METHOD, DEVICE AND RAILWAY VEHICLE, IN PARTICULAR RAILWAY VEHICLE, FOR HAZARD SITUATION DETECTION IN RAIL TRANSPORT, IN PARTICULAR RAIL TRANSPORT

Description

[0001] The invention relates to a method for detecting hazardous situations in railway traffic, in particular in rail traffic, according to the preamble of claim 1, a device for detecting hazardous situations in railway traffic, in particular in rail traffic, according to the preamble of claim 11 and a railway vehicle for detecting hazardous situations in railway traffic, in particular a railway vehicle for detecting hazardous situations in rail traffic, according to the preamble of claim 26.

[0002] Rail vehicles, as part of a modern transport infrastructure, are track-bound means of transport that move, for example, by rolling on or under one or two guide rails (tracks), suspended above or below a magnetic field, or suspended from steel cables. Of these track-bound means of transport, rail vehicles based on a wheel-rail system are the most widespread. These vehicles are either self-propelled (multiple units) or pulled or pushed by a locomotive, and predominantly use flanged steel wheels guided on two steel rails or tracks.

[0003] The object of the invention is to provide a method, a device and a railway vehicle, in particular a rail vehicle, for detecting hazardous situations in railway traffic, in particular in rail traffic, with which hazardous situations in railway traffic, when railway vehicles are traveling on railway lines in the railway network, or hazardous situations in railway traffic, when railway vehicles are traveling on railway lines in the railway network, are automatically detected.

[0004] Document DE 10 2014 206 473 A1 discloses a method for detecting hazardous situations in railway traffic based on image analysis.

[0005] The automatic detection of hazardous situations in rail transport, in particular in rail transport, which is the subject of the present International Patent Application (Application No. PCT / EP2017 / 081841; Publication No. WO 2018 / 104460 A1) and the priority-establishing German Patent Application (Application No. 102016224358.6), is an indispensable necessity with regard to future automated (autonomous) or assisted driving of railway vehicles in rail transport.

[0006] For automated or assisted driving of rail vehicles, it is therefore necessary to detect hazardous situations on platforms, in the area of ​​level crossings or in similar areas (hereinafter referred to as "Dangerous situations on train platforms or similar") and to proceed in such a dangerous situation in accordance with the company's rules, e.g. by emitting a warning tone, acoustic or visual warning signal.

[0007] However, it is not only the aspect of automatic hazard situation recognition that is important for future automated (autonomous) or assisted driving, but also the following aspects, all of which are more or less in a technical context with the present patent application and are therefore listed and whose contents must be considered and possibly even included in this context.

[0008] These are the aspects in question: 1) The automatic detection of signals in railway / rail traffic according to the International Patent Application (Application No. PCT / EP2016 / 057804; Publication No. WO 2017 / 174155 A1) and the technical teaching disclosed therein. 2)The automatic recognition of lanes / tracks in rail traffic according to the German patent application (application no. 102016224335.7) and the international patent application (application no. PCT / EP2017 / 081890; publication no. WO 2018 / 104477 A1) and the technical teaching disclosed therein. 3) The automatic detection of obstacles in rail traffic according to the German patent application (application no. 102016224344.6) and the international patent application (application no. PCT / EP2017 / 081834; publication no. WO 2018 / 104454 A2) and the technical teaching disclosed therein. 4)The alternative determination of positions in rail transport when conventional satellite-based positioning fails or is insufficient, according to the German patent application (application no. 102016224355.1) and the international patent application (application no. PCT / EP2017 / 081784; publication no. WO 2018 / 104427 A1) and the technical teaching disclosed therein. 5) Performing a track-based image analysis in rail transport according to the German patent application (application no. 102016224331.4) and the international patent application (application no. PCT / EP2017 / 081845; publication no. WO 2018 / 104462 A1) and the technical teaching disclosed therein.

[0009] The aforementioned context-related problem is solved, starting from the hazard situation detection method defined in the preamble of claim 1, by the features specified in the characterizing portion of claim 1.

[0010] Furthermore, the aforementioned context-related problem is solved, starting from the hazard situation detection device defined in the preamble of claim 11, by the features specified in the characterizing portion of claim 11.

[0011] Furthermore, the aforementioned context-related problem is solved, starting from the railway vehicle defined in the preamble of claim 26, in particular rail vehicle, by the features specified in the characterizing portion of claim 26.

[0012] The idea underlying the invention according to independent claims 1, 11 and 26 consists of using several images of a danger zone, known with respect to its spatial coordinates and potential hazard situations in rail traffic and partially arranged along a railway line of a railway network, to check by pattern comparison whether persons and / or movable objects are located in the critical sub-area. This sub-area is marked in each image and represents a sub-area of ​​the depicted danger zone that is classified as critical.

