Rail engineering vehicle auxiliary driving method, device and equipment based on signal lamp positioning and storage medium

Abstract

The invention discloses a rail engineering vehicle auxiliary driving method, device and equipment based on signal lamp positioning and a storage medium, and the method comprises the steps: obtaining image data in front of a target engineering vehicle, and calculating a reference signal lamp through positioning data; performing coordinate transformation on the reference signal lamp to obtain a pixel coordinate of the reference signal lamp; processing the image data to obtain first position coordinate data of all signal lamps; screening the first position coordinate data to obtain a signal lamp coordinate set corresponding to the current track line; respectively calculating the Euclidean distance between the pixel coordinate of the reference signal lamp and the coordinate of each signal lamp in the coordinate set, and determining a target signal lamp according to the calculation result; and when the engineering vehicle runs, controlling the engineering vehicle to execute a corresponding driving strategy according to the color information of the target signal lamp. The rail engineering vehicle auxiliary driving system based on signal lamp positioning achieves the effects of filtering false detection and positioning the target signal lamp of the engineering vehicle from a plurality of detected signal lamps.

Description

Technical Field

[0001] The present invention relates to the technical field of assisted driving, and in particular to a method for assisted driving of a rail engineering vehicle based on signal light positioning. Background Art

[0002] The rail engineering vehicle assisted driving system uses signal lights as positioning references, combined with advanced sensor technology and data processing algorithms, to provide positioning information and driving assistance for rail engineering vehicles. The system can be applied to urban rail transit, railway maintenance, track construction and other fields.

[0003] In the prior art, the engineering vehicle camera collects data about the road conditions ahead, and the data is inferred by the deep detection model to obtain the pixel positions and colors of all signal lights. However, due to the complexity of night driving, there are many reflective parking signs on the track, and there are many street lights and luminous billboards on outdoor roads. These luminous bodies are very similar to the signal lights, which can easily cause false detections. In addition, the vehicle section is a multi-track section, and multiple signal lights will be installed in parallel on different tracks. Therefore, the detection model will infer the pixel positions and colors of multiple signal lights, but only the signal lights on the track where the engineering vehicle is located can guide the engineering vehicle.

[0004] It can be seen that how to filter out false detections and locate the target signal light of the engineering vehicle from multiple detected signal lights has become a technical problem that needs to be urgently solved by those skilled in the art. Summary of the invention

[0005] The present invention provides a method for assisting driving of a rail engineering vehicle based on signal light positioning, so as to solve the technical problems of signal light misdetection and how to locate a target signal light. By screening the first position coordinate data and matching the reference signal light with the signal light coordinate set corresponding to the track line, the effect of filtering out false detections and locating the target signal light of the engineering vehicle from multiple detected signal lights can be achieved.

[0006] In order to solve the above technical problems, an embodiment of the present invention provides a railway engineering vehicle assisted driving method based on signal light positioning, comprising:

[0007] Acquire image data and position data of the target engineering vehicle in real-time operation, and confirm the reference signal light according to the position data;

[0008] Performing coordinate transformation on the reference signal light to obtain pixel coordinates of the reference signal light;

[0009] Processing the image data to obtain first position coordinate data of all signal lights and second position coordinates of the current track line corresponding to the target engineering vehicle;

[0010] Based on the acquired second position coordinate data of the current track line corresponding to the target engineering vehicle, the first position coordinate data is filtered to obtain a signal light coordinate set corresponding to the current track line;

[0011] respectively calculating the Euclidean distance between the pixel coordinates of the reference signal light and the coordinates of each signal light in the coordinate set, and determining the signal light corresponding to the smallest Euclidean distance as the target signal light;

[0012] When the engineering vehicle is running, the engineering vehicle is controlled to execute a corresponding driving strategy according to the color information of the target signal light, wherein the driving strategy at least includes deceleration, acceleration, steering or emergency braking.

[0013] As one of the preferred solutions, the world coordinates of the reference signal light based on the target engineering vehicle are calculated, and the world coordinates are transformed into the pixel coordinates according to the external parameters and internal parameters of the calibrated camera.

