Method for monitoring taillight, monitoring system and vehicle

Abstract

The invention relates to a method for monitoring a tail lamp (5) of a vehicle (1) by means of a camera (8) oriented rearward, the tail lamp (5) having a lighting unit (7a, 7b, 7c). The tail lamp (5) and / or a lighting environment (U5) illuminated by the tail lamp (5) are / is detected by means of at least one camera (8) and a camera signal (S8) is output. A camera image having pixels is provided in dependence on the output camera signal (S8), and a taillight (5) or a lighting environment (U5) of the vehicle (1) is presented in the lighting pixels of the respective camera image. Brightness values are learned and evaluated at least for light pixels of respective camera images. A functional condition of the tail lamp (5) is ascertained and output depending on the ascertained brightness value.

Description

Technical Field

[0001] The invention relates to a method for taillights of a vehicle, in particular a commercial vehicle, using a camera system, and also to a monitoring system and a vehicle having a monitoring system. Background Art

[0002] Functioning and visible taillights on vehicles are an important safety aspect in road traffic and are therefore subject to numerous regulations. For example, the Road Traffic Permit Ordinance (StVZO) specifies which taillights should be installed on motor vehicles or commercial vehicles and which taillights must be installed at least. Examples of taillights are taillights, brake lights, flashers, reflectors, rear fog lights, reversing lights and license plate lighting.

[0003] Light monitoring methods for such taillights are known from the prior art and are based on a measured power consumption or on monitoring the power supply lines, in particular monitoring individual bulbs or LEDs of the taillight for line interruptions (filament burnout).

[0004] In commercial vehicles, in particular trailers, light monitoring is performed by a trailer light control unit on the drive vehicle or the tractor vehicle, so that monitoring in the trailer depends on whether and to what extent the drive vehicle carries out light monitoring.

[0005] Self-testing of the taillights, for example by means of photodiodes integrated next to the individual bulbs / LEDs of the individual lighting units, also leads to problems, since external coverings of the entire taillight, for example due to dirt or snow, cannot be reliably detected, and the taillight must also notify the controller of the detected fault, i.e. communication must take place, which is again complex and expensive.

[0006] Ultimately, however, the original goal is not achieved by the light monitoring method described in the prior art, i.e. it is not ensured that when the taillights are on, i.e. actually functioning, they are visible or recognizable to the following traffic. For example, the brake lights may not be visible due to the taillights being covered by snow, although the taillights themselves are still functioning and accordingly cannot be identified as being faulty by monitoring the line. Summary of the invention

[0007] The object of the present invention is to specify a method for monitoring the taillights of a vehicle, with which the functioning of the taillights can be monitored simply and reliably. In addition, the object of the present invention is to specify a monitoring system and a vehicle with which the method can be carried out.

[0008] This object is achieved by a method, a monitoring system and a vehicle according to the independent claims. The dependent claims describe preferred developments.

[0009] The method according to the invention for monitoring the rear lights of a vehicle using a camera system, in particular as part of a reversing assistance device, wherein the camera system has a camera that is directed backwards. The camera can thus be directed at the rear space behind the vehicle or behind the respective vehicle part in which the camera is located. The rear lights have a lighting unit. The method comprises the following steps: - The rear lights of the vehicle and / or the lighting environment illuminated by the rear lights are detected by a camera at the vehicle and a camera signal is output. - A camera image with pixels is presented in dependence on the output camera signal, wherein the taillights of the vehicle and / or the lighting environment illuminated by the taillights are presented in the lighting pixels of the respective camera image. Therefore, the pixels of the camera image in which the taillights and / or the lighting environment are presented are referred to as lighting pixels. - A brightness value is known and detected at least for the light pixels of the respective camera image. This may mean that a value representing the brightness is known and processed at least for the light pixels or for some of the light pixels. - Determine and output the functional status of the taillights based on the determined brightness value or at least based on the brightness value associated with the taillights respectively represented in the respective camera image. Output of the functional status can be realized, for example, in the form of a graphical and / or acoustic signal on a user interface.

[0010] It is possible that the camera system has more than one camera and it is also possible that the camera system has more than one camera facing backwards. It is also possible that the vehicle has more than one taillight. In this case, a plurality of taillights or all taillights of the vehicle can be detected by the same camera or by different cameras. The method can thus be carried out simultaneously with one camera or with multiple cameras at one taillight or at multiple taillights or the method can be carried out in parallel for one or more taillights with multiple cameras.

[0011] It can be provided that, before one of the steps for monitoring the taillights, that is to say at least before the functional status of the at least one taillight is determined and outputted as a function of the determined brightness value, it is first checked whether the at least one taillight is activated. For this purpose, an activation signal transmitted via the CAN bus can be evaluated, which conveys the information whether the respective taillight is activated or not. The method is thus only carried out when the taillight to be monitored is also switched on or activated, thereby saving effort and computing power and limiting the output of the functional status to a relevant time period.

[0012] According to the invention, a monitoring system and a vehicle having such a monitoring system are also provided.

