RU2745531C2 - Method, a device and a railroad vehicle, in particular, a rail vehicle, for recognizing dangerous situations in railway service, in particular, in rail operation - Google Patents

Abstract

FIELD: railroad transport.SUBSTANCE: group of inventions relates to the field of railway transport. A lot of images (BIGB) of a hazardous area (GB) partly located along a rail section (BST) of a rail network (SNE) are recorded. In each of the images (BIGB) of the danger area (GB), an area (BIB) of the image is marked, showing a separate area (TBGB) of the graphically depicted danger area (GB), which is regarded as particularly critical. For the marked area (BIB), by comparison of samples, it is checked whether people and/or moving objects are in the critical separate area (TBGB). The hazard recognition device (GSEV) comprises an image recording device (BAZG) and a computing/analyzing device (BAWE) that is connected and operatively connected to an image recording device (BAZG) and an image storage device (BSPE). The railway vehicle contains a device (GSEV) for detecting dangerous situations.EFFECT: ability to recognize dangerous situations by interactive image analysis in combination with known metadata about dangerous areas.26 cl, 3 dwg

Description

The invention relates to a method for recognizing dangerous situations in railway traffic, in particular in rail traffic, according to the restrictive part of claim 1 of the claims, a device for recognizing dangerous situations in railway traffic, in particular in rail traffic, in accordance with the restrictive part of claim 11 of the claims and railway a vehicle for recognizing dangerous situations in railway traffic, in particular a rail vehicle for recognizing dangerous situations in rail traffic, in accordance with the limiting part of claim 26 of the claims.

Railway vehicles, as an integral part of modern transport infrastructure, are tracked means of communication and transport that move, for example, rolling on or under one or two guide rails (rail tracks), hovering above or under a magnetic field, or hanging on steel cables. Of the aforementioned track means of communication and transport, the most widespread are rail vehicles, which are based on a wheel-rail system, which either (have) their own chassis drive (motor car), or are pulled or moved by a locomotive, and which mainly have steel wheels with a crest bandage, are guided along two steel rails or, respectively, rail tracks.

The object underlying the invention is to provide a method, apparatus and a railway vehicle, in particular a rail vehicle, for the automatic recognition of hazardous situations in railway traffic, in particular in rail traffic, with the help of which hazardous situations in railway traffic are automatically recognized when rail vehicles are en route on railway tracks in the railway network, or, accordingly, dangerous situations in rail traffic, when rail vehicles are en route on rail tracks in the rail network.

Automatic recognition of dangerous situations in railway traffic, in particular in rail traffic, which is the subject of this international patent application (application No. PCT / ...; publication No. WO ...) and the DE patent application justifying its priority (application No. 102016224358.6), taking into account future automated (autonomous) or with the participation of the driver of railway vehicles in railway traffic or, respectively, rail vehicles in rail traffic is an absolute NECESSITY.

So, for the automated or with the participation of the driver of rail vehicles, it is necessary to recognize dangerous situations on aprons, or in the area of railway crossings or in similar areas (hereinafter “dangerous situations on aprons, etc.) and in such a dangerous situation, act in accordance with the operating rules e.g. by emitting a warning sound, by emitting an acoustic or visual warning sign.

But not only the aspect of automatic recognition of dangerous situations is important for the future automated (autonomous) or with the participation of a driver, but also the subsequent technical aspects, all of which are more or less in the technical context with this patent application and are therefore given, and in therefore, their content should be taken into account and, if necessary. even to be included in it.

These are the following aspects:

1) Automated signal recognition in railway / rail traffic in accordance with the international patent application (application No. PCT / EP2016 / 057804; publication No. WO 2017/174155 A1) and the technical theory disclosed therein.

2) Automatic recognition of tracks / tracks in railway / rail traffic in accordance with the patent application DE (application No. 102016224335.7) and international patent application (application No. PCT / ...; publication No. WO ...) and the technical theory disclosed in each of them ...

3) Automatic recognition of obstacles in rail / rail traffic in accordance with the patent application DE (application No. 102016224344.6) and international patent application (application No. PCT / ...; publication No. WO ...) and disclosed in each of them the technical theory.

4) Alternative positioning in rail traffic when traditional satellite-assisted positioning fails or is insufficient, according to DE patent application (application no. 102016224355.1) and international patent application (application no. PCT / ...; publication no. WO ... ) and the technical theory disclosed in each of them.

5) Performing image analysis on the basis of track / track in rail / rail traffic in accordance with the patent application DE (application No. 102016224331.4) and international patent application (application No. PCT / ...; publication No. WO ...) and disclosed in each of them by technical theory.

The above contextual problem is solved on the basis of a method for recognizing dangerous situations using the features specified in the characterizing part of claim 1 of the claims defined in the limiting part of claim 1 of the claims.

In addition, the above contextual problem is solved based on the device defined in the limiting part of claim 11 for recognizing dangerous situations using the features specified in the characterizing part of claim 11.