[0013] Furthermore, according to claims 2 and 12, it is advantageous if Additionally, based on several images representing the critical sub-area, the images and sub-area images are converted to the same size, taking into account the respective distance to the danger zone, an activity index is calculated by detecting movements of people and / or objects in the danger zone, and the calculated activity index is compared with a stored threshold value.

[0014] The basic principle of the invention is to identify hazardous situations in known danger zones of railway traffic, e.g., on platforms in station areas, level crossings with or without barriers, or the like, through iterative image analysis in combination with known metadata about the danger zones, such as e.g. Platforms, level crossings, etc., can be identified.

[0015] The aim is to enable a contribution to fully automated driving without additional investments in track infrastructure.

[0016] The automated detection of hazardous situations in danger zones of railway traffic, e.g. on platforms in station areas, level crossings with or without barriers, or the like, can be advantageously achieved, at least partially, by the following steps: 1. In a first step, when entering a station area with platforms or approaching a level crossing [the railway vehicle / rail vehicle is aware of the relevant location coordinates based on GPS data or positioning data according to the German patent application (application no. 102016224355.1) and the international patent application (application no. PCT / EP2017 / 081784; publication no. WO 2018 / 104427 A1), which are determined according to the technical teaching disclosed therein], a large number of images are captured or recorded from the railway vehicle, e.g. from the perspective of the train driver, using at least one image recording / acquisition device (e.g. one or more devices such as video cameras, laser sensors, thermal imaging cameras, radar, other image acquisition devices, etc.).

[0017] Multiple copies are primarily relevant for redundancy purposes. a. In a modification or further development / extension of the invention, images from several image recording devices or image acquisition devices of the same type (e.g., two video cameras) can also be used for mutual validation and synthesis of the results. b. In a further modification or further development / extension of the invention, images from several image recording devices or image acquisition devices of different types (e.g., a video camera and a thermal imaging camera) can also be used for mutual validation and synthesis of the results.

[0018] 2. In a second step, an area of ​​the image is marked to show a particularly critical (highly critical) area (e.g., in the case of the platform, the area between the platform edge and the safety strip bounded by a white line, approximately 2m from the platform edge) of the danger zone.

[0019] Option 1: These areas are known from previous initialization runs, for which the most critical (highly critical) areas of the danger zones were marked for each position of the train / rail vehicle within the station area (if a picture is taken twice from the same point upon entering the station area with the platform, the critical area remains the same). In this context, reference is made to the automatic signal recognition in rail traffic according to the international patent application (application no. PCT / EP2016 / 057804; publication no. WO 2017 / 174155 A1) and the technical teaching disclosed therein, where a comparable procedure is used with regard to signal recognition.

[0020] Option 2:First, the occupied lane / track is detected. Starting from the occupied lane / track, the platform edge is identified as the boundary of the danger zone, as well as the distance of the vehicle from the platform or the danger zone, and finally the (highly critical) particularly critical area relative to the platform edge or the boundary of the danger zone. In this context, reference is made to the implementation of a lane / track-based image analysis in rail traffic according to the German patent application (application no. 102016224331.4) and the international patent application (application no. PCT / EP2017 / 081845; publication no. WO 2018 / 104462 A1) and the technical teaching disclosed therein.

[0021] 3.In a third step, the images acquired for the highly critical area are examined to determine whether they predominantly contain people and / or movable objects. This is done through pattern matching.

[0022] If people and / or movable objects are located in the highly critical area, an acoustic signal should be emitted.

[0023] Case 1: Positive matching is used, meaning that people and / or movable objects are detected.

[0024] Case 2: Negative matching is applied, meaning that temporary changes in the structure of the danger zone are detected, for example, the interruption of the regular platform pattern (e.g. stone tiles, white line) is checked.

[0025] 4.In a fourth step, several images are additionally taken at short intervals for the (highly critical) particularly critical sub-area of ​​the danger zone.

[0026] These images are then resized to the same size, taking into account the respective distance to the platform or the edge of the danger zone. An activity index is then calculated by detecting the movement of people and / or movable objects on the platform (e.g., children playing or running around). If this activity index exceeds a threshold, the operational rules should be followed, for example, by sounding a warning tone (e.g., a whistle), an audible or visual warning signal.

[0027] The iterative image analysis of danger zones in rail traffic, e.g., on platforms in station areas, level crossings with or without barriers, or the like, as outlined above, in conjunction with metadata about these danger zones, makes it possible to achieve the following: People and / or movable objects in the (highly critical) particularly critical sub-area of ​​the danger zone can be detected, and reactions can be initiated in accordance with operational rules, e.g., issuing a warning tone (e.g., a whistle), an acoustic or visual warning signal. People and / or movable objects with an excessively high rate of movement (e.g., boisterous children) in the (highly critical) particularly critical sub-area of ​​the danger zone can be detected, and reactions can be initiated in accordance with operational rules, e.g., issuing a warning whistle, warning signal, etc. People can be detected more reliably under unfavorable visibility conditions than by train drivers. Train drivers are no longer needed to detect hazardous situations on platforms or similar, so that trains can operate regardless of their availability.