[0013] The monitoring system is therefore used to automatically or automatically detect whether the taillights of a vehicle are functioning or visible and can therefore also be perceived by the traffic behind. In this case, either the lights can be imaged directly or the light environment illuminated by the lights when the lights are activated can be imaged, such as the roadway, buildings, the vehicle itself, other vehicles, etc. The functional condition of the taillights therefore includes not only the technical operating capacity of the taillights, which may be impaired, for example, in the case of a defective supply line and / or a defective LED, but also the actual perceptibility, i.e. whether the taillights can fulfil their function of warning and / or increasing visibility for other road users.

[0014] In particular, the disadvantages of conventional light monitoring methods are overcome, according to which covered, ie dirty or snowy, taillights are detected as functional, but these taillights are no longer (fully) visible or perceptible to other road users, so that the taillights can no longer perform their actual intended function. This is done by directly observing the taillights or also by observing the light environment.

[0015] A further advantage is that the camera which supports the driver when maneuvering as part of the reversing assistant is additionally used to monitor the rear lights. The camera can thus fulfil a double function. Such cameras, in particular reversing cameras, are already widely used and will also be a mandatory requirement in the future, for example, in commercial vehicles, so that such cameras are already available anyway. No additional hardware is therefore required, but rather the already existing camera is used.

[0016] Thus, the method according to the invention for monitoring lights can simplify / automate and speed up operating procedures, such as start control (in which the function check of the tail lights is performed). In addition, the safety of the vehicle is increased, in particular in the case of autonomous operation of the vehicle without a driver controlling the vehicle and / or monitoring the driving.

[0017] According to one embodiment of the present invention, the brightness value of at least one taillight is evaluated or its functional state is determined by creating a histogram and / or a pattern representation (in a higher-dimensional feature space) based on the provided camera image, wherein the distribution of the brightness values ​​of at least the light pixels of the respective camera image is presented in the histogram and / or the pattern representation. In this way, it is possible to use the brightness distribution that characterizes the current state to determine the operating capacity of the taillight. If the pattern representation is used, then correspondingly, not only the brightness value but also, for example, hue, saturation, contrast will be available as additional features for evaluation, for example, by means of machine learning.

[0018] Here, it can be provided according to one embodiment that, in order to determine the functional state of at least one taillight, a histogram created from a camera image is compared with a reference histogram, wherein the reference histogram is created from a reference camera image. Alternatively or cumulatively, it can be provided that, in order to determine the functional state of at least one taillight, a pattern representation created from a camera image is compared with a reference pattern representation, wherein the reference pattern representation is created from a reference camera image. This comparison thus includes a comparison of previously captured historical (reference) camera images with the current camera image or the brightness distribution resulting therefrom.

[0019] On the one hand, it can be provided that the fully functioning taillights of the vehicle and / or the lighting environment illuminated by the fully functioning taillights of the vehicle are represented in the reference camera image. The functioning is thus checked in a simple manner by whether the brightness distribution at the time of recording the camera image corresponds to the brightness distribution when the taillights are functioning properly. If, for example, a light pixel is brighter in the reference camera image when the taillights are switched on than in the current camera image when the taillights are switched on, i.e. exhibits a higher intensity, it can be easily concluded that the currently recorded taillight is defective or covered, for example, is dirty or covered by snow, and a corresponding reaction can be made.

[0020] Thus, when the histogram created from the camera image deviates from the reference histogram and / or the pattern rendering created from the camera image deviates from the reference pattern rendering, the taillight or a taillight being defective or covered can be detected and output as a functional condition. In this way, the operating capacity can be detected and output simply and reliably.

[0021] On the other hand, it can also be provided that the reference camera image presents the deactivated taillights of the vehicle and / or the lighting environment when the taillights of the vehicle are deactivated. The operating capability can therefore be checked in a simple manner by the fact that the brightness distribution at the moment of capturing the camera image (when the taillights are activated) is different from the brightness distribution when the taillights are deactivated (reference camera image), which is accepted because the captured brightness should change. When the histogram created from the camera image corresponds to the reference histogram and / or the pattern presentation diagram created from the camera image corresponds to the reference pattern presentation diagram, it can then be detected and output as a functional condition that the taillight or a certain taillight is defective or covered, because the brightness does not change in this case. In this way, it is also possible to simply and reliably detect and output the operating capability.

[0022] According to another embodiment, it is provided that the histogram is subjected to brightness adjustment before being compared with a reference histogram and / or the pattern rendering diagram is subjected to brightness adjustment before being compared with a reference pattern rendering diagram, wherein, for this purpose, the brightness values ​​presented in the histogram or the pattern rendering diagram are adjusted depending on the current ambient brightness. It will be taken into account that the ambient brightness may change strongly, for example due to daytime or due to the environment, which also has an impact on the histogram and / or the pattern rendering diagram or the brightness values ​​imaged therein. In order to take this effect into account, the ambient brightness is removed or the histogram and / or the pattern rendering diagram is correspondingly standardized in terms of brightness, so as to provide a histogram or pattern rendering diagram for comparison with a reference independently of the ambient brightness. The ambient brightness can be obtained, for example, by averaging the brightness values ​​of all pixels of the camera image or the brightness values ​​of all pixels other than the light pixels.