Further, the above contextual problem is solved on the basis of a railway vehicle, in particular a rail vehicle, defined in the limiting part of claim 26 of the claims, using the features specified in the characterizing part of claim 26 of the claims.

The idea underlying the invention according to independent claims 1, 11 and 26 of the claims is that on the basis of several images of a certain hazardous area, known with respect to its local coordinates and potential hazardous situations in railway traffic, partially located along the railway of the railway network, in the area of the image marked on each of the images, which shows a certain separate area of the graphically depicted dangerous area, which is regarded as especially critical, by comparing samples it was checked whether there are people and / or moving objects in the critical separate area.

In addition, according to claims 2 and 12 of the claims, it is preferable when

additionally, on the basis of several images representing a critical separate area, the images and images of a separate area are recalculated to the same size, taking into account the corresponding distance to the dangerous area, the activity index is calculated by recognizing the movements of people and / or objects in the dangerous area, and

the calculated activity index is compared with the stored threshold value.

The basic principle of the invention is to recognize hazardous situations in known hazardous areas of railway traffic, for example, on aprons in the area of a railway station, with or without a barrier for railway crossings or the like, by iterative image analysis in combination with known metadata about hazardous areas, such as, for example, aprons, level crossings, etc.

The goal in each case is to make it possible to contribute to fully automated guidance without additional investment in the haul infrastructure.

Automated detection of hazardous situations in hazardous areas of railway traffic, e.g. on aprons in the area of a railway station, with or without a barrier at level crossings or the like, can advantageously be at least partially achieved by the following steps:

1. In the first step, when entering a station area with aprons, or approaching a railway crossing [railway vehicle / rail vehicle, the associated local coordinates are known from the GPS database or positioning data in accordance with the DE patent application (application No. 102016224355.1) and international patent application (application No. PCT / ...; publication No. WO ...), which are in accordance with the disclosed technical theory in each of them] using at least one device for recording images / for collecting images (for example ., one or more devices, such as video cameras, laser sensors, thermal cameras for taking images, radar, other devices for collecting images, etc.) from a railway vehicle, for example, from the perspective of a motor car driver, is recorded or, accordingly, filmed lots of images.

Repeated exercise is relevant primarily for redundancy purposes.

a. But in one of the modifications or improvements, additions of the invention, images from several devices for recording images or, respectively, devices for collecting images of the same type (for example, two video cameras) can also be used for mutual validation and synthesis of results.

b. In another modification or improvement, addition of the invention, images from several image recording devices or, accordingly, different types of image collection devices (e.g., video camera and thermal camera for capturing images) can also be used for mutual validation and synthesis of results.

2. In the second step, on each image, a certain area of the image is marked, which shows a particularly critical (highly critical) area (for example, in the case of an apron, the area between the apron edge and the safety strip bounded by the white line, approximately 2 m from the apron edge). area.

Option 1 : These areas are known from earlier initialization trips, for each of which (highly critical) especially critical areas of hazardous areas were marked for each position of the rail vehicle / rail vehicle in the station area (if the image is taken twice from the same the same place at the entrance to the station area, which has an apron, then the critical area remains always the same). In this regard, we refer to the automatic recognition of signals in railway / rail traffic in accordance with the international patent application (application No. PCT / EP2016 / 057804; publication No. WO 2017/174155 A1) and the technical theory disclosed therein, where they act in a comparable manner in relation to signal recognition.

Option 2 . The track / track track is recognized first. Based on the track / rail track, the apron edge is recognized as the edge of the danger area, as well as the distance from the vehicle to the apron or, respectively, the danger area, and finally a (highly critical) especially critical area in relation to the apron edge or, respectively, the edge of the danger area. area. In this regard, we refer to the performance of the image analysis based on the track / track in the railway / rail traffic in accordance with the patent application DE (application No. 102016224331.4) and the international patent application (application No. PCT / ...; publication No. WO ...) and disclosed in each of them by technical theory.

3. In the third step, on the basis of the obtained images of the highly critical area, it is checked whether there are preferably people and / or moving objects in it. It does this by comparing samples (pattern matching).

If there are people and / or moving objects in a highly critical area, an acoustic signal should be given.

Case 1 : Positive matching is applied, i.e. people and / or moving objects are recognized.

Case 2 : Negative matching is applied, i.e. temporary changes in the structure of the hazardous area are detected, then, for example, interruption of a regular apron pattern (eg stone tiles, white line) is checked.

4. In the fourth step, several images are taken at short intervals in addition to a (highly critical) especially critical individual area of the hazardous area.

After that, these images are recalculated to the same size, taking into account the corresponding distance to the apron or, respectively, to the edge of the dangerous area. The activity index is then calculated by recognizing the movements of people and / or moving objects on the apron (eg playing or mischievous children). If this activity index exceeds a certain threshold value, then it is necessary to act in accordance with the operating rules, for example, by issuing / giving off a warning sound (eg whistle), an acoustic or visual warning sign.