[0028] In the course of an advantageous further development of the invention, the following additional components - a) to c) for the image recording device (e.g. the image acquisition device) - can be used with regard to the hazard situation detection device according to claim 11: a. A correction component according to claim 21, which incorporates weather and brightness data for the evaluation of the image material. This allows, for example, in heavy fog, the evaluation of video images to be limited to the first 50 meters in front of the train or rail vehicle, and the speed of the vehicle to be reduced accordingly. b.A focal length adjustment component according to claim 22, which selects the correct shooting angle depending on the environment (e.g., train station, urban area, countryside, etc.) in order to optimally support image evaluation. For example, this allows for suitable handling of both shooting situations on open track (requiring images from a great distance to enable timely reactions due to speed) and shooting situations in the station area (requiring images with a high width). Furthermore, the focal length adjustment component allows the correct shooting angle to be selected depending on the distance to the danger zone, thus optimally supporting multiple evaluations of the danger zone. c. A lighting component according to claim 23, for example, a spotlight operating within or outside the human field of vision, which improves the quality of the image captured by the image recording device.The image acquisition device improved the quality of images captured at night or in poor weather conditions.

[0029] Furthermore, it is possible that the hazard situation detection device GSEV is designed and functions as a virtual machine in the sense of a "Software Defined Signal Recognition of Rail Traffic Systems".

[0030] Further advantages of the invention will become apparent from the following description of an exemplary embodiment of the invention based on the FIGURES 1 to 3 These show: FIGURE 1 a train-based detection of a hazardous situation when a train approaches a platform as a critical zone in terms of potential hazards, FIGURE 2 based on the one in the FIGURE 1 The scenario shown is of vehicle-based detection of a hazardous situation when a railway vehicle approaches a level crossing with barriers, which is considered a critical zone in terms of potential hazards. FIGURE 3a basic structure of a hazard situation detection device for the purposes of the FIGURES 1 and 2 Vehicle-based hazard detection at the platform and level crossing.

[0031] FIGURE 1 BVK shows a vehicle-based detection of a hazardous situation in rail traffic when, on a section-by-section railway line BST of a railway network BNE, e.g. in the vicinity of a station, a railway vehicle BFZ approaches a platform BSG on a track FS of the railway line BST as a critical zone with regard to possible hazards.

[0032] According to the present embodiment, the track-related railway line BST of the railway network BNE is a rail line SST of a railway network SNE, on which, for the purpose of hazard detection, a rail vehicle SFZ travels on track GL and approaches platform BSG. Based on the discussion presented at the outset, any other arbitrary short- or long-distance rail transport system is conceivable as a further embodiment of the invention, instead of the depicted rail transport SVK with the rail vehicle SFZ traveling on the rail line SST of the railway network SNE. For example, a magnetic levitation train transport system (e.g., Transrapid, Maglev) with a correspondingly comparable infrastructure consisting of a railway network, railway line, and rail vehicle would also be suitable.

[0033] In the FIGURE 1The depicted rail transport system is equipped with a hazard detection device (GSEV) for the rail vehicle-based detection of potential hazards in a railcar (TRW) of the rail vehicle (SFZ) with a driver's cab (TFS) and integrated display unit (AZE). The GSEV includes an image recording device (BAZG), which can be configured as, for example, a standard video camera, laser sensor, thermal imaging camera, radar system, infrared camera, etc., and is also referred to as an image acquisition device due to its image acquisition capabilities.

[0034] With the image recording device BAZG, when the rail vehicle SFZ traveling on track GL approaches platform BSG, which is a critical zone with regard to potential hazards, a multitude of images BI GB representing the danger zone GB can be captured from the rail vehicle SFZ, e.g., from the perspective of the driver FZF in the driver's cab TFS of the railcar TRW and / or from a fixed, track-monitoring position in or on the vehicle SFZ. This includes images BI GB of a danger zone GB, which is known in terms of its location coordinates and potential hazard situations in rail traffic SVK and is partially arranged along the track SST of the rail network SNE. In other words, the image recording device BAZG receives information as input (e.g.,(in the form of metadata) about potential hazard situations / hazard locations in rail traffic SVK and corresponding location coordinates, and, after / through appropriate triggering (setting a trigger) for these input variables, delivers the images BI GB representing the hazard area as output variables. In the . FIGURE 1 In the case described, the danger zone GB recorded by the image recording device BAZG is part of platform BSG. It is of course also possible that the danger zone GB encompasses the entire platform BSG.

