user. The determined road user data of the detected road user can be stored in the external storage device.

[0014] The step of evaluating and additionally or alternatively determining can be carried out using an artificial intelligence algorithm.

[0015] One of the steps of the method can be performed in a unit that can be located separately from another unit in which another step of the method can be performed. In this way, road user identification can be performed at at least two measurement locations.

[0016] This method can be implemented, for example, in software or hardware or in a mixed form of software and hardware, for example in a control unit.

[0017] The approach presented here further provides a device designed to perform, control, or implement the steps of a variant of a method presented here in corresponding devices. This embodiment of the invention in the form of a device also allows the problem underlying the invention to be solved quickly and efficiently.

[0018] For this purpose, the device can have at least one computing unit for processing signals or data, at least one memory unit for storing signals or data, at least one interface to a sensor or an actuator for reading sensor signals from the sensor or for outputting data or control signals to the actuator, and / or at least one communication interface for reading or outputting data embedded in a communication protocol. The computing unit can be, for example, a signal processor, a microcontroller, or the like, wherein the memory unit can be a flash memory, an EEPROM, or a magnetic storage unit.The communication interface can be designed to read in or output data wirelessly and / or wired, wherein a communication interface that can read in or output wired data can read this data, for example, electrically or optically from a corresponding data transmission line or output it to a corresponding data transmission line.

[0019] In this case, a device can be understood as an electrical device that processes sensor signals and outputs control and / or data signals depending on them. The device can have an interface, which can be implemented in hardware and / or software. In a hardware implementation, the interfaces can, for example, be part of a so-called system ASIC, which contains a wide variety of functions of the device. However, it is also possible for the interfaces to be separate integrated circuits or to consist at least partially of discrete components. In a software implementation, the interfaces can be software modules that are present, for example, on a microcontroller alongside other software modules.

[0020] A traffic monitoring device for detecting a road user in an environment of the traffic monitoring device comprises an embodiment of a device mentioned herein. The traffic monitoring device further comprises a sensor device and / or a spectrometer. In this way, the road user can be easily detected, and the road user data can be reliably and quickly recorded and evaluated.

[0021] The sensor device can comprise a laser sensor, a lidar sensor, a radar sensor, and, additionally or alternatively, an ultrasonic sensor. This advantageously allows a road user to be reliably detected. The sensors can be manufactured cost-effectively and installed in the traffic monitoring device in a space-saving manner.

[0022] The traffic monitoring device can have a lighting device. The lighting device can be arranged on the traffic monitoring device or adjacent to the traffic monitoring device. The lighting device can be switched on, for example, in poor lighting conditions, such as in the dark, to create an image of the road user. At least one light beam and / or one laser beam can be projected onto the road user, allowing spectral color components to be subsequently detected in the image using a sensor device and / or spectrometer.

[0023] Also advantageous is a computer program product or computer program with program code that can be stored on a machine-readable carrier or storage medium such as a semiconductor memory, a hard disk memory, or an optical memory. If the program product or program is executed on a computer or a control device, the program product or program can be used to carry out, implement, and / or control the steps of the method according to one of the embodiments described above.

[0024] Examples of the approach presented here are shown in the drawings and explained in more detail in the following description. It shows:

[0025] Fig. 1 shows an illustration of an embodiment of a traffic monitoring device;

[0026] Fig. 2 is a flowchart of an embodiment of a method for operating a traffic monitoring device; and

[0027] Fig. 3 is a block diagram of an embodiment of a device for operating a traffic monitoring device.

[0028] In the following description of advantageous embodiments of the present invention, the same or similar reference numerals are used for the elements shown in the various figures and having a similar effect, whereby a repeated description of these elements is omitted.

[0029] If an embodiment comprises an “and / or” link between a first feature and a second feature, this is to be read as meaning that the embodiment according to one embodiment has both the first feature and the second feature and according to another embodiment has either only the first feature or only the second feature.

[0030] Fig. 1 shows an illustration of an embodiment of a traffic monitoring device 110 for detecting a road user 100. The traffic monitoring device 110 is designed to monitor traffic or traffic events in an environment of the traffic monitoring device 110.

[0031] The traffic monitoring device 110 has a mast 115 and is arranged adjacent to a roadway 105, with the road user 100 arranged on the roadway 105. The traffic monitoring device 110 has a sensor device 130 and / or a spectrometer 120 for detecting the road user 100.

