Potential safety hazard point identification method and device, equipment, storage medium and program product

Abstract

The embodiment of the invention provides a potential safety hazard point identification method and device, equipment, a storage medium and a program product, and particularly relates to the technical field of traffic information processing. The method comprises the steps of performing potential safety hazard assessment on a confluence point based on a connection relationship between the confluence point and a road model in acquired confluence point data, and determining candidate potential safety hazard points; acquiring traffic sign image data obtained by shooting road traffic signs at the candidate potential safety hazard points; and based on the traffic sign image data, performing potential safety hazard assessment on the candidate potential safety hazard points, and identifying a target potential safety hazard point. The method is used for achieving the effect of improving the recognition accuracy of the potential safety hazard points.

Description

Technical Field

[0001] The present application relates to the technical field of traffic information processing, and in particular to a method, device, equipment, storage medium and program product for identifying potential safety hazards. Background Art

[0002] Merging points are high-risk areas for traffic accidents, especially collisions and skidding accidents caused by changes in vehicle speed, direction and traffic flow. By identifying merging points with potential safety hazards, drivers can be warned in advance to adjust their speed, maintain distance and lane, thereby effectively preventing traffic accidents.

[0003] At present, based on the road topology, all highway confluence points with ramps are regarded as safety hazard points. Although this method can fully cover all possible hazard points, its recognition accuracy is low. Summary of the invention

[0004] The embodiments of the present application provide a method, device, equipment, storage medium and program product for identifying potential safety hazards, so as to improve the accuracy of identifying potential safety hazards.

[0005] In a first aspect, an embodiment of the present application provides a method for identifying a potential safety hazard point, including:

[0006] Based on the connection relationship between the merging point and the road model in the acquired merging point data, the safety hazard of the merging point is evaluated to determine the candidate safety hazard points;

[0007] Acquire traffic sign image data obtained by photographing a road traffic sign at the candidate potential safety hazard point;

[0008] Based on the traffic sign image data, a safety hazard assessment is performed on the candidate safety hazard points to identify target safety hazard points.

[0009] In a possible implementation, the step of performing safety hazard assessment on the merging point based on the connection relationship between the merging point and the road model in the acquired merging point data and determining the candidate safety hazard point includes:

[0010] For any confluence point, based on a connection relationship between the confluence point and a road model, determining a plurality of road models connected to the confluence point, wherein the road model represents a road segment between two road nodes;

[0011] Based on the number of lanes included in a plurality of road models connected to the merging point, a safety hazard assessment is performed on the merging point to determine a candidate safety hazard point.

[0012] In a possible implementation, the step of performing safety hazard assessment on the candidate safety hazard points based on the traffic sign image data and identifying target safety hazard points includes:

[0013] For any candidate potential safety hazard point, performing traffic sign recognition of a specified type based on the traffic sign image data corresponding to the candidate potential safety hazard point to obtain a traffic sign recognition result;

[0014] Based on the traffic sign recognition result, determining the relative position relationship between the designated type of traffic sign and the candidate safety hazard point;

[0015] Based on the relative position relationship, a safety hazard assessment is performed on the candidate safety hazard points to identify target safety hazard points.

[0016] In a possible implementation manner, determining the relative position relationship between the designated type of traffic sign and the candidate potential safety hazard point based on the traffic sign recognition result includes:

[0017] Extracting a local road network based on the candidate potential safety hazard points to obtain a local road network extraction result;

[0018] Importing the traffic sign recognition result and the local road network extraction result into a map platform;

[0019] The spatial relationship between traffic signs and road networks is analyzed through the map platform to obtain the relative position relationship between the specified type of traffic signs and the candidate safety hazard points.

[0020] In a possible implementation, the step of performing a safety hazard assessment on the candidate safety hazard points based on the relative position relationship and identifying a target safety hazard point includes:

[0021] Based on the number of lanes respectively included in a plurality of lane models connected to the candidate potential safety hazard point, performing a potential safety hazard assessment on the candidate potential safety hazard point to obtain a first assessment score;

[0022] Based on the relative position relationship, performing a safety hazard assessment on the candidate safety hazard point to obtain a second assessment score;

[0023] Calculating a total score of the candidate potential safety hazard point based on the first evaluation score and the second evaluation score;

[0024] If the total score meets the preset score condition, the candidate potential safety hazard point is determined as the target potential safety hazard point.