[0035] The images BI GB of the danger zone GB contain an image area BIB that, in relation to the depicted danger zone GB, shows a sub-area TB GB that is classified as particularly critical with regard to potential hazards. In the case of platform BSG, this particularly critical area is preferably the area between the platform edge and the safety strip delimited by a white line, which is located approximately 2 meters from the platform edge. This is a highly critical part of the danger zone GB. Furthermore, when the rail vehicle SFZ traveling on track GL approaches platform BSG, which is a critical zone with regard to potential hazards, the image recording device BAZG also captures a large number of images BI TB representing the critical sub-area TB GB as a highly critical part of the danger zone GB.

[0036] How the hazard situation detection is carried out based on the images BI GB of the danger zone GB and / or the images BI TB of the (particularly) critical sub-zone TB GB will be explained later in connection with the description of FIGURE 3 explained.

[0037] However, regardless of the method of hazard detection, if the hazard detection device GSEV detects a hazardous situation on platform BSG, e.g., moving persons and / or movable objects in the danger zone GB and / or moving persons and / or movable objects in the particularly critical (highly critical) sub-zone TB GB of the danger zone GB, the hazard detection device GSEV transmits a control signal SSI to a control unit STE in the power car TRW of the rail vehicle SFZ, whereupon the power car TRW issues a warning signal WSI. This warning signal WSI is, for example, a warning tone (e.g., a whistle), an acoustic warning signal, or a visual warning signal, representing a reaction in accordance with the operational rules for rail transport SVK.

[0038] FIGURE 2BVK shows a railway vehicle-based detection of a hazardous situation in rail traffic when a railway vehicle BFZ approaches a level crossing BÜG as a critical zone with regard to possible hazards on a section-by-section railway line BST of a railway network BNE on a track FS of the railway line BST.

[0039] The track-related railway line BST of the railway network BNE is again a railway line SST of a railway network SNE, on which, for the purpose of hazard detection, a rail vehicle SFZ travels on track GL and approaches platform BSG. Due to the discussion at the beginning, any other arbitrary short- or long-distance rail transport system is conceivable as a further embodiment of the invention, instead of the depicted rail transport SVK with the rail vehicle SFZ traveling on the railway line SST of the railway network SNE. For example, a magnetic levitation train transport system (e.g., Transrapid, Maglev) with a correspondingly comparable infrastructure consisting of a railway network, railway line, and rail vehicle would also be suitable.

[0040] In the FIGURE 2In the depicted rail transport system, the rail vehicle SFZ, with its driver's cab TFS and integrated display unit AZE (where the driver's workstation is located), houses the hazard detection device GSEV for the rail vehicle-based detection of potential hazards. The hazard detection device GSEV again includes the image recording device BAZG, which can be configured as, for example, a standard video camera, laser sensor, thermal imaging camera, radar system, infrared camera, etc.

[0041] With the image recording device BAZG, when the rail vehicle SFZ traveling on track GL approaches the level crossing BÜG, which is a critical zone with regard to potential hazards, the image recording device BAZG can capture a multitude of images BI GB representing the danger zone GB. This is done from the perspective of the rail vehicle SFZ, e.g., from the driver's perspective FZF in the driver's cab TFS of the railcar TRW and / or from a fixed, track-monitoring position in or on the vehicle SFZ. The image recording device captures images BI GB representing the danger zone GB, which is known in terms of its location coordinates and potential hazard situations in rail traffic SVK and is partially arranged along the track SST of the rail network SNE. In other words, the image recording device BAZG receives information as input (e.g.,(in the form of metadata) about potential hazard situations / hazard locations in rail traffic SVK and corresponding location coordinates, and, after / through appropriate triggering (setting a trigger) for these input variables, delivers the images BI GB representing the hazard area as output variables. In the . FIGURE 2 In the case described, the danger zone GB recorded by the image recording device BAZG encompasses the entire gated level crossing BÜG.

[0042] If the hazard detection device (GSEV) detects a hazardous situation at the level crossing (BÜG), e.g., moving persons and / or movable objects in the danger zone (GB), the GSEV transmits the control signal (SSI) to the control unit (STE) in the railcar (TRW) of the rail vehicle (SFZ). The railcar (TRW) then issues the warning signal (WSI). This warning signal (WSI) can be, for example, a warning tone (e.g., a whistle), an acoustic warning signal, or a visual warning signal, representing a response in accordance with the operational rules for rail transport (SVK).

[0043] FIGURE 3 shows the basic structure of the GSEV hazard situation detection device for the requirements of the FIGURES 1 and 2 Vehicle-based hazard detection at platform BSG and at level crossing BÜG.