[0032] The sensor device 130 is designed, for example, as a camera and detects the road user 105 when they are located within a detection range of the sensor device 130. More precisely, the sensor device 130 creates an image of the road user 105. The spectrometer 120 and / or the sensor device 130 is designed, for example, to detect reflections from the road user 105. Headlights 180, sensors 160, and also the paint 170 of the road user 105 generate reflections, for example, which are detected by the sensor device 130 and / or the spectrometer 120 as spectral color components in the image of the road user 100. The spectral color components are arranged, for example, at different positions in the image, whereby a number and / or arrangement of the headlights 180 and / or sensors 160 of the road user 105 can be determined.The headlights 180 and the sensors 160, for example, have a road user-specific arrangement and / or number on the road user 105. The paint 170 of the road user 105 is also road user-specific. An evaluation of the arrangement and / or number of the spectral color components in the image can thus lead to a precise identification of the road user 105 – the model, make, and color of the road user 105 can be determined. In addition, it is possible to determine an intensity of the spectral color components in the image in order to detect, for example, the use of unauthorized or counterfeit headlights 180 and / or sensors 160 for the road user 105. Using the approach presented here, a clear identification of the paint 170 of the road user 105 is also possible.Thus, an illegal repainting of the road user 105 can be detected by means of the traffic monitoring device 110.

[0033] Identification of road user 105 is possible even in poor lighting conditions, for example, in the dark. For this purpose, traffic monitoring device 110 has a lighting device 190, which is arranged on traffic monitoring device 110 merely by way of example and is designed to illuminate road user 105.

[0034] In other words, Fig. 1 shows a traffic monitoring device 110, which can also be referred to as a traffic monitoring system, at the side of the roadway of a road 105 at point A with a mast 115 or tripod and with a sensor device 130, which can also be referred to as an image sensor or video camera, and a spectrometer 120. The spectrometer 120 receives emitted or reflected light as light rays 150 from the road user 100. The most important emission sources or reflectors are listed: 180 headlights, 160 lidar sensor, 170 varnish or paint. These emission sources or reflectors are detected both by the spectrometer 120 and by the sensor device 130. The sensor device 130 is additionally equipped with an automatic license plate reader for recognizing and evaluating the license plate 145. The lighting device 190, which can also be referred to as a light source orA laser, which can be referred to as a laser, is directed, for example, at road user 100 and is preferably built into the housing of traffic monitoring device 110 or arranged in the form of a special street lamp. The same applies to sensors such as lidar, radar, etc. for determining speed or red light violations. According to one embodiment, the approach presented here uses artificial intelligence, abbreviated to K1, which compares video data and spectrometer data on a computing unit not shown here, for example in the back office. In particular, a superposition of the data leads to a geometric mapping, which provides a video image of road user 100 on which the data or spectra of spectrometer 120 can be seen.In a further step, this data can be compared with data from a database, or a forensic analysis of a suspect vehicle as a road user can be subsequently reproduced and compared with the data generated here. Example: A getaway vehicle as a road user for an ATM bombing is captured by the traffic monitoring device 110. The drivers are masked and cannot be recognized in the vehicle as road user 100. The license plate 145 was stolen from another vehicle as a road user. Months later, a vehicle is found as a road user. This road user is subsequently measured using the method presented here. A comparison of the data with the data from the day of the getaway leads to a clear match. This allows for further forensic investigations to be carried out in the vehicle as road user 105.Since these forensic investigations are very expensive and time-consuming, suspicion of a specific type of road user is not sufficient - a unique "fingerprint" using spectrum mapping is better.

[0035] In other words, Fig. 1 shows a combination of a traffic monitoring device 110, which can also be referred to as a traffic monitoring unit, with a built-in spectrometer 120 for analyzing headlight light. In addition to / alternatively to frequency detection of the illumination, frequency detection and evaluation of any active and passive emitters can be performed using the spectrometer 120. The focus is on detecting additional unique features for identifying road users for civil security purposes, but also for TLE. With the approach presented here, Make-Model-Colour can be extended to include the properties of the spectrum of the reflected or emitted light.

[0036] Newer vehicles as road users are equipped with laser sensors that can be detected using the approach presented here. This results in new methods for visualizing and thus identifying road users. In addition to pure video / image sensor detection of the color of a road user 100, a secure spectral breakdown of the exact color is performed. In addition, characteristic features of the road user's lighting and, above all, the laser radiation of the road user sensors, which is virtually invisible to the human eye, and their interaction are used to unambiguously identify the vehicle as road user 105. Alternatively, a separate analysis of a frequency spectrum of road users is possible without comparison to image data and / or video data of the road user 100 or the license plate 145.For example, it is possible to identify road users using “make-model-colour” video data, although the light sources can only be detected using video.