[0014] As one of the preferred solutions, track line detection is performed on the image data based on the optimized UFLDT algorithm to obtain second position coordinate data of the current track line;

[0015] Based on the second position coordinate data, the first position coordinate data is filtered to obtain a signal light coordinate set corresponding to the current track line.

[0016] As one of the preferred solutions, the UFLDT algorithm is obtained by optimizing the UFLD algorithm based on Transfomer's self-attention mechanism and adding a channel attention module in the auxiliary segmentation network to optimize the second position coordinate data.

[0017] As one preferred solution, the Euclidean distance between the second position coordinate data and the first position coordinate data of each traffic light is calculated respectively;

[0018] The Euclidean distance is compared with a threshold value, and based on the comparison result, a set of signal light coordinates corresponding to the current track line is obtained.

[0019] As one of the preferred solutions, the Euclidean distance calculation formula is as follows:

[0020]

[0021] Among them, d l is the distance, (x,y) is the pixel coordinate, (x l ,y l ) are the signal light coordinates.

[0022] As one of the preferred solutions, the color information of the target signal light is fed back to the control console for processing, and after manual review, the control curve of the engineering vehicle will be closed at the next signal light;

[0023] If the emergency braking condition is met, the target engineering vehicle is controlled to trigger emergency braking, wherein the emergency braking condition is:

[0024] It is detected that the color of the target signal light is red, the manual review fails, and the target engineering vehicle does not stop at the closed point of the target signal light.

[0025] Another embodiment of the present invention provides a railway engineering vehicle auxiliary driving device based on signal light positioning, comprising:

[0026] An information acquisition module, used to acquire image data and position data of the target engineering vehicle in real-time operation, and confirm the reference signal light according to the position data;

[0027] A coordinate transformation module, used for performing coordinate transformation on the reference signal light to obtain pixel coordinates of the reference signal light;

[0028] An image processing module, used for processing the image data to obtain first position coordinate data of all signal lights and second position coordinate data of a current track line corresponding to the target engineering vehicle;

[0029] A screening module, configured to screen the first position coordinate data based on the acquired second position coordinate data of the current track line corresponding to the target engineering vehicle, to obtain a signal light coordinate set corresponding to the current track line;

[0030] a signal light determination module, configured to respectively calculate the Euclidean distance between the pixel coordinates of the reference signal light and the coordinates of each signal light in the coordinate set, and determine the signal light corresponding to the smallest Euclidean distance as the target signal light;

[0031] The auxiliary driving module controls the engineering vehicle to execute a corresponding driving strategy according to the color information of the target signal light when the engineering vehicle is running, wherein the driving strategy at least includes deceleration, acceleration, steering or emergency braking.

[0032] Another embodiment of the present invention provides a railway engineering vehicle auxiliary driving device based on signal light positioning, comprising:

[0033] A processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the above-mentioned railway engineering vehicle assisted driving method based on signal light positioning when executing the computer program.

[0034] Another embodiment of the present invention provides a computer-readable storage medium, including:

[0035] The computer-readable storage medium stores a computer program, wherein when the device where the computer-readable storage medium is located executes the computer program, the above-mentioned railway engineering vehicle assisted driving method based on signal light positioning is implemented.

[0036] Compared with the prior art, the embodiments of the present invention have at least the following beneficial effects:

[0037] (1) By screening the first position coordinate data, a signal light coordinate set corresponding to the current track line is obtained, and then the pixel coordinates are matched with the coordinates of each signal light in the signal light coordinate set corresponding to the current track line by Euclidean distance to obtain the target signal light, which can filter out false detections and locate the target signal light of the engineering vehicle from multiple detected signal lights; realize the perception, judgment and analysis of the signal light position, as well as the route control of the engineering vehicle, so as to better ensure the driving efficiency of the engineering vehicle, ensure the safety of track equipment, reduce conflicts with other engineering vehicles, and greatly improve driving safety;

[0038] (2) The original UFLD algorithm is optimized by referencing the Transformer attention mechanism and adding a channel attention module to enhance the detection capability of the track where the engineering vehicle is located. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a flow chart of a method for assisting driving of a rail engineering vehicle based on signal light positioning in one embodiment of the present invention;