[0044] The starting point for the detection of hazardous situations is, according to the explanations regarding the FIGURES 1 and 2 the image recording device BAZG, which, upon a corresponding impulse or trigger (see the explanations in the description of the FIGURE 1 The images BI GB of the hazard zone GB and / or the images BI TB of the sub-zone TB GB are captured for hazard situation detection. How this trigger is generated and transmitted to the image recording device BAZG is not the subject of this application.

[0045] The image recording device BAZG is preferably designed to be swivelled for alignment with the image object.

[0046] Furthermore, it is possible, and potentially also advantageous for data acquisition reasons, to integrate multiple image recording devices (BAZG) of the same type, e.g., multiple video cameras, or devices of different types, e.g., multiple video cameras, laser sensors, radar-based sensors, sensors based on radio-based positioning and distance measurement, infrared cameras, and / or thermal imaging cameras, into the hazard situation detection device (GSEV), which record the images BI GB and BI TG. Such multiple image recording or acquisition systems are particularly relevant for redundancy purposes.

[0047] To further improve the quality of the images recorded or acquired with the BAZG image recording device, the BAZG image recording device preferably includes the following components: 1. A correction component (KOK) that incorporates weather and brightness data into the image analysis. This component makes it possible, for example, to limit the analysis of video images to the first 50 meters in front of the train in heavy fog and to reduce the train's speed accordingly. 2. A focal length adjustment component (BVK) that selects the correct shooting angle depending on the environment (e.g., train station, urban area, countryside, etc.) to optimally support image analysis. This allows for suitable recording situations both on open track (requiring images from a great distance to allow for timely reactions due to speed) and in station areas (requiring images with a high width).Furthermore, the focal length adjustment component allows the correct recording angle to be selected depending on the distance to the danger zone, thus optimally supporting multiple evaluations of the danger zone. 3. A lighting component BLK, designed, for example, as a spotlight operating within or outside the human field of vision, which improves the quality of the image material captured by the image recording device or the image acquisition device BAZG at night or in poor weather conditions.

[0048] The images thus captured are stored by the image recording device BAZG in an image storage device BSPE. This image storage device BSPE is either connected to the image recording device BAZG as a component of the hazard situation detection device GSEV, according to option "A", or, according to option "B", is located outside the hazard situation detection device GSEV, e.g., as a storage database in the railcar or in a data cloud, and is assigned to or connectable with the image recording device BAZG.

[0049] For the evaluation of the recorded or acquired images for the detection of hazards in danger zones GB along the railway line, e.g. the platform BSG according to the FIGURE 1 or the level crossing (BÜG) according to the FIGURE 2The image recording device BAZG is connected to a calculation / evaluation unit BAWE, which is also a component of the hazard situation detection device GSEV. For this purpose, the calculation / evaluation unit BAWE, like the image recording device BAZG, is either connected to the image storage unit BSPE according to option "A" or assigned to or connectable to the image storage unit BSPE according to option "B". In this way, a functional unit is created from the calculation / evaluation unit BAWE, the image recording device BAZG, and the image storage unit BSPE, in which the aforementioned components of the hazard situation detection device GSEV functionally interact for calculation / evaluation-based hazard situation detection.

[0050] For this purpose, the BAWE calculation / evaluation unit preferably has a non-volatile, readable memory SP in which processor-readable control program instructions of a program module PGM controlling hazard situation detection are stored, and a processor PZ that executes the control program instructions of the program module PGM for calculation / evaluation-based hazard situation detection. For this purpose, the processor PZ accesses the image recording device BAZG and the image storage device BSPE for control purposes and to read data.

[0051] The calculation / evaluation unit BAWE or the program module PGM with the processor PZ, which executes the control program commands of the program module PGM for calculation / evaluation-based hazard situation recognition, are now designed with regard to calculation / evaluation-based hazard situation recognition in such a way that in the images BI GB of the hazard area GB, the image area BIB is marked which, in relation to the pictorially represented hazard area GB, shows the sub-area TB GB that is classified as particularly critical (highly critical).

[0052] This marking can now be done, for example, by aligning the image area BIB with the critical sub-area TB GB of the recorded hazard area GB based on the comparison with the one in the FIGURES 1 and 2The respective journey of the rail vehicle SZF is preceded by initialization journeys on the same track GL of the railway line SST of the rail network SNE or based on a process according to the FIGURES 1 and 2 In each case, track- or rail-based image analysis is performed on the depicted journey of the rail vehicle SZF.

[0053] In the first case (variant 1), such danger zones are known from previous initialization runs, in which the danger zone itself and the highly critical part of the danger zone (the particularly critical sub-area) were marked for each position of the rail vehicle in the station area. For example, a picture is taken twice, from the same location. e.g.upon entering the station area with the platform. In this way, the danger zone and the particularly critical sub-area always remain the same. In this context, reference is made to the automatic signal recognition in rail traffic according to the international patent application (application no. PCT / EP2016 / 057804; publication no. WO 2017 / 174155 A1) and the technical teaching disclosed therein, where a comparable approach is taken with regard to signal recognition.