[0023] According to another embodiment, it can be provided that, in order to determine the functional status of the taillights, it is determined whether the brightness values ​​of the histogram and / or the pattern rendering are within the rated brightness range assigned to the respective taillight. A plurality of rated brightness ranges can be assigned to each taillight. It is therefore also possible to check whether a unique brightness value for the respective taillight is detected in the histogram and / or in the pattern rendering, wherein this may be related to the color of the light-emitting unit of the taillight or contained in the taillight, for example. It is therefore also possible to assign a rated brightness range to each light-emitting unit of the respective taillight, so that the rated brightness range can be read from the histogram and / or the pattern rendering in a lamp-specific manner.

[0024] In this case, it can also be provided that it is additionally determined whether the brightness value of at least one specific setpoint pixel fraction lies within the setpoint brightness range assigned to the respective taillight. Thus, not only is it checked whether a specific brightness value occurs in the histogram and / or the pattern display, but also the frequency of brightness values ​​within the brightness range. In this way, it is also possible to draw conclusions about the degree of functional capacity, such as partial defects or partial covering.

[0025] If, for example, the brightness values ​​of a histogram and / or a pattern representation created from the camera image are not within an assigned setpoint brightness range or are not within at least one assigned setpoint brightness range for a certain setpoint pixel fraction, then it can be detected and output as a functional condition that the taillight or a taillight is defective or covered. In this way, a simple check and output of the functional capability of the taillight is provided.

[0026] According to a further embodiment of the method, the light monitoring is also improved or made more stable by a calibration step, wherein the number of pixels considered for evaluating the brightness value is further limited by the calibration step. This can be done, for example, in that the brightness values ​​are only determined and evaluated for static pixels of the provided camera image, wherein the light pixels are included as a subset of the static pixels.

[0027] During the driving of the vehicle, all non-static, i.e., dynamic pixels change, so that the dynamic pixels represent the constantly changing environment around the vehicle. By detecting these dynamic pixels, it is possible to infer clearly the static pixels in the camera image that represent objects that are fixed relative to the camera and thus relative to the vehicle. By identifying the static pixels, the area in the camera image where the taillights are located can be first delimited, because the taillights are connected to the vehicle in a fixed position relative to the vehicle and the light pixels are therefore a component or subset of these static pixels. Therefore, the contour of the vehicle including the taillights that can be seen in the camera image can be (preliminarily) identified during the driving of the vehicle by this motion image comparison or this distinction between dynamic and static pixels.

[0028] With the aid of histograms, the identification of taillights in camera images can be further refined, so that it is possible to determine and evaluate brightness values ​​only for light pixels of a provided camera image, wherein light pixels are identified in that the brightness values ​​of pixels, in particular only static pixels, of the provided camera image when the respective taillights are activated and then deactivated are evaluated over time, wherein pixels whose brightness values ​​change over time due to the activation and then deactivation of the respective taillights are identified as light pixels.

[0029] In order to more accurately define the positioning of the tail lights in the camera image, the tail lights can be activated and deactivated in a controlled manner during the initial calibration in a fully functional state, while observing the brightness values. As a result, light pixels can be found in the camera image in a simpler and more reliable manner and the subsequent evaluation of the brightness values ​​during vehicle operation can be limited to these light pixels, which reduces the evaluation effort and makes the recognition more stable, because the "background" of brightness values ​​that do not belong to the tail lights will not be contained in the histogram or this "background" can be minimized.

[0030] In another embodiment of the method, light monitoring is performed for the power vehicle taillights at the power vehicle of the vehicle and / or for the trailer taillights at the trailer of the vehicle, wherein the respective taillights have at least one light-emitting unit selected from the group consisting of: reflectors, brake lights, taillights, rear fog lights, license plate lighting devices, flashers, and width marker lights.

[0031] The functional status of a taillight or taillights can thus be determined and output individually and, if necessary, also for each lighting unit, so that individual taillights or lighting units can be replaced, repaired and / or cleaned in a targeted manner. The method is therefore not limited to specific vehicle models.

[0032] In a further embodiment of the method, a heating element at the respective tail light and / or a cleaning device of the respective tail light is controlled as a function of at least the detected and evaluated brightness values ​​for the light pixels of the respective camera image and / or as a function of the detected and outputted functional state of at least one tail light.

[0033] The new LED lights can have a heating element in order to melt the snow cover and thus ensure visibility of the light when it snows. Advantageously, the heating element is only switched on as needed to save energy, which can advantageously be done in coordination with the functional conditions known in advance. Dirt and / or snow can be removed from the camera or the taillights by means of a cleaning device, such as a wiper or a spraying device, in particular for the camera or for the taillights. If the functional condition first indicates that a defective or covered taillight is present, a reliable camera image can be established again by means of a cleaning attempt or the taillight can be illuminated again.

[0034] After the heating element and / or the cleaning device have been activated, the method can then be repeated and the functional state can be checked again in order to indicate a final defect later. This avoids outputting an erroneous functional state of the taillights due to covering of the taillights or the camera (dirt / snow).

