Title of Invention: Railway train equipment for the detection of objects and their subsequent classification Technical Field

[0001] The technical solution concerns the railway train equipment for the detection of objects and their subsequent classification.

Background Art

[0002] Similarly to the automotive industry, the railway industry is also beginning to develop systems that should gradually make it possible to fully replace human work. This trend in the railway world is mainly aimed at replacing the sensory, decision making and execution skills of the engine driver. The full replacement of these capa bilities corresponds to GoA4 (Grade of Automation). Fully automated GoA4 subways have been running around the world for many years, but projects equivalent to GoA2 are only now getting off the ground on conventional rail. This means that the system can start and stop the train automatically, but the engine driver has to be present in the cabin at all times to supervise the train. Compared to the closed environment of the subway, the open environment of the conventional railway is much more demanding in terms of perception and the number of possibilities of interaction with the surrounding environment.

[0003] The whole system for unmanned train operation has to be a very complex so phisticated system of cooperating subsystems. These subsystems include, for example, the Automatic Train Operation (ATO) system, known in the Czech Republic under the abbreviation AVV (Automatic Train Control), as well as an expert train decision making system replacing the engine driver's decision-making skills and, last but not least, a number of detectors replacing the engine driver's sensory perception. These detectors include the object detector, which is intended to replace the eyes or vision of the engine driver when monitoring the area in front of and around the railway vehicle. Summary of Invention

[0004] The subject of the presented technical solution is the design and technical solution of the equipment for the detection of objects and their subsequent classification which is railway train equipment for the detection of objects.

[0005] The essence of the technical solution is that detection sensors (a group of lidars, a stereo camera, a thermal camera and a high-resolution camera) placed in an adaptive bracket on the front of the railway vehicle continuously monitor what is happening in the area in front of the train and in close proximity to the train. Thanks to the use of different types of sensors, a given scene can be captured in multiple parts of the elec- tromagnetic spectrum both visible and invisible to the human eye. All raw sensor data is analyzed and stored in the computing unit of the object detector. All data processing and calculations for object detection take place in this unit in real time and inde pendently of the speed of the moving vehicle. The data is processed using analytical al gorithms and also with the help of artificial intelligence, which is able to classify not only common objects (human, animal, vehicles) but also special railway objects (signals, their signaling signs, etc.). Two approaches are used to determine the clearance profile and define the safe zone. The first is to use a digital map created by scanning the track, and the second approach is to detect the track (or. rails) to refine the entire alignment. The output of the computing unit of the object detector is then mainly position and character information (e.g. the position of the detected object in relation to the train head or the type and properties of this object). This information is ready to be distributed to downstream train subsystems (e.g. train expert decision making system, automatic unmanned train control system or unmanned train traffic control monitoring terminal).

Brief Description of Drawings Fig·!

[0006] [Fig.l] represents the embodimen of the device according to this technical solution.

Description of Embodiments

[0007] Embodiments of the invention are described in detail in the following example.

Examples

[0008] The subject of the technical solution is a railway device 10 for the detection of objects and their subsequent classification, comprising detection sensors connected to a computing unit 8 with a module 7 of the Global Positioning System Global Positioning System (hereinafter also GNSS).

[0009] The essence of the technical solution lies in the fact that in the bracket 6 located on the front of the rail vehicle, there are sensors comprising a group of lidars 1, a stereo camera 2, a thermal camera 3 and a high resolution camera 4, together powered by a power supply and control module 5, which are connected to a switchboard 9 inside the rail vehicle with a computing unit 8 and a module 7 of the global navigation satellite system GNSS. The computing unit 8 for detection and classification of objects is con nectable to the expert train system 11 for making decisions, to the system 12 for automatic control of the unmanned train and to the traffic controller's monitoring terminal 13 for unmanned trains. The computing unit 8 is adapted to provide positional and character information, including the distance of the detected object from the front of the train and the type of detected object.