[0040] Figure 2 is a schematic diagram of calculating the world coordinates of a signal light in one embodiment of the present invention;

[0041] Figure 3 is a schematic diagram of a UFLDT track line detection algorithm in one embodiment of the present invention;

[0042] Figure 4 is a structural diagram of a channel attention module in one embodiment of the present invention;

[0043] Figure 5 It is a structural schematic diagram of a railway engineering vehicle auxiliary driving device based on signal light positioning in one embodiment of the present invention;

[0044] Figure 6 It is a structural block diagram of a railway engineering vehicle auxiliary driving device based on signal light positioning in one embodiment of the present invention;

[0045] Reference numerals:

[0046] Among them, 10, processor; 20, memory; A, computer program; A1, computer program; 11, information acquisition module; 12, coordinate transformation module; 13, image processing module; 14, screening module; 15, traffic light determination module; 16, assisted driving module. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. The purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] In the description of this application, the terms "first", "second", "third", etc. are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second", "third", etc. may explicitly or implicitly include one or more of the feature. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0049] In the description of the present application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be a connection between the two elements. The terms "vertical", "horizontal", "left", "right", "upper", "lower" and similar expressions used herein are only for illustrative purposes, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0050] In the description of this application, it should be noted that, unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as those commonly understood by those skilled in the art. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood by specific circumstances.

[0051] An embodiment of the present invention provides a railway engineering vehicle assisted driving method based on signal light positioning. For details, see Figure 1 , Figure 1 The figure shows a flow chart of a method for assisting driving of a railway engineering vehicle based on signal light positioning in one embodiment of the present invention, which specifically includes steps S1 to S6:

[0052] S1. Obtain image data and position data of the target engineering vehicle in real-time operation, and confirm the reference signal light according to the position data;

[0053] S2, performing coordinate transformation on the reference signal light to obtain pixel coordinates of the reference signal light;

[0054] S3, processing the image data to obtain first position coordinate data of all signal lights and second position coordinates of the current track line corresponding to the target engineering vehicle;

[0055] S4, based on the acquired second position coordinate data of the current track line corresponding to the target engineering vehicle, filtering the first position coordinate data to obtain a signal light coordinate set corresponding to the current track line;

[0056] S5, respectively calculating the Euclidean distance between the pixel coordinates of the reference signal light and the coordinates of each signal light in the coordinate set, and determining the signal light corresponding to the smallest Euclidean distance as the target signal light;

[0057] S6. When the engineering vehicle is running, the engineering vehicle is controlled to execute a corresponding driving strategy according to the color information of the target signal light, wherein the driving strategy at least includes deceleration, acceleration, steering or emergency braking.

[0058] A complete embodiment is provided below for the technical concept of the present invention.

[0059] The technical solution of this embodiment specifically includes the following steps:

[0060] Step 1: Information acquisition. Two cameras are installed on the left and right sides of the front of the engineering vehicle in this embodiment, which are used to obtain the image data of the signal lights on the track in real time, and obtain the position data of the engineering vehicle, the kilometer mark of the signal light in front, etc. in real time through the on-board equipment. Of course, different numbers and different positions of cameras can also be installed according to the actual model of the rail vehicle, which is determined by the actual product model and is not specifically limited in the embodiment of the present invention.

[0061] Step 2: Coordinate transformation. First, calculate the world coordinates of the front signal light based on the engineering vehicle, and then project the world coordinates onto the image to obtain the pixel coordinates of the front signal light according to the external and internal parameters obtained by camera calibration.

[0062] Step 3: Image processing: The image data is processed based on the track line detection algorithm and the signal light detection algorithm to obtain the second position coordinate data of the track line where the target engineering vehicle is located and the first position coordinate data of all signal lights on the image.

[0063] Step 4: Calculate the distance between the second position coordinate data and the first position coordinate data of each traffic light respectively; if the distance is less than a threshold, the traffic light will be used as the traffic light coordinate corresponding to the current track line.