By using the iterative analysis of the images of hazardous areas outlined above in railway / rail traffic, e.g. on aprons in the area of a station, with or without a barrier at level crossings or the like, in combination with metadata about these hazardous areas, it can be achieved that:

- people and / or moving objects in a (highly critical) particularly critical separate area of the hazardous area are recognized and reactions can be taken in accordance with the operating rules, e.g. by emitting / sounding a warning sound (e.g. whistle), acoustic or visual warning sign;

- people and / or moving objects with too high a speed of movement (e.g. mischievous children) in a (highly critical) particularly critical separate area of the danger area are recognized and reactions can be taken in accordance with the operating rules, e.g. blowing a warning whistle, warning signal, etc. .;

- under unfavorable visibility conditions, people can be recognized more reliably than by motor car drivers;

- the drivers of the motor car are no longer needed to recognize dangerous situations or the like, so that driving is possible regardless of their presence.

In the course of one of the preferred improvements of the invention in relation to the device for recognizing hazardous situations according to claim 11 of the claims, the following additional components a) -c) for an image recording device (e.g. an image collecting device) can also be applied:

a. The corrective component according to claim 21 of the claims, which adds weather and illumination data for analytical evaluation of graphic material. In this case, for example, in heavy fog, the analytical assessment of video images can be limited to the first 50 meters in front of a railway vehicle or, respectively, a rail vehicle, and the vehicle speed can be throttled accordingly.

b. The component for changing the focal length according to claim 22 of the claims, which, depending on the environment (eg, train station, urban area, countryside, etc.), selects the correct shooting angle in order to optimally support the analytical evaluation of the image. For example, both free-lane shooting situations (requiring images from a great distance so that speed based responses can be responded to in a timely manner) and train station area shooting situations (requiring images having a wider width) can then be properly handled. In addition, the correct shooting angle can be selected with the help of the component for changing the focal length depending on the distance to the hazardous area, so as to optimally support the multiple analytical assessment of the hazardous area.

c. An illumination component according to claim 23, for example, a searchlight that operates within or outside the area visible to a person, with the help of which the quality of graphic material taken by an image recording device or, respectively, an image collection device at night or in bad weather conditions is improved ...

In addition, it is possible for the GSVE device for hazard recognition to be implemented and operate as a virtual machine as "Software Defined Signal Recognition of Rail Traffic Systems".

Other advantages of the invention result from the following description of one embodiment of the invention using FIGS. 1-3. They show:

Fig. 1: recognition on the basis of a railway vehicle of a dangerous situation when a railway vehicle approaches an apron as a critical zone with respect to possible hazards;

Fig. 2: in accordance with the scenario shown in Fig. 1, recognition on the basis of a rail vehicle of a hazardous situation when a rail vehicle approaches a barrier-type level crossing as a hazard-critical zone;

FIG. 3 shows a basic construction of a hazard recognition device for hazard detection based on a railway vehicle in accordance with FIGS. 1 and 2 at the platform and at the level crossing.

1 shows the recognition on the basis of a rail vehicle of a hazardous situation in the BVK rail link when, on a BST rail section of the BNE rail network, for example, in the vicinity of a train station, a BFZ rail vehicle approaches the apron along the FS track of the BST rail section. BSG as a critical area in relation to possible hazards.

In the present exemplary embodiment, the tracked track BST of the BNE rail network is an SST track of the SNE rail network, on which, in the SVK rail system, for hazard recognition, the SFZ rail vehicle is en route on the GL track and is approaching the BSG apron. Instead of the depicted rail system SVK with the rail vehicle SFZ traveling on the SST track of the SNE rail network, as already discussed, as another embodiment of the invention, any other rail system based on short-distance or long-distance traffic is possible and conceivable. So, one could also talk, for example, about a communication system of a magnetic suspension road (keyword: Transrapid, Maglev, etc.), which has a correspondingly comparable infrastructure, consisting of a railway network, a railway track and a railway vehicle.

In the rail system shown in FIG. 1, in the TRW motor car of the SFZ rail vehicle, which has the TFS control panel of the motor car driver and the integrated AZE display device, in which the operator's workplace FZF of the vehicle is located, a device is placed on the basis of the rail vehicle to recognize a possible hazardous situation GSEV for detecting dangerous situations. To this end, the GSEV for the detection of dangerous situations includes a BAZG image recording device, which is designed, for example, in the form of a conventional video camera, a laser sensor, a thermal imaging camera, a radar device, an infrared camera, etc., and in connection with image collection is also called an image collection device.