[0035] In one embodiment of the monitoring system, it is provided that at least one rearward-oriented camera has a detection range with an opening angle of ≥180°, the camera being in particular a fisheye camera, so that the camera can directly detect at least one taillight and the lighting environment. It is thus possible to detect the taillights with only one camera at the rear side of the respective vehicle or vehicle part. Such a camera can also be effectively used in a reversing assistance device, because the camera detects a large part of the rear space behind the vehicle or behind the relevant vehicle part. The taillights of the vehicle are usually also within this detection range. However, it can also be provided that the camera can only detect the lighting environment when, for example, the fisheye camera has not yet been used or the field of view is blocked. In this case, the lighting monitoring can also be performed as described by detecting only the lighting environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The invention is explained in more detail below with the aid of the accompanying drawings.

[0037] Figure 1 shows a schematic top view of a vehicle with a camera system;

[0038] Figure 2 shows a histogram with an exemplary distribution of brightness values ​​of a taillight detected via a camera system;

[0039] Figure 3a showing a camera image of a camera of a camera system;

[0040] Figure 3b A camera image of a camera is shown, wherein only dynamic pixels are shown;

[0041] Figure 3c showing a camera image of the camera, wherein only static pixels are shown; and

[0042] Figure 4 A flow chart diagram of the method according to the invention is shown. DETAILED DESCRIPTION

[0043] Figure 1 A schematic top view of a trailer 2b or semitrailer is shown as a component of a vehicle 1, which, as indicated, also has a motor vehicle 2a as a tractor. The vehicle 1 has a camera system 4, which has a camera 8, in particular a rearward-facing trailer camera 8b arranged on the trailer 2b, which can be a component of a reversing assistant 3, for example, and a control unit 6. The control unit 6 can also be arranged in the motor vehicle 2a.

[0044] The trailer camera 8b is provided with a fisheye lens, that is, the trailer camera is implemented as a fisheye camera 9 (also called Fisheye camera) and therefore has a detection range E with an opening angle ≥180°. The motor vehicle 2a can also have a rearward-oriented motor vehicle camera 8a as a component of the camera system 6, which is implemented as a fisheye camera 9 and can be a component of the reversing assistant 3. In this way, the motor vehicle 2a can be assisted in approaching the trailer 2b, for example during a coupling process.

[0045] The controller 6 is configured to execute a method for monitoring the taillights 5 of the vehicle 1, in particular the trailer taillights 5b at the trailer 2b, wherein each trailer taillight 5b in the illustrated embodiment is respectively composed of three light-emitting units 7a, 7b, 7b, which emit light into the lighting environment U5, in particular onto the ground, buildings, the vehicle 1, other vehicles, etc., when the respective taillights 5 are activated. However, the method can also be used to monitor the power vehicle taillights 5a at the power vehicle 2a, in particular when the trailer 2b is not coupled. In addition, the method can also be used to monitor the taillights 5 of a one-section vehicle 1 having only the power vehicle 2a, such as a box truck, a luggage truck, a flatbed truck, etc.

[0046] In order to carry out such monitoring, the control unit 6 is connected via a corresponding interface 6a to a bus system 10 of the vehicle 1, for example a CAN bus, so that it can first be determined whether the respective tail light 5 of the vehicle 1 is activated or not. In this case, a corresponding message or activation signal S5 with information about the activation or deactivation of the tail light 5 is transmitted via the bus system 10. Monitoring is only meaningful when the respective tail light 5 is activated.

[0047] The monitoring system 20 composed of the controller 6 and the camera system 4 or the camera 8; 8a; 8b can be used, for example, in the following manner: Figure 4 The method for monitoring the taillights 5; 5a, 5b of the vehicle 1 is performed in the steps shown in: - detecting at least one taillight 5; 5a, 5b of the vehicle 1 and / or the light environment U5 of the taillight by means of a camera 8; 8a, 8b at the vehicle 1 and outputting a camera signal S8; S8a, S8b (ST1); - providing a camera image B; Ba, Bb with pixels P or image points as a function of the output camera signal S8; S8a, S8b, wherein at least one rear light 5; 5a, 5b of the vehicle 1 and / or a light environment U5 is represented in the light pixel PL of the respective camera image B; Ba, Bb (ST2); - at least for the respective camera images B; Ba, Bb, the light pixel PL is known and evaluated with a brightness value HW (ST3) and - As a function of the determined and evaluated brightness values ​​HW, in particular the brightness values ​​HW associated with the taillights 5; 5a, 5b and / or the lighting environment U5 respectively represented in the respective camera images B; Ba, Bb, a functional state F of at least one taillight 5; 5a, 5b is determined and output (ST4).

[0048] By means of respective cameras 8; 8a; 8b with fisheye lenses, it is possible to Figure 1 As indicated by the dotted semicircle (detection range E) in the first step ST1, the lighting environment U5 projected by all the taillights 5; 5a, 5b of the two-section vehicle 1 and the light of the respective taillights 5; 5a, 5b is detected. Next, in the second step ST2, the generated camera signals S8; S8a, S8b and / or the camera images B; Ba, Bb formed therefrom are transmitted to the controller 6, and then the controller performs light / dark recognition, especially for the light pixels PL, in the provided camera images B; Ba, Bb based on the brightness values ​​HW acquired in the third step ST3.