[0025] In a possible implementation, before performing safety hazard assessment on the merging point based on the connection relationship between the merging point and the road model in the acquired merging point data and determining the candidate safety hazard point, the method further includes:

[0026] Based on the connection relationship between the road nodes and the road models in the acquired road network data, identifying the road nodes contained in the road network data that meet the preset road model connection quantity requirement, and obtaining the candidate confluence point;

[0027] Based on the angles between multiple road models connected to the candidate merging point, a candidate merging point that meets the preset road model angle requirement is identified to obtain a target merging point;

[0028] The confluence point data corresponding to the target confluence point is extracted from the road network data.

[0029] In a possible implementation, the step of performing safety hazard assessment on the merging point based on the number of lanes included in the plurality of road models connected to the merging point to determine a candidate safety hazard point includes:

[0030] Determining a main road model and a ramp road model based on angles between a plurality of road models connected to the confluence point;

[0031] Determining whether the number of lanes included in the main road model and the ramp road model meets a preset lane number relationship condition;

[0032] If the number of lanes included in the main road model and the ramp road model meets a preset lane number relationship condition, the merging point is determined as a candidate safety hazard point.

[0033] In a second aspect, an embodiment of the present application provides a device for identifying potential safety hazards, including:

[0034] A first evaluation module is used to evaluate the safety hazard of the merging point based on the connection relationship between the merging point and the road model in the acquired merging point data, and determine the candidate safety hazard point;

[0035] An acquisition module, used to acquire traffic sign image data obtained by photographing a road traffic sign at the candidate potential safety hazard point;

[0036] The second evaluation module is used to perform safety hazard evaluation on the candidate safety hazard points based on the traffic sign image data and identify target safety hazard points.

[0037] In a possible implementation manner, the first evaluation module is specifically configured to:

[0038] For any confluence point, based on a connection relationship between the confluence point and a road model, determining a plurality of road models connected to the confluence point, wherein the road model represents a road segment between two road nodes;

[0039] Based on the number of lanes included in a plurality of road models connected to the merging point, a safety hazard assessment is performed on the merging point to determine a candidate safety hazard point.

[0040] In a possible implementation manner, the second evaluation module is specifically configured to:

[0041] For any candidate potential safety hazard point, performing traffic sign recognition of a specified type based on the traffic sign image data corresponding to the candidate potential safety hazard point to obtain a traffic sign recognition result;

[0042] Based on the traffic sign recognition result, determining the relative position relationship between the designated type of traffic sign and the candidate safety hazard point;

[0043] Based on the relative position relationship, a safety hazard assessment is performed on the candidate safety hazard points to identify target safety hazard points.

[0044] In a possible implementation manner, the second evaluation module is specifically configured to:

[0045] Extracting a local road network based on the candidate potential safety hazard points to obtain a local road network extraction result;

[0046] Importing the traffic sign recognition result and the local road network extraction result into a map platform;

[0047] The spatial relationship between traffic signs and road networks is analyzed through the map platform to obtain the relative position relationship between the specified type of traffic signs and the candidate safety hazard points.

[0048] In a possible implementation manner, the second evaluation module is specifically configured to:

[0049] Based on the number of lanes respectively included in a plurality of lane models connected to the candidate potential safety hazard point, performing a potential safety hazard assessment on the candidate potential safety hazard point to obtain a first assessment score;

[0050] Based on the relative position relationship, performing a safety hazard assessment on the candidate safety hazard point to obtain a second assessment score;

[0051] Calculating a total score of the candidate potential safety hazard point based on the first evaluation score and the second evaluation score;

[0052] If the total score meets the preset score condition, the candidate potential safety hazard point is determined as the target potential safety hazard point.

[0053] In a possible implementation manner, the potential safety hazard point identification device is further used to:

[0054] Based on the connection relationship between the road nodes and the road models in the acquired road network data, identifying the road nodes contained in the road network data that meet the preset road model connection quantity requirement, and obtaining the candidate confluence point;

[0055] Based on the angles between multiple road models connected to the candidate merging point, a candidate merging point that meets the preset road model angle requirement is identified to obtain a target merging point;

[0056] The confluence point data corresponding to the target confluence point is extracted from the road network data.