[0010] The device 10 consists of the following parts: • detection sensors in a defined configuration, which is a group of lidars 1, a stereo camera 2, a thermal camera 3 and a high resolution camera 4;

• protective and supporting bracket 6 with adaptable attachment to the front of the rail vehicle,

• power and control module 5,

• GNSS module 7 and communication module,

• computing unit 8 of the object detector,

• switchboard 9 inside the rail vehicle.

[0011] Each sensor, by its technological nature, generally perceives the environment at different distances, at different angles of view and in different parts of the electro magnetic spectrum. The above-mentioned sensor configuration can also capture some information beyond the current vision of the human eye or the engine driver's eye. [0012] The individual sensing principles are as follows:

[0013] For lidar 1, this involves accurately measuring the distance of objects and creating a 3D scene using the reflection of laser beams. For stereo camera 2, it is about cal culating the disparity map and illustrating the 3D scene. In the case of thermal camera 3, it is the imaging of emitted infrared radiation, and in the case of high-resolution camera 4, it is an image in the visible spectrum of electromagnetic radiation. All raw data from sensors i.e. lidars 1, stereo cameras 2, thermal cameras 3 and camera 4, are analyzed and stored in the computing unit 8 of the object detector. The power supply of the individual sensors is provided by the power supply and control module 5.

[0014] The sensors i.e. lidars 1, stereo cameras 2, thermal cameras 3 and camera 4, including the power supply and control module 5 are placed in a special bracket 6, which is located on the front of the rail vehicle. This bracket 6 has not only a load-bearing function, but also a protective function. One of the key features of this bracket 6 is that it can be installed on any standard rail vehicle thanks to its adaptable mounting. It consists of two parts: a universal fixed support and protection box for lidars 1, stereo cameras 2, thermal cameras 3 and camera 4, and a power supply module 5 and an adapter (vehicle mounted structure) corresponding to the design of the type of railway vehicle.

[0015] Directly in the train there is a railway switchboard 9 with a computing unit 8 of the object detector and a GNSS module 7 (and a communication module). The computing unit 8 of the object detector performs all the computing operations necessary for object detection and classification using artificial intelligence. In addition to standard objects (human, animal, vehicles), it is also able to classify special railway objects (signals, their signs, etc.). In addition, the track (or rail) itself is also detected so that it can be determined whether or not the detected object is located in the line clearance profile. The output of the computing unit 8 of the object detector is then mainly position and character information (e.g. the distance of the detected object from the front of the train or the type of detected object). All operations take place in real time regardless of the speed of the moving vehicle.

[0016] The computing unit 8 of the object detector interfaces not only with its own subsystems and modules i.e. lidars 1, stereo cameras 2, thermal cameras 3 and camera 4, power supply module 5 and modul 7, but also with related surrounding railway subsystems.

[0017] These subsystems include in particular the expert train decision-making system 11 (and hence the downstream automatic train control system 12). The computing unit 8 sends status information and information about the detected objects to the expert decision-making system 11, so that it can decide to take the appropriate action. Fur thermore, it is possible for the object detection device 10 to send visual information to downstream systems outside the train, namely with remote management and control of the train (traffic controller monitoring terminal 13 of unmanned trains).

Industrial Applicability

[0018] In addition to the primary use of this device in an unmanned train (GoA4), where the engine driver is not present on board, the device can also be used when the train is operated in lower levels of automation or in degraded states. In these cases, it will serve as an assistance system for the engine driver or other authorized persons present on the train, or for authorized persons outside the train. .

Reference Signs List

[0019] 1 - Lidars group

2 - Stereo camera

3 - Thermal camera

4 - High resolution camera

5 - Power supply and control module

6 - Bracket

7 - GNSS module

8 - Computing unit

9 - Switchboard

10 - Object detector

11 - Expert train system for decision making

12 - System for automatic control of unmanned trains

13 - The traffic control monitoring terminal for unmanned trains