[0049] In such processing of the respective camera images B; Ba, Bb, it is possible that brightness values ​​HW of pixels P which are not assigned to the tail lights 5; 5a, 5b or the lighting environment U5 or cannot be clearly assigned are also determined and evaluated, for example because clear delimitation of image areas with and without tail lights 5; 5a, 5b or with and without illuminated lighting environment U5 is not possible or is not provided. This is taken into account accordingly in the subsequent observations.

[0050] When performing light and dark recognition, the determined brightness values ​​HW can be subjected to a histogram comparison, for example, in a first evaluation step ST3.1. Within the scope of the histogram comparison, the distribution of the brightness values ​​HW of the relevant pixels P is presented in a histogram H, such as Figure 2 This created histogram H can then be compared with the reference histogram HR ( Figure 2 The distribution of the brightness values ​​HW of the relevant pixels P is also plotted in the reference histogram HR.

[0051] The reference histogram HR is derived from a previously recorded historical reference camera image BR, in which, for example, fully functioning taillights 5; 5a, 5b or a lighting environment U5 illuminated by these taillights are presented. Therefore, the histogram comparison in this embodiment includes a comparison of historical brightness values ​​HW in a fully functioning state of the taillights 5; 5a, 5b with brightness values ​​HW for the current state of the taillights 5; 5a, 5b.

[0052] In this case, it can be provided that the histogram H is first subjected to a brightness adjustment before being compared with the reference histogram HR, wherein for this purpose the brightness values ​​HW presented in the histogram H are adjusted as a function of the current ambient brightness UH. It is thereby taken into account that the ambient brightness UH may change strongly, for example due to the time of day or due to the environment, which also has an effect on the histogram H or the brightness values ​​HW imaged therein. In order to be able to take this effect into account, the ambient brightness UH is removed or the histogram H is correspondingly standardized in terms of brightness, so that a histogram for comparison with the reference histogram HR is available independently of the ambient brightness UH. The ambient brightness UH can be determined, for example, by averaging the brightness values ​​HW of all pixels P of the camera images B; Ba, Bb or the brightness values ​​HW of all pixels P other than the light pixels PL.

[0053] If it is then determined from the reference histogram HR that for fully functioning taillights 5; 5a, 5b there is a deviating or higher intensity than that obtained from the current histogram H, then it can be inferred that the taillight(s) 5; 5a, 5b represented in the current camera image B; Ba, Bb or the taillight(s) 5; 5a, 5b illuminating the presented light environment U5 are defective or covered (dirt or snow). Whether defective or covered, this will of course result in a change, in particular a reduction, of the respective brightness value HW (relative to the expected brightness value). Therefore, in the fourth step ST4, the functional status F is output accordingly.

[0054] According to another embodiment, in coordination with the activation signal S5, the reference histogram HR can also be derived from a historical reference camera image BR previously captured with the tail lights 5; 5a, 5b deactivated, while the histogram H is derived from the current camera image B; Ba, Bb after the tail lights 5; 5a, 5b are activated. In this embodiment, the histogram comparison includes a comparison of the historical brightness values ​​HW in the deactivated state of the tail lights 5; 5a, 5b with the brightness values ​​HW for the current state of the tail lights 5; 5a, 5b in the activated state. This embodiment is then suitable for the presentation of the light environment U5 illuminated by the tail lights 5; 5a, 5b and for the direct presentation of the tail lights 5; 5a, 5b in the light pixels PL.

[0055] However, in other embodiments, the operating capacity of the taillights 5; 5a, 5b can also be inferred from the histogram H without relying on the reference histogram HR. For this purpose, in the second evaluation step ST3.2, it is determined, for example, whether a plurality of brightness values ​​HW are within one or more desired brightness ranges HSoll of the histogram H that are expected for the respectively presented or used taillights 5; 5a, 5b, optionally also taking into account the ambient brightness UH as described above. For this purpose, for example, a desired pixel share PSoll (relative or absolute) of the pixels P that are within the one or more desired brightness ranges HSoll can be determined. The desired pixel share PSoll can, for example, be based on the size of the image segment being observed (the number of pixels P) and / or the resolution of the camera images B; Ba, Bb and / or the type of lighting environment U5 that is illuminated (gravel, asphalt, buildings, the vehicle 1, etc.).

[0056] In addition, one or more rated brightness ranges HSoll are assigned to each taillight 5; 5a, 5b depending on the type and size of the light-emitting unit 7a, 7b, 7c located therein, because, for example, a taillight 5; 5a, 5b that emits purely red light will cause the distribution of brightness values ​​HW in the histogram H to be different from the distribution of a taillight 5; 5a, 5b that emits purely orange light or purely white light or a taillight 5; 5a, 5b having light-emitting units 7a, 7b, 7c that emit light of different colors.

[0057] In a fourth step ST4, the functional status F of the respective taillight 5; 5a, 5b can then be determined based on whether the set pixel share PSoll for the respectively associated set brightness range HSoll is reached (or exceeded). If taillights 5; 5a, 5b with light units 7a, 7b, 7c emitting light of different colors are present side by side, then a plurality of set brightness ranges HSoll (separately for each color) can also be subjected to such an evaluation simultaneously and the functional status F for the different light units 7a, 7b, 7c can be determined in parallel with one another.