[0057] In a possible implementation manner, the first evaluation module is specifically configured to:

[0058] Determining a main road model and a ramp road model based on angles between a plurality of road models connected to the confluence point;

[0059] Determining whether the number of lanes included in the main road model and the ramp road model meets a preset lane number relationship condition;

[0060] If the number of lanes included in the main road model and the ramp road model meets a preset lane number relationship condition, the merging point is determined as a candidate safety hazard point.

[0061] In a third aspect, an embodiment of the present application provides a safety hazard point identification device, including: a memory, a processor;

[0062] The memory stores computer-executable instructions;

[0063] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementations of the first aspect.

[0064] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the first aspect above and / or various possible implementations of the first aspect.

[0065] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above first aspect and / or various possible implementation methods of the first aspect.

[0066] The safety hazard point identification method, device, equipment, storage medium and program product provided in the embodiment of the present application can evaluate the safety hazard of the merging point based on the connection relationship between the merging point and the road model in the merging point data, and preliminarily screen out the merging points with potential safety hazards. These merging points are candidate safety hazard points. The candidate safety hazard points are not the final safety hazard points, but the objects that need further analysis and verification. For the candidate safety hazard points, the traffic sign image data obtained by photographing the road traffic signs at the candidate safety hazard points can be obtained. Based on the traffic sign image data, the candidate safety hazard points can be evaluated for safety hazards, and finally the merging points with actual safety hazards are confirmed. These merging points are the target safety hazard points. Compared with the prior art that all merging points of highways with ramps are regarded as safety hazard points, the present application combines the road network data and the traffic sign image data to identify the merging points with potential safety hazards from the full amount of merging points, that is, to distinguish the merging points with actual safety hazards from the normal merging points, so as to achieve the effect of improving the recognition accuracy of safety hazard points. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0068] Figure 1 A schematic diagram of a scenario for the method for identifying potential safety hazards provided in this application;

[0069] Figure 2 Schematic diagram of the process of identifying potential safety hazards provided in this application Figure 1 ;

[0070] Figure 3 Schematic diagram of the process of identifying potential safety hazards provided in this application Figure 2 ;

[0071] Figure 4 A schematic diagram of the confluence point provided for this application;

[0072] Figure 5 A schematic diagram of the process of performing spatial relationship analysis provided for this application;

[0073] Figure 6 Schematic diagram of the installation of the attention merging sign provided for this application;

[0074] Figure 7 A schematic diagram of the structure of the safety hazard point identification device provided in this application;

[0075] Figure 8 This is a schematic diagram of the structure of the safety hazard point identification device provided in this application.

[0076] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0077] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0078] The application scenario of the present application is specifically to identify the scenario of merging points with potential safety hazards. The merging point refers to the place where two or more lanes merge into one lane on a highway or other multi-lane road. On a highway, when the ramp of the highway (such as an entrance ramp or an exit ramp) merges into the main road, the merging area formed is the merging point. In this area, vehicles from the ramp need to merge into the traffic flow of the main road. The merging point is an area where the traffic flow varies greatly, and traffic congestion and accidents are prone to occur.

[0079] Combined with the above scenario, in the prior art, all highway converging points with ramps are regarded as safety hazard points. Although this method can fully cover all possible hazard points, its recognition accuracy is low. Specifically, since all ramp access points are treated equally as safety hazard points, this method fails to effectively distinguish between converging points with actual safety hazards and normal converging points, resulting in too much data in the identification results. During the hazard investigation process, key hazards may not be dealt with in a timely manner, affecting the efficiency and accuracy of the hazard investigation work. In addition, the merging safety hazard points identified only based on the road topological relationship regard the risk levels of merging safety hazards with different characteristics as consistent, losing their original characteristics. This homogenization process cannot provide effective data support for refined management, nor can it provide targeted guidance for subsequent hazard remediation work.