With the BAZG device for recording images when an SFZ rail vehicle traveling on the GL track approaches the BSG apron as a critical area with regard to possible hazards from an SFZ rail vehicle, e.g. from the perspective of an FZF motor car driver at the TFS driver's console of a TRW wagon and / or from a stationary, providing visibility of the track position in or on the SFZ vehicle, a plurality of BI _GB images of a certain GB hazardous area, known with respect to its local coordinates and potential hazardous situations in the rail traffic SVK, partially located along the rail the SST haul of the SNE rail network, representing this GB hazardous area. In other words: the BAZG device for recording images receives information as input values (e.g., in the form of metadata) about potential hazardous situations / dangerous places in the rail traffic SVK and the corresponding local coordinates and gives after / due to the corresponding actuation (trigger setting) to these input quantities representing the hazardous area GB of the image BI _GB as output quantities. In the case shown in FIG. 1, the hazardous area GB detected by the BAZG image recorder is part of the BSG apron. It is, of course, also possible for the GB hazardous area to include the entire BSG apron.

In the BI _GB images, the GB hazardous area contains some BIB area of the image showing some separate TB _{GB area of the} graphically depicted GB hazardous area, which is regarded as particularly critical with regard to possible hazards. In the case of a BSG apron, this particularly critical area is preferably the area between the edge of the apron and the safety strip bounded by the white line, which is approx. 2 meters from the edge of the apron. This is the highly critical part of the GB hazardous area. With the BAZG image recorder, in addition, when an SFZ rail vehicle traveling on the GL track approaches the BSG apron as a hazard-critical area, a plurality of BI _TB images are also recorded, representing the critical single TB _{GB area} as highly critical. part of the GB hazardous area.

How hazard recognition is now carried out on the basis of the images BI _{GB of the} hazardous area GB and / or the images BI _{TB of the} (especially) critical individual area TB _GB is now explained in connection with the description of FIG. 3.

However, if, regardless of how the hazardous situation is detected by the GSEV for hazard detection, a hazardous situation on the BSG apron is detected, e.g. (moving) people and / or moving objects in the GB hazardous area, and / or (moving) people and / or moving objects in a particularly critical (highly critical) single area TB _GB hazardous area GB, the GSEV transmits the SSI control signal to the STE control unit in the TRW motor car of the SFZ rail vehicle by the GSEV to detect hazardous situations, after which the TRW motor wagon then issues a WSI warning signal ... This WSI warning signal is, for example, a warning sound (eg a whistle), an acoustic warning sign or a visual warning sign that displays a response according to operating rules in the SVK rail traffic.

Figure 2 shows the recognition on the basis of a rail vehicle of a hazardous situation in the BVK rail link, when a BFZ rail vehicle approaches the BSG apron on the BST rail section of the BNE rail network on the FS track of the BST rail network, as it is critical with respect to possible hazards to the zone.

The track-assigned BST section of the BNE railway network is again the SST section of the SNE rail network, on which the SFZ rail vehicle is en route on the GL track in the SVK rail system to detect hazardous situations and is approaching the BSG apron. Instead of the depicted SVK rail system with the SFZ rail vehicle traveling on the SST track of the SNE rail network, and here again, as already discussed, as another embodiment of the invention, any other rail system based on short-distance or long-distance traffic is possible and conceivable. ... So, one could also talk, for example, about a communication system of a magnetic suspension road (keyword: Transrapid, Maglev, etc.), which has a correspondingly comparable infrastructure, consisting of a railway network, a railway track and a railway vehicle.

In the rail system shown in FIG. 2, and here again in the TRW wagon of the SFZ rail vehicle, which has a TFS control panel for the wagon driver and an integrated AZE display unit, in which the driver's station FZF of the vehicle is located, for recognizing a possible hazardous situation on the basis of the track a GSEV device is placed for detecting dangerous situations. For this, the GSEV for hazard detection again contains the BAZG image recording device, which is designed, for example, as a conventional video camera, laser sensor, thermal image camera, radar device, infrared camera, etc.

With the BAZG image recording device, when an SFZ rail vehicle traveling on a GL track approaches a BÜG railway crossing, as a critical area with regard to possible hazards, from an SFZ rail vehicle, e.g. from the perspective of an FZF motor car driver on the TFS console of the TRW motor car driver and / or from a stationary, providing visibility of the track position in or on the SFZ vehicle, a plurality of BI _GB images of a GB hazardous area, known with respect to its local coordinates and potential hazardous situations in the SVK rail traffic, can be recorded, partially located along the SST track of the SNE rail network, representing this GB hazardous area. In other words: the BAZG device for recording images receives information as input values (e.g., in the form of metadata) about potential hazardous situations / dangerous places in the rail traffic SVK and the corresponding local coordinates and gives after / due to the corresponding actuation (trigger setting) to these input quantities representing the hazardous area GB of the image BI _GB as output quantities. In the case shown in FIG. 2, the danger area GB detected by the image recording device BAZG includes the entire railway crossing BÜG equipped with a barrier.