[0064] Step 5: respectively calculating the Euclidean distance between the pixel coordinates and the coordinates of each traffic light in the coordinate set, and determining the traffic light corresponding to the minimum Euclidean distance as the target traffic light based on the argmin function;

[0065] Step 6: When the engineering vehicle is running, the color information of the target traffic light is fed back to the control console for processing. After manual review, the control curve of the engineering vehicle will be closed at the next traffic light; if the emergency braking conditions are met, the target engineering vehicle is controlled to trigger emergency braking, where the emergency braking conditions are: the color of the target traffic light is detected to be red, the manual review is not passed, and the target engineering vehicle does not stop at the closing point of the target traffic light.

[0066] The calculation method of the world coordinates in step 2 is described in detail below.

[0067] See also Figure 2 , Figure 2 The figure shows a schematic diagram of calculating the world coordinates of a signal light in one embodiment of the present invention. Taking a curved track as an example, the engineering vehicle can obtain the kilometer mark of the engineering vehicle, the signal light in front, and the current track radius R in real time through the on-board equipment when traveling. The kilometer mark of the engineering vehicle and the signal light in front is subtracted to obtain the route distance between the two. The track is approximated into an arc, and the center angle B is calculated according to the route distance A and the track radius R, and then the world coordinates of the signal light are calculated in combination with the vertical distance K (empirical value) from the signal light to the center of the track.

[0068] The calculation formula of the center angle B is:

[0069]

[0070] Take the center point of the track where the engineering vehicle is located as the origin and the speed direction as the y-axis direction to establish a coordinate system. The calculation formula for the world coordinates (ΔX, ΔY) of the signal light in the coordinate system is as follows:

[0071] ΔX=(R+K)*cos(B)-R

[0072] ΔY=(R+K)*sin(B)

[0073] If the track is straight, the world coordinates of the signal light are as follows:

[0074] ΔX=K

[0075] ΔY=A

[0076] Assume that the distance from the traffic light to the ground is ΔZ, and the calculation formula from the world coordinate system to the pixel coordinate p(x,y) is:

[0077]

[0078] Where K, R and t represent the intrinsic parameter matrix, rotation matrix and translation vector respectively.

[0079] The track line detection algorithm in step 3 is described in detail below.

[0080] See also Figure 3 , Figure 3 The figure shows a schematic diagram of the UFLDT track line detection algorithm in one embodiment of the present invention. The present invention optimizes the UFLD (track line detection algorithm) by using the self-attention mechanism of the Transformer to obtain the UFLDT track line detection algorithm. The specific steps of the UFLDT algorithm are as follows:

[0081] After the input image passes through the network skeleton, the feature map obtained is three-dimensional, and the Transformer Encoder needs to output a vector sequence, that is, a two-dimensional matrix. Manually divide the feature map of FULDT into N small blocks, and flatten the features of each small block into a vector. The N vectors and position encoding are used as the input of the Transformer Encoder, and the output is the image features of N vectors. The output features and the Object query are used as the input of the Transformer Decoder. The output of the Transformer Decoder is used as the input of the feedforward network, and finally the coordinates of the track line points and their classification probabilities are obtained. Among them, Object query is a learnable embedding, and each Oject query corresponds to the description of a classified object. In UFLD, the anchor is static, but in UFLDT, the Object query can be regarded as a learnable dynamic anchor.

[0082] See also Figure 4 , Figure 4The structure diagram of the channel attention module in one embodiment of the present invention is shown. The auxiliary network used by UFLD segments the track line. In the UFLDT algorithm proposed in the present invention, a channel attention module is added to the auxiliary segmentation network. The channel attention module can assign different weights to each channel and establish the relationship between the channels of the feature map, thereby enhancing the network's ability to judge important feature channels. The input features of the channel attention network are input into a shared multi-layer perceptron (MLP) after passing through the maximum pooling layer and the average pooling layer, and the output of the MLP is summed element by element and sigmoid processed.