[0037] In other words, the approach presented here enables a cost-effective extension of a traffic monitoring device 110 using a spectrometer 120, as well as a legally binding assignment and identification of road users. Furthermore, the approach presented here enables an increase in the hit rate for "make-model-color" by expanding the visualization of road user-specific properties of light sources, such as low beams, turn signals, brake lights, laser sensors, lidar sensors, or their specific light spectra and geometric arrangements relative to one another—mapping. The approach presented here is particularly applicable in the field of civil security, for example, when using counterfeit license plates or duplicates.In the case of vehicles that have been repainted after a theft, it is possible to detect paint differences compared to the original paint of the vehicle manufacturer, thus providing reasonable initial suspicion that the vehicle was repainted to conceal a crime. Furthermore, a fully automatic comparison with an alarm message to a computing unit is possible, which can be part of the traffic monitoring device 110 or as a back-office solution. A frequency sweep using defined frequencies of the illumination device 190 can be projected as an excitation signal onto the paint 170 or the light sources 160, 180.

[0038] In summary, the traffic monitoring device 110 for the secure identification of road users comprises the sensor device 130 and the spectrometer 120. Image data from the sensor device 130 is provided to a computing unit for determining the road user make (make), the road user model (model), and / or the license plate 145 and / or the road user driver, and optionally the road user color (color). Spectrometer data from the spectrometer 120 is provided to the computing unit for determining the emitted and / or reflected frequencies and / or frequency spectra (spectrum). The emitted and / or reflected frequencies and / or frequency spectra (spectrum) are compared with road user-specific data from a database to assign a road user make (make), road user model (model), and / or road user color.The computing unit performs frequency and / or frequency spectrum mapping of the individual reflectors or emitters of the road user and measures their relative positions and / or lists them in a coordinate system. The computing unit compares the image data from the image sensor and the spectrometer data from the spectrometer, thereby determining a road user color or verifying the road user color from the image data using spectrometer data. The computing unit outputs a unique road user, including unique road user characteristics such as the currently registered license plate and the currently registered road user owner.

[0039] Active irradiation by means of the illumination device 190 is carried out, for example, by one or more light sources, for example with different wavelengths, lasers, lamps, etc., and the spectral analysis is performed on the captured image. If necessary, a laser sweep is recorded, i.e., the laser is scanned once over the road user 100 and the response is broken down spectrally and, if necessary, also temporally, in order to obtain a type of "signature of the road user." Thus, differences in the road user 100 may potentially enable unique identification. The illumination device 190 can also be used to irradiate the road user 100 with a uniform spectrum to improve lighting conditions in the dark. Furthermore, identification of the road user 100 from more than one measurement location is possible.A comparison of the image data by means of the spectrometer 120 is possible, for example, using artificial intelligence, for example a convolutional neural network (CNN).

[0040] Fig. 2 shows a flowchart of an embodiment of a method 200 for operating a traffic monitoring device. The method 200 is similar to or corresponds to the method described in Fig. 1 and is carried out, for example, using the traffic monitoring device described in Fig. 1.

[0041] The method 200 comprises, merely by way of example, a step 220 of outputting an illumination signal to the road user. A different illumination signal with different illumination spectral ranges is output at different times. The output step 220 is performed before the reading step 205. In the reading step 205, a sensor signal is read in from the sensor device via an interface. The sensor signal represents an image of a road user detected in an area surrounding the traffic monitoring device. According to one embodiment, in the reading step 205, an image of the area surrounding the detected road user in an optically visible range and / or in an infrared range is read in as the image.

[0042] Furthermore, the method 200 comprises a step 210 of evaluating spectral color components at different positions of the image in order to obtain an evaluation signal using the sensor signal.

[0043] Furthermore, method 200 includes a step 215 of determining a road user signal using the evaluation signal. The evaluation step 210 and / or the determination step 215 are performed, for example, using an artificial intelligence algorithm.

[0044] According to one embodiment, in step 215 of determining, the evaluation signal at different positions is compared with expected color components at corresponding positions read from a database in order to obtain the road user data. The road user signal represents road user data of the detected road user. Additionally or alternatively, the road user signal represents, as road user data, a make of the road user, a model of the road user, vehicle owner information, and / or a color of the road user. According to one embodiment, in step 215 of determining, a distance and / or a relative arrangement between at least two positions in the image is determined.

[0045] According to one embodiment, the method 200 comprises a step 225 of providing the road user signal to an interface to an external storage device in order to compare the determined road user data of the detected road user with road user data of another road user. According to one embodiment, one of the steps of the method 200 is carried out in a unit that is arranged separately from another unit in which another step of the method 200 is carried out.