When the GSEV for hazard detection detects a dangerous situation at a railway crossing BÜG equipped with a barrier, e.g. (moving) people or moving objects in the GB hazardous area, the GSEV again transmits the SSI control signal to the STE control unit in the TRW motor car for hazard detection. rail vehicle SFZ, then a WSI warning signal is issued by the TRW motor wagon. This WSI warning signal can, for example, again be a warning sound (eg a whistle), an acoustic warning sign, or a visual warning sign that displays a response according to operational rules in the SVK rail traffic.

Fig. 3 shows the basic construction of a GSEV device for recognizing hazardous situations for the recognition according to Figs. 1 and 2 on the basis of a railway vehicle of hazardous situations at the BSG apron and at the BÜG level crossing.

In this case, the starting point for recognizing dangerous situations, in accordance with the reasoning for Figs. 1 and 2, is the BAZG device for recording images, which, with a corresponding impulse or, respectively, a trigger (compare the reasoning in the description of Fig. 1) records images BI _GB hazardous area GB and / or images BI _TB separate area TB _GB for hazard detection. How this pulse or, accordingly, the trigger is created and applied to the BAZG device for recording images is not the subject of this application.

To this end, the BAZG image recording device is preferably rotatable for orientation to the image object.

Furthermore, possibly and under certain circumstances, also for technical reasons related to registration, it is advisable that the GSEV for detecting hazardous situations contains several BAZG devices for recording images of the same design, for example, several video cameras, or devices of different design, for example, several video cameras, laser sensors, radar-based sensors based on wireless location and distance measurement, infrared cameras and / or thermal cameras for capturing images that capture images BI _GB , BI _TG . Such a repeated implementation of the recording of images or, respectively, of the collection of images is relevant, in particular, for purposes of redundancy.

To further enhance the quality of images captured or collected with the BAZG Image Recorder, the BAZG Image Recorder preferably contains the following components:

1. Corrective component KOK, with the help of which weather and illumination data are added for analytical evaluation of graphic material. With this component, it is possible, for example, in heavy fog, to limit the analytical evaluation of the video images to the first 50 meters in front of the rail vehicle and accordingly throttle the speed of the rail vehicle.

2. Component BVK focal length change, which, depending on the environment (eg, train station, urban area, countryside, etc.), selects the correct shooting angle in order to optimally support the analytical assessment of the image. This can then be properly handled for both free-lane shooting situations (requiring images from a great distance so that a speed-based response can be made in a timely manner) and train station area shooting situations (requiring images that are wider). In addition, the correct shooting angle can be selected with the help of the component for changing the focal length depending on the distance to the hazardous area, so as to optimally support the multiple analytical assessment of the hazardous area.

3. Component BLK illumination, made, for example, in the form of a searchlight, which operates within or outside the area visible to a person, and with the help of which the quality of graphic material taken by an image recorder or, respectively, a BAZG device for collecting images at bad weather conditions.

The images captured in this way are stored by the BAZG for image recording in the BSPE for image storage. This BSPE image storage device is either, in accordance with option "A", as a component of the GSEV for hazard detection, respectively connected to the BAZG device for image recording, or, according to option "B", outside the GSEV for hazard detection situations, for example, in the form of a data memory bank, in a motor car or in a data cloud is intended for the BAZG device for recording images or, accordingly, can be connected to it.

For the analytical evaluation of recorded or collected images for hazard detection in GB hazardous areas along a track, e.g. on a BSG apron in accordance with FIG. 1 or a BÜG barrier-type railway crossing in accordance with FIG. 2, a BAZG recording device image is connected to the BAWE computing / analyzing device, which is also one of the components of the GSEV for detecting hazardous situations. For this purpose, the BAWE computing / analyzing device, like the BAZG device for recording images, is either, in accordance with option "A", connected to a BSPE device for storing images, or, in accordance with option "B", intended for a BSPE device for memorizing images or, accordingly, can connect with it. Thus, a functional block emerges from the BAWE computing / analyzing device, the BAZG image recording device and the BSPE image storage device, in which the named components of the GSEV hazard detection device functionally interact for computationally / analytical evaluation-supported hazard recognition.

For this, the BAWE computing / analyzing device has preferably a non-volatile readable memory SP, in which the processor-readable PGM control program commands are stored, and the PZ processor, which executes the PGM control program commands for computational / analytical evaluation support. dangerous situations. For this, the PZ processor has access to the BAZG device for recording images and the BSPE device for storing images for control purposes and for reading data.

The BAWE computing / analyzing device or, respectively, the PGM software module, which has a PZ processor that executes the commands of the control program of the PGM software module for the recognition of hazardous situations supported by computations / analytical evaluation, are now designed in such a way that, in relation to hazard recognition, on each of the images BI _GB hazardous area GB is marked with the BIB area of the image, in which some separate TB area is shown _{GB of the} graphically depicted GB hazardous area, which is regarded as particularly critical (highly critical).