[0054] In the alternative case (variant 2), the track being traversed is first detected. Starting from the track being traversed, the platform edge is identified as the boundary of the danger zone, as well as the distance of the rail vehicle from the platform or the danger zone. Finally, relative to the platform edge or the boundary of the danger zone, the (highly critical) particularly critical sub-area of ​​the danger zone and the danger zone itself are determined. In this context, reference is made to the implementation of a track-based image analysis in rail transport according to German patent application (application no. 102016224331.4) and international patent application (application no. PCT / EP2017 / 081-845; publication no. WO 2018 / 104462) A1 and the technical teaching disclosed therein.

[0055] Is the marking e.g.If the calculation / evaluation unit BAWE performs one of the two variants outlined above, then the calculation / evaluation unit BAWE or the program module PGM with the processor PZ, which executes the control program commands of the program module PGM for calculation / evaluation-based hazard situation recognition, is further designed in such a way that, for the marked image area BIB, it is checked by pattern comparison whether persons and / or movable objects are located in the critical sub-area TB GB.

[0056] The pattern comparison is a pattern matching process in which either a positive comparison is used to preferably detect persons and / or movable objects, or a negative comparison is used to preferably detect temporary changes in the structure of the danger zone GB, whereby in the latter case, for example, the interruption of the regular platform pattern (e.g. stone tiles, white line) is checked.

[0057] For this check to determine whether persons and / or movable objects are located in the critical sub-area TB GB, several images related to the description of the (highly critical) particularly critical sub-area are taken at short intervals. FIGURE 1 The previously mentioned images BI TB were taken.

[0058] After the images BI GB over the danger zone GB have already been captured by the image recording device BAZG, the calculation / evaluation unit BAWE and the image recording device BAZG are further configured and functionally interact in such a way as to capture the images BI TB over the sub-area TB GB. 1) A large number of images representing the critical sub-area TB GB are captured. 2) The entire images BI GB and BI TB are resized to the same size, taking into account the respective distance to the danger zone GB. 3) An activity index is calculated by detecting movements of people and / or objects in the danger zone GB (e.g., playing or romping children) and 4) The calculated activity index is compared with a stored threshold.

[0059] The threshold comparison is performed by the BAWE calculation / evaluation unit or the PZ processor, which executes the control program commands of the PGM program module for calculation / evaluation-based hazard detection. If persons and / or movable objects are located in the critical sub-area TB GB and the comparison shows that the calculated activity index equals or exceeds the threshold, the BAWE calculation / evaluation unit or the PZ processor generates the SSI control signal. This signal indicates the hazard situation in the danger zone GB according to the operational rules for rail transport SVK. This is preferably done by the rail vehicle SFZ issuing the WSI warning signal. It should be noted again that the warning signal can be either acoustic or visual.

[0060] In order to be able to issue the warning signal WSI, the BAWE calculation / evaluation unit of the GSEV hazard situation detection device is connected to the STE control unit in the TRW railcar of the SFZ rail vehicle (see FIGURE 1 ).

[0061] The hazard detection device GSEV, as described above, can assist or even fully implement automated (autonomous) or assisted driving of the rail vehicle BFZ or the rail vehicle SFZ along a route without additional infrastructure. This is particularly true when the hazard detection device GSEV is implemented as a virtual machine designed and functioning as a "Software Defined Signal Recognition of Rail Traffic Systems".

Claims

1. Method for hazardous situation recognition in track-guided traffic (BVK), in particular in rail traffic (SVK), characterized in that wherein a) from a track-guided vehicle (BFZ), in particular a rail vehicle (SFZ), in particular from the perspective of a tractive unit driver (FZF, TFS, TRW) and / or from a stationary, track-observing position in or on the vehicle (BFZ, SFZ), in respect of a hazardous region (GB) which is known with regard to its spatial coordinates and by virtue of potential hazardous situations in track-guided traffic (BVK, SVK) and is arranged partially along a railway section (BST) of a railway network (BNE), in particular a rail section (SST) of a rail network (SNE), a multiplicity of images (BIGB) representing the hazardous region (GB) are captured, b) an image region (BIB) is marked in each of the images (BIGB) , said image region showing, with regard to the pictorially presented hazardous region (GB), a partial region (TBGB) classified as critical, c) for the marked image region (BIB), a check is made by means of pattern comparison to ascertain whether persons and / or movable objects are situated in the critical partial region (TBGB) .