[0058] Thus, light monitoring can also be carried out with the aid of camera system 4 , which is already present as a component of reversing assistance device 3 in vehicle 1 , by correspondingly expanding the signal evaluation in control unit 6 .

[0059] According to another embodiment, it can be provided that, instead of the histogram H, a pattern rendering diagram M is considered for evaluating the brightness value HW, in which not only the brightness is observed as a dimension, but also, for example, the color channel (RGB), saturation, contrast, etc. are observed. The pattern rendering diagram M is therefore used in a feature space of higher dimensions, which enables a more detailed evaluation. Then, the lighting monitoring can be performed by comparing the pattern rendering diagram M with a reference pattern rendering diagram MR in a manner similar to that for the histogram H, for example, by means of machine learning tools. As described for the reference histogram, the reference pattern rendering diagram MR is generated here under the same conditions for additional features of the feature space.

[0060] Additionally, the positioning of the light pixels PL in the camera images B; Ba, Bb can be calibrated in advance in a calibration step ST2.1, which further improves the reliability of the method or makes the recognition more stable, because the brightness values ​​HW or features of the light pixels PL in the camera images B; Ba, Bb or in the reference camera image BR can be mainly considered to create the histogram H or pattern presentation diagram M and possible reference histogram HR or reference pattern presentation diagram MR.

[0061] to this end, Figure 3a A black-and-white camera image Bb recorded by the trailer camera 8b is shown, which is composed of a plurality of pixels P. This camera image Bb of the trailer camera 8b also shows the fixed relative positioning of the trailer taillights 5b or the light pixels PL assigned to these trailer taillights. The positioning of these light pixels PL does not change, because both the trailer camera 8b and the trailer taillights 5b are firmly connected to the vehicle 1 or the trailer 2b and therefore their relative positioning to each other is fixed.

[0062] This can be used to calibrate the positioning of the light pixels PL. For this purpose, the camera image Bb of the trailer camera 8b is shown in Figure 3b and 3c As shown in FIG. 1 , the pixel PD is divided into regions with dynamic pixels PD ( Figure 3b , shaded) and an area with static pixels PS ( Figure 3c , shaded). The starting point here is that the dynamic pixels PD change due to the changing environment when the vehicle 1 is traveling, while the trailer 2b is represented unchanged in the static pixels PS. Therefore, the trailer taillights 5b or the light pixels PL assigned to these trailer taillights fall as a subset in the area of ​​the static pixels PS, wherein the static pixels PS can be identified by corresponding image processing.

[0063] Thus, the number of pixels P considered for creating the histogram H or the pattern representation M based on the camera image Bb of the trailer 2b is already significantly reduced when only static pixels PS are used. The same applies to the creation of the reference histogram HR or the reference pattern representation MR in the first evaluation step ST3.1, wherein only static pixels PS in the reference camera image BR are used for this purpose.

[0064] However, this can be further refined by creating a histogram H or a pattern display M for these static pixels PS during initial installation, for example, when activating and subsequently deactivating the trailer taillight 5b, and evaluating them over time. Based on the change in the brightness value HW or the characteristic during this initial activation / deactivation, it can be known in advance for each individual static pixel PS whether it is assigned to the trailer taillight 5b or whether this static pixel PS is a light pixel PL. This knowledge can then be taken into account for the subsequent monitoring of the trailer taillight 5b by using only the light pixels PL that have been identified to create the current histogram H or the current pattern display M. The histogram H or the pattern display M created after the initial activation of the trailer taillight 5b can then also be stored at the same time as a reference histogram HR or a reference pattern display MR.

[0065] If such a fine selection of static pixels PS is not possible, then at least in the second evaluation step ST3.2, when evaluating the histogram H or the pattern display M, a "background" (components other than the taillights 5; 5a, 5b) is taken into account, which leads to a corresponding change in the distribution of the brightness values ​​HW or the features. This background can also be found again in the reference histogram HR or the reference pattern display MR in the first evaluation step ST3.1, so that it is already taken into account in the histogram comparison or the pattern display comparison.

[0066] If the respective cameras 8; 8a, 8b are still designed so that they can only reliably detect the lighting environment U5, that is, the environment illuminated by the respective taillights 5; 5a, 5b or lighting units 7a, 7b, 7c, but cannot reliably detect or completely detect the respective taillights 5; 5a, 5b or lighting units 7a, 7b, 7c themselves, then this refined selection of static pixels PS can also only be carried out conditionally. In this case, a histogram comparison or pattern comparison between activated and deactivated taillights 5; 5a, 5b or lighting units 7a, 7b, 7c or an evaluation of the setpoint pixel proportion PSoll of the respectively associated setpoint brightness range HSoll is used.

[0067] Furthermore, the described selection of the pixels P by division into static and dynamic pixels PS, PD also takes place in a consistent manner for a powertrain taillight 5 a or any other taillight 5 on the vehicle 1 .

[0068] Depending on the functional state determined, the heating element 14 can then be switched on, for example, depending on the situation, and can heat the respective taillight 5; 5a, 5b or the lighting unit 7a, 7b, 7c in a targeted manner, for example to melt snow coverings that could lead to a reduction in the brightness value HW. The heating element can thus be used in an energy-saving manner only if a possible snow covering is inferred based on the functional state F. The cleaning device 15 can also be activated in a targeted manner, for example to clean dirty taillights 5; 5a, 5b, which could also lead to a reduction in the brightness value HW.