This marking can now be carried out, for example, in such a way that the image area BIB of the critical separate area TB _{GB of the} registered danger area GB on the basis of the previous trips of the SFZ rail vehicle shown in each of Figs. track GL of the track SST of the rail network SNE, or on the basis of the trip of the rail vehicle shown in each of FIGS. 1 and 2, the SFZ is subjected to image analysis based on the track or rails.

In the first named case (option 1), such hazardous areas are known from earlier trips for the purpose of initialization, at each of which, for each position of the rail vehicle in the station area, the hazardous area as such and the highly critical part of the hazardous area (especially the critical separate area) were marked ... So, for example, the image is taken twice, and moreover from the same place, for example, at the entrance to the station area, which has an apron. Thus, both the dangerous area and especially the critical individual area remain always the same. In this regard, we refer to the automatic recognition of signals in the railway / rail traffic in accordance with the international patent application (application No. PCT / EP2016 / 057804; publication No. WO 2017/174155 A1) and the technical theory disclosed therein, where in a comparable way regarding signal recognition.

In the alternative case (variant 2), the track is first recognized. Based on the track, the apron edge is recognized as the edge of the danger area, as well as the distance from the rail vehicle to the apron or, respectively, the danger area, and finally a (highly critical) especially critical area in relation to the apron edge or, respectively, the edge of the danger area. on the one hand, and the dangerous area as such, respectively. In this regard, we refer to the performance of the image analysis based on the track / track in the railway / rail traffic in accordance with the patent application DE (application No. 102016224331.4) and the international patent application (application No. PCT / ...; publication No. WO ...) and disclosed in each of them by technical theory.

When marking, for example, according to one of the options outlined above, is carried out using the BAWE computing / analyzing device, the BAWE computing / analyzing device or, respectively, the PGM software module together with the program module PGM executing commands of the control program for the supported computation / analytical evaluation In relation to the computationally supported / analytical evaluation, hazard recognition is also performed in such a way that for the marked BIB area of the image, by comparing samples, it is checked whether there are people and / or moving objects _{in the critical separate area TB GB.}

In this case, the comparison of samples is a matching of patterns, in which either by means of a positive comparison, preferably people and / or moving objects, or by means of a negative comparison, preferably temporary changes in the structure of the dangerous area GB are recognized, and in the latter, for example, the interruption of a regular pattern is checked. platform (eg stone tiles, white line).

For this check, whether there are _{people and / or moving objects in the critical segregated area TB GB,} several images are taken at short intervals for the (highly critical) particularly critical segregated area, already mentioned in connection with the description of FIG. 1 of the BI _TB images.

After image BI _TB of hazardous area GB is already recorded BAZG device for recording images, the computing / analyzing apparatus BAWE and BAZG device for recording BI _TB images for registration BI _TB images on separate area T _GB are also formed and functionally interact in such a way what

1) a plurality of BI _GB images of the critical segregated area T _GB are recorded, representing this critical segregated area;

2) recalculation is carried out for the same size of all images BI _GB , BI _TB , taking into account the corresponding distance to the dangerous area GB;

3) the activity index is calculated by recognizing the movements of people and / or objects in the GB hazardous area (e.g. playing or mischievous children) and

4) the calculated activity index is compared with the stored threshold value.

A comparison of the threshold value is performed Computing / analysis apparatus BAWE or, respectively, processor PZ, which executes instructions of software PGM module control program to support computing / analytical assessment of recognition of dangerous situations, while, if the critical specific area TB _GB are the people and / or moving objects, and the comparison shows that the calculated activity index meets or exceeds the threshold value, the BAWE computing / analyzing device or, respectively, the PZ processor generates an SSI control signal, which indicates a dangerous situation in the GB hazardous area according to the operating rules in rail service SVK. This is preferably done by giving a WSI warning signal by the SFZ rail vehicle. At this point, it should be pointed out again that the warning signal can be performed both in the form of an acoustic signal and in the form of a visual signal.

To enable a WSI warning signal, the calculating / analyzing device BAWE of the GSVE device for detecting hazardous situations is connected to the control device STE in the motor car TRW of the rail vehicle SFZ (cf. FIG. 1).

With the help of the GSVE device described above for recognizing dangerous situations, it is possible to assist or, accordingly, even implement an automated (autonomous) or with the participation of an operator in guiding a railway vehicle BFZ or, respectively, a rail vehicle SFZ without additional infrastructure for some haul. This is particularly the case when the GSVE hazard detection device is implemented as a virtual machine, which is designed and operates as "Software Defined Signal Recognition of Rail Traffic Systems".