[0083] For step 4 above, after detecting the two tracks where the engineering vehicle is located, it is necessary to locate the signal light on the track where the engineering vehicle is located among multiple signal lights. According to the data from the on-board equipment, the position of the signal light on the track can be obtained (on the left or right side of the track). Based on this information, the distance between the signal light and the nearest track line is calculated. If the distance is less than the threshold T r , then the signal light will be used as the positioning result of the track. Of course, the threshold T r The actual value of is determined by factors such as the actual railway track width, which will not be elaborated here.

[0084] Assume R k is the kth detection track line, which is a set of m points, p r (x i ,y i ) is the set R k Let L be the set of detected traffic light center points, p l (x l ,y l ) is the lth point of set L. For a point p in set L l to R k The distance is

[0085]

[0086] Assume the distance threshold from the track line to the signal light is T r , the set of traffic lights that meet the threshold is L T

[0087] L T ={p l}, dr l <T r

[0088] For the above step 5, the set of signal lights that can be located through track line detection is L T , the pixel coordinates obtained by projection of the world coordinates are p(x,y). For point p in the traffic light set l (xl ,y l ) to the coordinate p is:

[0089]

[0090] This is the signal light finally located:

[0091]

[0092] Another embodiment of the present invention provides a schematic diagram of a rail engineering vehicle assisted driving device based on signal light positioning, including a processor 10, a memory 20, and a computer program stored in the memory 20 and configured to be executed by the processor 10 (the computer program may include computer program A and computer program A1, etc.), and when the processor 10 executes the computer program, it implements the steps in the embodiment of the rail engineering vehicle assisted driving method based on signal light positioning as described above.

[0093] Another embodiment of the present invention provides a structural block diagram of a railway engineering vehicle auxiliary driving device based on signal light positioning, including:

[0094] The information acquisition module 11 is used to acquire the image data of the target engineering vehicle in real-time operation and confirm the reference signal light;

[0095] A coordinate transformation module 12, used for performing coordinate transformation on the reference signal light to obtain pixel coordinates of the reference signal light;

[0096] An image processing module 13, used for processing the image data to obtain first position coordinate data of all traffic lights;

[0097] A screening module 14 is used to screen the first position coordinate data based on the acquired second position coordinate data of the current track line corresponding to the target engineering vehicle, so as to obtain a signal light coordinate set corresponding to the current track line;

[0098] A traffic light determination module 15, configured to respectively calculate the Euclidean distance between the pixel coordinates and the coordinates of each traffic light in the coordinate set, and determine the traffic light corresponding to the smallest Euclidean distance as the target traffic light;

[0099] The auxiliary driving module 16 controls the engineering vehicle to execute a corresponding driving strategy according to the color information of the target signal light when the engineering vehicle is running, wherein the driving strategy at least includes deceleration, acceleration, steering or emergency braking.

[0100] The method for assisted driving of a rail engineering vehicle based on signal light positioning provided by an embodiment of the present invention has the beneficial effect of obtaining a signal light coordinate set corresponding to the current track line by screening the first position coordinate data, and then performing Euclidean distance matching on the pixel coordinates with the coordinates of each signal light in the signal light coordinate set corresponding to the current track line to obtain a target signal light, thereby filtering out false detections and locating the target signal light of the engineering vehicle from multiple detected signal lights.

[0101] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A railway engineering vehicle assisted driving method based on signal light positioning, characterized in that: include: Acquire image data and position data of the target engineering vehicle in real-time operation, and confirm the reference signal light according to the position data; Performing coordinate transformation on the reference signal light to obtain pixel coordinates of the reference signal light; Processing the image data to obtain first position coordinate data of all signal lights and second position coordinates of the current track line corresponding to the target engineering vehicle; Based on the second position coordinate data of the current track line corresponding to the target engineering vehicle, the first position coordinate data is filtered to obtain a signal light coordinate set corresponding to the current track line; respectively calculating the Euclidean distance between the pixel coordinates of the reference signal light and the coordinates of each signal light in the coordinate set, and determining the signal light corresponding to the smallest Euclidean distance as the target signal light; When the engineering vehicle is running, the engineering vehicle is controlled to execute a corresponding driving strategy according to the color information of the target signal light, wherein the driving strategy at least includes deceleration, acceleration, steering or emergency braking.