[0069] After the heating element 14 and / or the cleaning device 15 have been activated in this way, the monitoring can be performed again in the described steps. If the brightness value HW still indicates that the taillight 5; 5a, 5b is defective or covered, then this can ultimately be output as a functional status F, so that the driver can react accordingly.

[0070] List of reference numerals (part of the description)

[0071] 1 Vehicle

[0072] 2a Power car

[0073] 2b Trailer

[0074] 3 Reversing assist device

[0075] 4-Camera System

[0076] 5a Tail lights of power car 2a

[0077] 5b Tail lights of trailer 2b

[0078] 6 Controller

[0079] 6a Interface

[0080] 7a, 7b, 7c Light-emitting unit

[0081] 8 Camera

[0082] 8a Power Car Camera

[0083] 8b Trailer Camera

[0084] 9 Fisheye Camera

[0085] 10 Bus system

[0086] 14 Heating element

[0087] 15. Cleaning Equipment

[0088] 20 Monitoring System

[0089] B Camera image of camera 8

[0090] Ba Power Car Camera 8a Camera Image

[0091] Bb Camera image of trailer camera 8b

[0092] BR Reference Camera Image

[0093] E Detection range

[0094] F Functional status

[0095] H Histogram

[0096] HR Reference Histogram

[0097] HW brightness value

[0098] HU Ambient brightness

[0099] M pattern presentation

[0100] MR reference pattern rendering

[0101] P Pixel

[0102] PL Light Pixels

[0103] S5 Activation Signal

[0104] S8 Camera 8 camera signal

[0105] S8a Camera signal of power car camera 8a

[0106] S8b Camera signal from trailer camera 8b

[0107] U5 Lighting Environment

Claims

1. A method for monitoring the taillights (5) of a vehicle (1) using a camera system (4), wherein: The camera system (4) has a rearward-facing camera (8), wherein the taillight (5) has a lighting unit (7a, 7b, 7c), and the method comprises the following steps: - detecting the taillight (5) of the vehicle (1) and / or the lighting environment (U5) illuminated by the taillight (5) by a camera (8) at the vehicle (1) and outputting a camera signal (S8) (ST1); - providing a camera image (B) having pixels (P) as a function of the output camera signal (S8), wherein the taillights (5) of the vehicle (1) and / or the light environment (U5) illuminated by the taillights (5) are represented in the light pixels (PL) of the respective camera image (B) (ST2); - for the light pixels (PL) of the respective camera image (B), a brightness value (HW) is known and evaluated (ST3); and - as a function of the determined brightness value (HW), the functional status (F) of the taillight (5) is determined and output (ST4).

2. The method according to claim 1, characterized in that In order to determine the functional status (F) of the taillight (5) based on the provided camera image (B), a histogram (H) and / or a pattern presentation diagram (M) is created, wherein the distribution of brightness values ​​(HW) of at least the light pixels (PL) of the respective camera image (B) is presented in the histogram (H) and / or in the pattern presentation diagram (M).

3. The method according to claim 2, characterized in that In order to know the functional status (F) of the taillight (5), - provide a reference camera image (BR), and - comparing (ST3.1) a histogram (H) created based on the camera image (B) with a reference histogram (HR), wherein the reference histogram (HR) is created based on the reference camera image (BR), and / or - comparing (ST3.1) a pattern rendering map (M) created based on the camera image (B) with a reference pattern rendering map (MR), wherein the reference pattern rendering map (MR) is created based on the reference camera image (BR).

4. The method according to claim 3, characterized in that Presented in the reference camera image (BR) is a taillight (5) of a vehicle (1) in a fully functioning state, and / or presented in the reference camera image (BR) is a lighting environment (U5) illuminated by the taillight (5) of the vehicle (1) in a fully functioning state, Among them, when - a histogram (H) created from the camera image (B) deviates from the reference histogram (HR) and / or - when the pattern representation (M) created based on the camera image (B) deviates from the reference pattern representation (MR), Whether the tail light (5) is defective or covered is detected as a functional condition (F) and output (ST4).

5. The method according to claim 3, characterized in that: Presented in the reference camera image (BR) are taillights (5) of the vehicle (1) in a deactivated state, and / or presented in the reference camera image (BR) are lighting environments (U5) in a state in which the taillights (5) of the vehicle (1) are in a deactivated state, Among them, when - a histogram (H) created from said camera image (B) corresponds to said reference histogram (HR), and / or - when the pattern presentation map (M) created based on the camera image (B) corresponds to the reference pattern presentation map (MR), Whether the tail light (5) is defective or covered is detected as a functional condition (F) and output (ST4).

6. The method according to any one of claims 3 to 5, characterized in that make - said histogram (H) before comparison with said reference histogram (HR), and / or - the pattern presentation image (M) before being compared with the reference pattern presentation image (MR), A brightness adjustment is performed, wherein for this purpose the brightness values ​​(HW) represented in the histogram (H) and / or the pattern representation map (M) are adjusted as a function of the current ambient brightness (HU).