Claims (48)

1. A method for recognizing dangerous situations in railway traffic (BVK), in particular in rail traffic (SVK), characterized in that a) from a railway vehicle (BFZ), in particular a rail vehicle (SFZ), in particular from the driver's perspective (FUF, TFS, TRW) of a motor car and / or from a stationary, visible track position in or on a vehicle (BFZ, SFZ), register multiple images (BI _GB ) of a hazardous area (GB), known in relation to its local coordinates and potential hazardous situations in rail traffic (BVK, SVK), partly located along the railway section (BST) of the rail network (SNE), representing this hazardous area (GB); b) on each of the images (BI _GB ), a dangerous area (GB) is marked with an area (BIB) of the image showing a separate area (TB _GB ) of the graphically depicted danger area (GB), which is regarded as particularly critical; c) For the marked area (BIB), by comparison of samples, it is checked whether people and / or moving objects _{are in the critical separate area (TB GB).} 2. The method according to claim 1, characterized in that a) record multiple images (BI_GB) critical separate region (T_GB) representing this critical discrete area; b) recalculate to the same size all images (BI _GB , BI _TB ) taking into account the corresponding distance to the hazardous area (GB); c) calculate the activity index by recognizing the movements of people and / or objects in the hazardous area (GB), and d) The calculated activity index is compared with the stored threshold value. 3. A method according to claim 1 or 2, characterized in that A hazardous situation in a hazardous area (GB) according to the operating regulations in railway traffic (BVK, SVK) is indicated by the fact that an acoustic warning signal (WSI) is preferably given when a) there are people and / or moving objects in a critical segregated area (TB _GB); b) Comparison shows that the calculated activity index meets or exceeds the threshold. 4. A method according to claim 3, characterized in that the warning signal (WSI) is supplied by a railway vehicle (BFZ, SFZ). 5. The method according to one of claims 1-4, characterized in that the images (BI _GB , BI _TG ) are taken by several devices (BAZG) for recording images of the same design, for example, video cameras, or devices of different designs, for example, video cameras, laser sensors, radar-based sensors based on wireless location and distance measurement, infrared cameras and / or thermal cameras for capturing images. 6. Method according to one of claims 1 to 5, characterized in that the area (BIB) of the image of the critical separate area (TB _GB ) of the registered hazardous area (GB) is marked on the basis of previous trips for the purpose of initialization on railway tracks (BST, SST ) railway network (BNE, SNE) or based on image analysis based on gauge, in particular on the basis of track or rails. 7. The method according to claim 6, characterized in that, when analyzing the images on the basis of the track, the track (FS) of the track is first recognized, in particular the track (GL) of the track, the railway line (BST, SST), based on the track (FS, GL ) following, the edge (R _GB ) of the hazardous area (GB), as well as the distance from the rail vehicle to the hazardous area (GB) and, ultimately, the critical separate area (TB _GB ) relative to the edge (R _GB ) of the hazardous area (GB ). 8. A method according to one of claims 1-7, characterized in that the comparison of samples is performed as a positive comparison, in which people and / or moving objects are preferably recognized, or as a negative comparison, in which temporary changes in the structure of the dangerous area ( GB). 9. A method according to one of claims 1-8, characterized in that the hazardous area (GB) refers either to the apron (BSG) where people enter the railway vehicle (BFZ, SFZ) and / or exit, or to the one equipped with a barrier or a railway crossing without a barrier (BÜG). 10. A method according to one of claims 1 to 9, characterized in that this method provides assistance to the automated (autonomous) or with the participation of the driver in the guidance of a railway vehicle (BFZ, SFZ) without additional infrastructure for the route. 11. Device (GSEV) for detecting dangerous situations in railway traffic (BVK), in particular in rail traffic (SVK), characterized in that it contains a) at least one device (BAZG) for recording images with which from a railway vehicle (BFZ), in particular a rail vehicle (SFZ), in particular from a driver's perspective (FZF, TFS, TRW) of a motor car and / or from a stationary, visible track position in or on a vehicle (BFZ, SFZ), multiple images (BI _GB ) of a hazardous area (GB), known for its local coordinates and potential hazardous situations in railway traffic (BVK, SVK), partly located along the track (BST) of the rail network (BNE), in the mounted state of the track (SST) of the rail network (SNE), representing this hazardous area (GB), and can be stored in the device (BSPE) for storing images ; b) a computing / analyzing device (BAWE), which, when connected and operatively interacting with an apparatus (BAZG) for recording images and a device (BSPE) for storing images, is thus designed, in particular, has a non-volatile readable memory (SP), in which the program module (PGM) control program commands read by the processor are stored, and the processor (PZ), which executes the program module control program (PGM) commands for the computationally supported / analytical evaluation of hazard recognition, so that on each of the images ( BI _GB ) hazardous area (GB) marked a certain area (BIB) of the image, showing some separate area (TB _GB ) of a graphically depicted hazardous area (GB), which is regarded as particularly critical; moreover c) the computing / analyzing device (BAWE) is designed in such a way that for the marked area (BIB), by comparing samples, it is checked whether there are people and / or moving objects _{in the critical separate area (TB GB).