[0046] Fig. 3 shows a block diagram of an embodiment of a device 300 for operating a traffic monitoring device. Device 300 is designed, for example, to control the method from Fig. 2 or a similar method.

[0047] For this purpose, the device 300 has a unit 305 for reading in a sensor signal 315. The sensor signal 315 is read in via an interface by the sensor device 130. The sensor signal 315 represents an image of a road user detected in an area surrounding the traffic monitoring device. For example, an image of the surrounding area of ​​the detected road user in an optically visible range and / or in an infrared range is read in as the image.

[0048] In addition, the device 300 has a unit 310 for evaluating spectral color components at different positions of the image to obtain an evaluation signal 320. The evaluation signal 320 is evaluated using the sensor signal 315.

[0049] The device 300 also has a unit 325 for determining a road user signal 335 using the evaluation signal 320. The road user signal 335 represents road user data of the detected road user, for example, a make of the vehicle as a road user, a model of the vehicle as a road user, vehicle owner information, and / or a color of the vehicle as a road user. The evaluation signal 320 is compared, for example, at different positions with expected color components at corresponding positions read from a database in order to obtain the road user data.

[0050] According to one exemplary embodiment, the device 300 comprises a unit 340 for outputting an illumination signal 350. The output unit 340 is controlled, merely by way of example, before the reading unit 305. In the output unit 340, a different illumination signal with different illumination spectrals is output at different times. The device 300 comprises, merely by way of example, a unit 345 for providing the road user signal 335 to an interface to an external storage device 360 ​​in order to compare the determined road user data of the detected road user with road user data of another road user.

Claims

Patent claims 1. A method (200) for operating a traffic monitoring device (110) for a road user (100), wherein the traffic monitoring device (110) has a sensor device (130) and a spectrometer (120), the method (200) comprising the following steps: Reading (205) a sensor signal (315) via an interface from the sensor device (130) and the spectrometer (120), wherein the sensor signal (315) represents an image of a road user (100) detected in an area surrounding the traffic monitoring device (110); Evaluating (210) spectral color components at different positions of the image to obtain an evaluation signal (320) using the sensor signal (315); and Determining (215) a road user signal (335) using the evaluation signal (320), wherein the road user signal (335) represents road user data of the detected road user (100) and, in step (215) of determining, the evaluation signal (320) is compared at different positions with expected color components read from a database at corresponding positions in the image in order to obtain the road user data.

2. Method (200) according to claim 1, wherein in step (205) of reading in as an image an image of the surrounding area of the detected road user (100) is read in in an optically visible range and / or in an infrared range.

3. Method (200) according to one of the preceding claims, wherein in the step (215) of determining a distance and / or a relative arrangement between at least two positions in the image at which spectral color components were determined is determined.

4. Method (200) according to one of the preceding claims, with a step (220) of outputting an illumination signal (350) to the road user (100) carried out before the step (205) of reading in, wherein in the step (220) of outputting a different illumination signal (350) with different illumination spectral components is output at different times.

5. Method (200) according to one of the preceding claims, wherein in the step (215) of determining the road user signal (335), a brand of the road user (100), a model of the road user (100), owner information and / or a color of the road user (100) is determined as road user data.

6. Method (200) according to one of the preceding claims, comprising a step (225) of providing the road user signal (335) to an interface to an external storage device (360) in order to compare the determined road user data of the detected road user (100) with road user data of a reference road user.

7. The method (200) according to any one of the preceding claims, wherein the step (210) of evaluating and / or the step (215) of determining is carried out using an artificial intelligence algorithm.

8. The method (200) according to any one of the preceding claims, wherein one of the steps of the method (200) is carried out in a unit arranged separately from another unit in which another step of the method (200) is carried out.

9. Device (300) which is designed to carry out and / or control the steps of the method (200) according to one of the preceding claims 1 to 8 in corresponding units.

10. Traffic monitoring device (110) for detecting a road user (100) in an environment of the traffic monitoring device (100), with a device (300) according to claim 9, in particular wherein the Traffic monitoring device (110) further comprises a sensor device (130) and a spectrometer (120).

11. Traffic monitoring device (110) according to claim 10, wherein the sensor device (130) comprises a laser sensor, a lidar sensor, a radar sensor and / or an ultrasonic sensor.

12. Traffic monitoring device (110) according to one of claims 10 to 11, with a lighting device (190), wherein the lighting device (190) is arranged on the traffic monitoring device (110) or adjacent to the traffic monitoring device (110).

13. Computer program product with program code for carrying out the method (200) according to one of the preceding claims 1 to 8, when the computer program product is executed on a device.

14. A machine-readable storage medium on which the computer program according to claim 13 is stored.

Images