2. Method according to Claim 1, characterized in that a) in respect of the critical partial region (TBGB) a multiplicity of images (BITB) representing the critical partial region are captured, b) the entire images (BIGB, BITB) are converted to the same size, taking into account the respective distance from the hazardous region (GB), c) an activity index is calculated by recognizing movements of persons and / or objects in the hazardous region (GB), and d) the calculated activity index is compared with a stored threshold value.

3. Method according to Claim 1 or 2, characterized in that attention is drawn to the hazardous situation in the hazardous region (GB) according to the operational rules in track-guided traffic (BVK, SVK), preferably by an acoustic warning signal (WSI) being issued, if a) persons and / or movable objects are situated in the critical partial region (TBGB) , b) the comparison reveals that the calculated activity index corresponds to or exceeds the threshold value.

4. Method according to Claim 3, characterized in that the warning signal (WSI) is issued by the track-guided vehicle (BFZ, SFZ) .

5. Method according to any of Claims 1 to 4, characterized in that the images (BIGB, BITG) are recorded by a plurality of image recording device s (BAZG) of identical design, e.g. by video cameras, or of varying design, e.g. by video cameras, laser sensors, RADAR-based sensors based on radio-based locating and distance measurement, infrared cameras, and / or thermal imaging cameras.

6. Method according to any of Claims 1 to 5, characterized in that the marking of the image region (BIB) with regard to the critical partial region (TBGB) of the captured hazardous region (GB) is effected on the basis of previous initialization journeys on the railway sections (BST, SST) of the railway network (BNE, SNE) or on the basis of a track-based image analysis, in particular rail track- or rail-based image analysis.

7. Method according to Claim 6, characterized in that the track-based image analysis involves recognizing firstly a traversed track (FS), in particular a traversed rail track (GL), of the railway section (BST, SST), proceeding from the traversed track (FS, GL) border (RGB) of the hazardous region (GB) and also the distance between the track-guided vehicle (BFZ, SFZ) and the hazardous region (GB) and finally the critical partial region (TBGB) relative to the edge (RGB) of the hazardous region (GB).

8. Method according to any of Claims 1 to 7, characterized in that the pattern comparison is carried out as a positive comparison, in which preferably the persons and / or the movable objects are recognized, or is carried out as a negative comparison, in which preferably temporary changes in the structure of the hazardous region (GB) are recognized.

9. Method according to any of Claims 1 to 8, characterized in that the hazardous region (GB) belongs either to a platform (BSG), where persons get on and / or off the track-guided vehicle (BFZ, SFZ), or to a level crossing (BÜG) with or without barriers.

10. Method according to any of Claims 1 to 9, characterized in that the method assists automated (autonomous) or assisted driving of the track-guided vehicle (BFZ, SFZ) without additional infrastructure along a route.

11. Apparatus (GSEV) for hazardous situation recognition in track-guided traffic (BVK), in particular in rail traffic (SVK), characterized in that a) there is at least one image recording device (BAZG) by means of which, from a track-guided vehicle (BFZ), in particular a rail vehicle (SFZ), in particular from the perspective of a tractive unit driver (FZF, TFS, TRW) and / or from a stationary, track-observing position in or on the vehicle (BFZ, SFZ), in respect of a hazardous region (GB) which is known with regard to its spatial coordinates and by virtue of potential hazardous situations in track-guided traffic (BVK, SVK) and is arranged partially along a railway section (BST) of a railway network (BNE), in particular a rail section (SST) of a rail network (SNE) , a multiplicity of images (BIGB) representing the hazardous region (GB) are capturable and storable in an image storage device (BSPE), b) there is a calculation / evaluation device (BAWE) connected to and functionally cooperating withconnected to and functionally cooperating with the image recording device recording device (BAZG) and the image storage device (BSPE) in such a way, in particular with a non-volatile, readable memory (SP), in which processor-readable control program instructions of a program module (PGM) controlling the hazardous situation recognition are stored, and a processor (PZ), which executes the control program instructions of the program module (PGM) for calculation- / evaluation-aided hazardous situation recognition, that an image region (BIB) is marked in each of the images (BIGB) , said image region showing, with regard to the pictorially presented hazardous region (GB), a partial region (TBGB) classified as critical, c) the calculation / evaluation device (BAWE) is designed in such a way that, for the marked image region (BIB), a check is made by means of pattern comparison to ascertain whether persons and / or movable objects are situated in the critical partial region (TBGD) .

12. Apparatus (GSEV) according to Claim 11, characterized in that a) the calculation / evaluation device (BAWE) and the image recording device recording device (BAZG) are designed and functionally interact in such a way that in respect of the critical partial region (TBGB) a multiplicity of images (BITB) representing the critical partial region are captured, b) the calculation / evaluation device (BAWE), the image recording device (BAZG) and the image storage device (BSPE) are designed and functionally interact in such a way that the entire images (BIGB, BITB) are converted to the same size, taking into account the respective distance from the hazardous region (GB), c) the calculation / evaluation device (BAWE) is designed in such a way that c1) an activity index is calculated by recognizing movements of persons and / or objects in the hazardous region (GB), and c2) the calculated activity index is compared with a stored threshold value.