} 12. Device (GSEV) according to claim 11, characterized in that a) Computing / Analyzing Device (BAWE) and Image Recorder (BAZG) (BI _TB ), which are configured and functionally interact such that multiple images (BI _GB ) of a Critical Separate Region (T _GB ) are recorded representing this Critical Separate region; b) a computing / analyzing device (BAWE), a device (BAZG) for recording images and a device (BSPE) for storing images, which are designed and functionally interact in such a way that all images are recalculated to the same size (BI _GB , BI _TB ) with taking into account the appropriate distance to the hazardous area (GB); c) computing / analyzing device (BAWE), which is designed in such a way that c1) the activity index is calculated by recognizing the movements of people and / or objects in the hazardous area (GB), and c2) The calculated activity index is compared with the stored threshold value. 13. Device (GSEV) according to claim 11 or 12, characterized in that a computing / evaluating device (BAWE) can be connected to a control device (STE) in a railway vehicle (BFZ, SFZ) and thus activates a control device (STE) in such a way that a hazardous situation in a hazardous area (GB) is railway traffic (BVK, SVK) is indicated by preferably an acoustic warning signal (WSI) when a) there are people and / or moving objects in a critical segregated area (TB _GB); b) Comparison shows that the calculated activity index meets or exceeds the threshold. 14. Apparatus (GSEV) according to claim 13, characterized in that the warning signal (WSI) can be supplied by a railway vehicle (BFZ, SFZ). 15. Device (GSEV) according to one of claims 11-14, characterized in that it contains several devices (BAZG) for recording images of the same design, for example, several video cameras, or devices of different design, for example, several video cameras, laser sensors, sensors based on radar, based on wireless location and distance measurement, infrared cameras and / or thermal imaging cameras that capture images (BI _GB , BI _TG ). 16. Device (GSEV) according to one of claims 11-15, characterized in that the computing / analyzing device (BAWE) is designed in such a way that the marking of the area (BIB) of the image of the critical separate area (TB _GB ) of the registered hazardous area (GB) is performed on the basis of previous trips for the purpose of initialization on the tracks (BST, SST) of the railway network (BNE, SNE) or on the basis of image analysis based on gauge, in particular on the basis of track or rails. 17. Device (GSEV) according to claim 16, characterized in that by the analysis of the track images carried out on the calculating / analyzing device (BAWE), the track (FS) of the track, in particular the track (GL) of the track, of the railway haul (BST, SST), based on the track (FS, GL) of the following, edge ( _GB ) of the hazardous area (GB), as well as the distance from the rail vehicle to the hazardous area (GB) and, ultimately, the critical separate area (TB _GB ) relative to the edge (R _GB ) of the hazardous area (GB). 18. Device (GSEV) according to one of claims 11-17, characterized in that the computing / analyzing device (BAWE) is designed in such a way that the comparison of the samples is performed as a positive comparison, in which people and / or moving objects are preferably recognized, or as a negative comparison, in which temporary changes in the structure of the hazardous area (GB) are preferably recognized. 19. Device (GSEV) according to one of claims 11-18, characterized in that the hazardous area (GB) refers either to the apron (BSG) where people enter and / or exit a railway vehicle (BFZ, SFZ), or to a barrier-free or non-barrier railway crossing (BÜG). 20. Device (GSEV) according to one of claims 11-19, characterized in that the device (BAZG) for recording images is rotatable. 21. A device (GSEV) according to one of claims 11-20, characterized in that it has a correcting component (KOK) for recording images, which adds weather and illumination data for analytical evaluation of graphic material. 22. Device (GSEV) according to one of claims 11-21, characterized in that the device (BAZG) for recording images has a component (BVK) for changing the focal length, which, depending on the environment, for example, a train station, urban area, rural terrain, etc., selects the correct shooting angle in order to optimally support the analytical evaluation of the image (BI _GB , BI _TB ), and / or, depending on the distance to the danger area (GB), selects the correct shooting angle in order to optimally maintain the multiple an analytical assessment of the hazardous area (GB). 23. Device (GSEV) according to one of claims 11 to 22, characterized in that the device (BAZG) for recording images has a component (BLK) of illumination, in particular a spotlight, which operates within or outside the area visible to a person. 24. Device (GSEV) according to one of claims 11-23, characterized by a virtual machine, which is designed and functions as "Software Defined Signal Recognition of Rail Traffic Systems" (software-defined recognition of signals from rail transport systems). 25. Device (GSEV) according to one of clauses 11-24, characterized in that with the help of the device (GSEV) it is possible to assist the automated (autonomous) or with the participation of the driver of the railway vehicle (BFZ, SFZ) without additional infrastructure for the haul ... 26. Railway vehicle for detecting hazardous situations in rail traffic (BVK), in particular a rail vehicle (SFZ) for detecting hazardous situations in rail traffic (SVK), characterized in that the device (GSEV) for detecting hazardous situations in one of pp. 11-25 is integrated into a railway vehicle (BFZ, SFZ).

Images