2. The railway engineering vehicle assisted driving method based on signal light positioning according to claim 1, characterized in that: The coordinate transformation of the reference signal light is performed to obtain the pixel coordinates of the reference signal light, specifically: The world coordinates of the reference signal light based on the target engineering vehicle are calculated, and the world coordinates are transformed into the pixel coordinates according to the extrinsic parameters and intrinsic parameters of the calibrated camera.

3. The railway engineering vehicle assisted driving method based on signal light positioning according to claim 1, characterized in that: The first position coordinate data is filtered based on the second position coordinate data of the current track line corresponding to the target engineering vehicle to obtain a signal light coordinate set corresponding to the current track line, specifically: Performing track line detection on the image data based on the optimized UFLDT algorithm to obtain second position coordinate data of the current track line; Based on the second position coordinate data, the first position coordinate data is filtered to obtain a signal light coordinate set corresponding to the current track line.

4. The railway engineering vehicle assisted driving method based on signal light positioning according to claim 3, characterized in that: The UFLDT algorithm is obtained by optimizing the UFLD algorithm based on Transformer's self-attention mechanism and adding a channel attention module in the auxiliary segmentation network to optimize the second position coordinate data.

5. The railway engineering vehicle assisted driving method based on signal light positioning according to claim 3, characterized in that: The first position coordinate data is filtered based on the second position coordinate data to obtain a signal light coordinate set corresponding to the current track line, specifically: respectively calculating the Euclidean distance between the second position coordinate data and the first position coordinate data of each traffic light; The Euclidean distance is compared with a threshold value, and based on the comparison result, a set of signal light coordinates corresponding to the current track line is obtained.

6. The railway engineering vehicle assisted driving method based on signal light positioning according to claim 1, characterized in that: The Euclidean distance calculation formula is as follows: Among them, d l is the distance, (x,y) is the pixel coordinate, (x l ,y l ) are the signal light coordinates.

7. The railway engineering vehicle assisted driving method based on signal light positioning according to claim 1, characterized in that: According to the color information of the target signal light, the engineering vehicle is controlled to execute a corresponding driving strategy, specifically: Feedback the color information of the target signal light to the control console for processing. After manual review, the control curve of the engineering vehicle will be closed at the next signal light; If the emergency braking condition is met, the target engineering vehicle is controlled to trigger emergency braking, wherein the emergency braking condition is: It is detected that the color of the target signal light is red, the manual review fails, and the target engineering vehicle does not stop at the closed point of the target signal light.

8. A railway engineering vehicle auxiliary driving device based on signal light positioning, characterized in that: include: An information acquisition module, used to acquire image data and position data of a target engineering vehicle in real-time operation, and to confirm a reference signal light according to the position data; A coordinate transformation module, used for performing coordinate transformation on the reference signal light to obtain pixel coordinates of the reference signal light; An image processing module, used for processing the image data to obtain first position coordinate data of all signal lights and second position coordinate data of a current track line corresponding to the target engineering vehicle; A screening module, configured to screen the first position coordinate data based on the second position coordinate data of the current track line corresponding to the target engineering vehicle, to obtain a signal light coordinate set corresponding to the current track line; A signal light determination module, used to respectively calculate the Euclidean distance between the pixel coordinates of the reference signal light and the coordinates of each signal light in the coordinate set, and determine the signal light corresponding to the smallest Euclidean distance as the target signal light; The auxiliary driving module controls the engineering vehicle to execute a corresponding driving strategy according to the color information of the target signal light when the engineering vehicle is running, wherein the driving strategy at least includes deceleration, acceleration, steering or emergency braking.

9. A railway engineering vehicle auxiliary driving device based on signal light positioning, characterized in that: The invention comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the railway engineering vehicle assisted driving method based on signal light positioning as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein when the device where the computer-readable storage medium is located executes the computer program, the railway engineering vehicle assisted driving method based on signal light positioning as described in any one of claims 1 to 7 is implemented.

Images