13. Apparatus (GSEV) according to Claim 11 or 12, characterized in that the calculation / evaluation device (BAWE) is connectable to a control device (STE) in the track-guided vehicle (BFZ, SFZ) and in this case controls the control device (STE) in such a way that attention is drawn to the hazardous situation in the hazardous region (GB) according to the operational rules in track-guided traffic (BVK, SVK), preferably by an acoustic warning signal (WSI) being issued, if a) persons and / or movable objects are situated in the critical partial region (TBGB), b) the comparison reveals that the calculated activity index corresponds to or exceeds the threshold value.

14. Apparatus (GSEV) according to Claim 13, characterized in that the warning signal (WSI) is able to be issued by the track-guided vehicle (BFZ, SFZ).

15. Apparatus (GSEV) according to any of Claims 11 to 14, characterized in that it contains a plurality of image recording device s (BAZG) of identical design, e.g. a plurality of video cameras, or of varying design, e.g. a plurality of video cameras, laser sensors, RADAR-based sensors based on radio-based locating and distance measurement, infrared cameras, and / or thermal imaging cameras, which record the images (BIGB, BITG) .

16. Apparatus (GSEV) according to any of Claims 11 to 15, characterized in that the calculation / evaluation device (BAWE) is designed in such a way that the marking of the image region (BIB) with regard to the critical partial region (TBGB) of the captured hazardous region (GB) is effected on the basis of previous initialization journeys on the railway sections (BST, SST) of the railway network (BNE, SNE) or on the basis of a track-based image analysis, in particular rail track- or rail-based image analysis.

17. Apparatus (GSEV) according to Claim 16, characterized in that the track-based image analysis performed on the calculation / evaluation device (BAWE) makes it possible to recognize firstly a traversed track (FS), in particular a traversed rail track (GL), of the railway section (BST, SST), proceeding from the traversed track (FS, GL) a border (RGB) of the hazardous region (GB) and also the distance between the track-guided vehicle (BFZ, SFZ) and the hazardous region (GB) and finally the critical partial region (TBGB) relative to the edge (RGB) of the hazardous region (GB).

18. Apparatus (GSEV) according to any of Claims 11 to 17, characterized in that the calculation / evaluation device (BAWE) is designed in such a way that the pattern comparison is carried out as a positive comparison, in which preferably the persons and / or the movable objects are recognized, or is carried out as a negative comparison, in which preferably temporary changes in the structure of the hazardous region (GB) are recognized.

19. Apparatus (GSEV) according to any of Claims 11 to 18, characterized in that the hazardous region (GB) belongs either to a platform (BSG), where persons get on and / or off the track-guided vehicle (BFZ, SFZ), or to a level crossing (BÜG) with or without barriers.

20. Apparatus (GSEV) according to any of Claims 11 to 19, characterized in that the image recording device (BAZG) is designed in pivotable fashion.

21. Apparatus (GSEV) according to any of Claims 11 to 20, characterized in that the image recording device (BAZG) has a correction component (KOK), which includes weather and brightness data for the evaluation of the image material.

22. Apparatus (GSEV) according to any of Claims 11 to 21, characterized in that the image recording device (BAZG) has a focal length varying component (BVK), which chooses the correct recording angle depending on the surroundings, e.g. railway station, urban area, countryside, etc., in order thus to optimally support the evaluation of the image (BIGB, BITB) , and / or which chooses the correct recording angle depending on the distance with respect to the hazardous region (GB) in order thus to optimally support the multiple evaluation of the hazardous region (GB).

23. Apparatus (GSEV) according to any of Claims 11 to 22, characterized in that the image recording device (BAZG) has an illumination component (BLK), in particular a spotlight that operates within or outside the range visible to human beings.

24. Apparatus (GSEV) according to any of Claims 11 to 23, characterized by a virtual machine that is designed and functions in the sense of a "Software Defined Signal Recognition of Rail Traffic Systems".

25. Apparatus (GSEV) according to any of Claims 11 to 24, characterized in that the apparatus (GSEV) makes it possible to assist automated (autonomous) or assisted driving of the track-guided vehicle (BFZ, SFZ) without additional infrastructure along a route.

26. Track-guided vehicle (BFZ) for hazardous situation recognition in track-guided traffic (BVK), in particular rail vehicle (SFZ) for hazardous situation recognition in rail traffic (SVK), characterized in that an apparatus (GSEV) for hazardous situation recognition according to any of Claims 11 to 25 is integrated into the track-guided vehicle (BFZ, SFZ).