7. The method according to any one of claims 2 to 6, characterized in that In order to determine the functional status (F) of the taillight (5), it is determined whether the brightness values ​​(HW) of the histogram (H) and / or the pattern rendering (M) are within at least one setpoint brightness range (HSoll) assigned to the respective taillight (5).

8. The method according to claim 7, characterized in that In addition, it is determined whether a brightness value (HW) of at least one certain setpoint pixel fraction (PSoll) lies within at least one setpoint brightness range (HSoll) associated with the respective tail light (5).

9. The method according to claim 8, characterized in that When the brightness values ​​of the histogram (H) created based on the camera image (B) and / or the brightness values ​​(HW) of the pattern rendering (M) created based on the camera image (B) are not within at least one assigned setpoint brightness range (HSoll) or are not within at least one assigned setpoint brightness range (Hsoll) for a certain setpoint pixel share (PSoll), it is detected as a functional condition (F) that the taillight (5) is defective or covered and is output (ST4).

10. The method according to any one of claims 7 to 9, characterized in that A setpoint brightness range (H setpoint ) is assigned to each luminous unit ( 7 a , 7 b , 7 c ) of the respective taillight ( 5 ).

11. The method according to any one of the preceding claims, characterized in that Brightness values ​​(HW) are determined and evaluated only for static pixels (PS) of the provided camera image (B), wherein the light pixels (PL) are contained in the static pixels (PS).

12. The method according to claim 11, characterized in that In advance, in a calibration step (ST2.1), static pixels (PS) of a provided camera image (B) are identified while the vehicle (1) is traveling.

13. The method according to any one of the preceding claims, characterized in that Brightness values ​​(HW) are determined and evaluated only for light pixels (PL) of a provided camera image (B), wherein the light pixels (PL) are identified in that the brightness values ​​(HW) of pixels (P) of the provided camera image (B) when the respective tail light (5) is activated and then deactivated are evaluated over time, wherein pixels (P) whose brightness values ​​(HW) change over time due to the respective tail light (5) being activated and then deactivated are identified as light pixels (PL).

14. The method according to any one of the preceding claims, characterized in that Monitoring of the taillights (5) is performed for the power vehicle taillights (5a) at the power vehicle (2a) of the vehicle (1) and / or the trailer taillights (5b) at the trailer (2b) of the vehicle (1), wherein the respective taillights (5) have a light-emitting unit (7a, 7b, 7c) selected from the group consisting of: reflectors, brake lights, rear lights, rear fog lights, license plate lighting devices, flashers, and width lights.

15. The method according to any one of the preceding claims, characterized in that A heating element (14) at the respective tail light (5) and / or a cleaning device (15) of the respective tail light (5) is controlled as a function of at least a detected and evaluated brightness value (HW) for a light pixel (PL) of the respective camera image (B) and / or as a function of the detected and outputted functional state (F) of the tail light (5).

16. The method according to claim 15, characterized in that After the heating element (14) and / or the cleaning device (15) have been activated, the method is carried out again.

17. A method according to any one of the preceding claims, characterised in that Before the functional state (F) of the tail light (5) is determined and output (ST4) as a function of the determined brightness value (HW), it is checked whether the tail light (5) is activated.

18. A monitoring system (100) for a vehicle (1), the monitoring system comprising: a camera system (4) having a rearward-facing camera (8) for detecting the rear lights (5) of the vehicle (1) and / or the light environment (U5) illuminated by the rear lights (5), wherein: The camera (8) is configured to output a camera signal (S8), and - a controller (6), in particular a controller for carrying out the method according to any of the preceding claims, wherein the controller (6) is designed to: - processing camera images (B) with pixels (P) provided in dependence on the output camera signal (S8), wherein the taillights (5) of the vehicle (1) and / or the lighting environment (U5) illuminated by the taillights (5) are represented or imaged in the light pixels (PL) of the respective camera images (B); - determine and output a brightness value (HW) for at least the light pixel (PL) of the respective camera image (B); and - determining and outputting a functional state (F) of the taillight (5) as a function of the determined brightness value (HW).

19. The monitoring system (20) according to claim 18, characterized in that The rearward-directed camera (8) has a detection range (E) such that the at least one taillight (5) and the light environment (U5) can be directly detected by the camera (8), in particular by configuring the rearward-directed camera (8) as a fisheye camera (9); or such that only the light environment (U5) can be detected.

20. The monitoring system (20) according to claim 18 or 19, characterized in that The camera system (4) is a component of the reversing assistance device (3).

21. The monitoring system (20) according to any one of claims 18 to 20, characterized in that The controller (6) has an interface (6a) for receiving an activation signal (S5), wherein the activation signal (S5) conveys whether the tail light (5) is activated or not activated, and the controller (6) is configured to confirm whether the tail light (5) is activated with the help of the activation signal (S5) before determining the functional status (F) of the tail light (5).

22. A vehicle (1), in particular a commercial vehicle, having a monitoring system (20) according to any one of claims 18 to 21, wherein: The camera (8) is a power vehicle camera (8a) on a power vehicle (2a) of the vehicle (1) and / or a trailer camera (8b) on a trailer (2b) of the vehicle (1), the cameras being respectively oriented backwards.

Images