[0080] The safety hazard point identification method provided by the present application can evaluate the safety hazard of the merging point based on the connection relationship between the merging point and the road model in the merging point data, and preliminarily screen out the merging points with potential safety hazards. These merging points are candidate safety hazard points. Candidate safety hazard points are not the final safety hazard points, but objects that need further analysis and verification. For the candidate safety hazard points, traffic sign image data obtained by photographing road traffic signs at the candidate safety hazard points can be obtained. Based on the traffic sign image data, the candidate safety hazard points can be evaluated for safety hazards, and finally the merging points with actual safety hazards are confirmed. These merging points are the target safety hazard points. Compared with the prior art that regards all merging points of highways with ramps as safety hazard points, the present application combines road network data and traffic sign image data to identify merging points with potential safety hazards from all merging points, that is, to distinguish merging points with actual safety hazards from normal merging points, which solves the technical problem that the prior art fails to effectively distinguish merging points with actual safety hazards from normal merging points, resulting in low recognition accuracy.

[0081] Figure 1 A schematic diagram of a scenario of a method for identifying potential safety hazards provided in this application, such as Figure 1 As shown, the vehicle-mounted camera device can be placed on the vehicle 101 to photograph road traffic signs to obtain traffic sign image data. The road network data can be stored in the server 103. The terminal device 102 can obtain the traffic sign image data from the vehicle 101 and the road network data from the server 103. By combining the road network data and the traffic sign image data, the merging points with potential safety hazards can be identified from the full amount of merging points contained in the road network data.

[0082] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0083] Figure 2 Schematic diagram of the process of identifying potential safety hazards provided in this application Figure 1 ,like Figure 2 As shown, the method includes:

[0084] S201. Based on the connection relationship between the merging point and the road model in the acquired merging point data, a safety hazard assessment is performed on the merging point to determine candidate safety hazard points.

[0085] Road network data includes road nodes and road models. A road model represents a road segment between two road nodes. A road node represents an endpoint of a road model or an intersection between road models. A road model (i.e., a link) can contain only one line segment or multiple line segments.

[0086] In an embodiment of the present application, road network data can be obtained, road nodes belonging to confluence points contained in the road network data can be identified, and confluence point data can be obtained. Based on the connection relationship between the confluence point and the road model in the confluence point data, a safety hazard assessment can be performed on the confluence point, and confluence points with potential safety hazards can be preliminarily screened out from all confluence points. These confluence points are candidate safety hazard points. The candidate safety hazard points are not the final safety hazard points, but are objects that require further analysis and verification.

[0087] S202: Obtain traffic sign image data obtained by photographing road traffic signs at candidate potential safety hazard points.

[0088] In an embodiment of the present application, traffic sign image data obtained by photographing road traffic signs near a candidate safety hazard point may be obtained.

[0089] S203: Based on the traffic sign image data, perform safety hazard assessment on the candidate safety hazard points and identify the target safety hazard points.

[0090] In an embodiment of the present application, based on the traffic sign image data, the traffic sign setting status at the candidate safety hazard points can be known, so that the candidate safety hazard points can be evaluated for safety hazard, and the final safety hazard point, i.e., the target safety hazard point, can be screened out from the candidate safety hazard points.

[0091] The safety hazard point identification method provided in the embodiment of the present application can evaluate the safety hazard of the merging point based on the connection relationship between the merging point and the road model in the merging point data, and preliminarily screen out the merging points with potential safety hazards. These merging points are candidate safety hazard points. Candidate safety hazard points are not the final safety hazard points, but objects that need further analysis and verification. For the candidate safety hazard points, traffic sign image data obtained by photographing road traffic signs at the candidate safety hazard points can be obtained. Based on the traffic sign image data, the candidate safety hazard points can be evaluated for safety hazards, and finally the merging points with actual safety hazards are confirmed. These merging points are the target safety hazard points. Compared with the prior art that all merging points of highways with ramps are regarded as safety hazard points, the present application combines road network data and traffic sign image data to identify merging points with potential safety hazards from all merging points, that is, to distinguish merging points with actual safety hazards from normal merging points, so as to achieve the effect of improving the recognition accuracy of safety hazard points.

[0092] Figure 3 Schematic diagram of the process of identifying potential safety hazards provided in this application Figure 2 ,like Figure 3 As shown, in this embodiment Figure 2 Based on the embodiment, a method for identifying potential safety hazards is described in detail. The method includes:

[0093] S301. For any confluence point, based on a connection relationship between the confluence point and a road model, determine a plurality of road models connected to the confluence point, where the road model represents a road segment between two road nodes.

[0094] In an embodiment of the present application, based on the connection relationship between the merging point and the road model in the acquired merging point data, a safety hazard assessment can be performed on the merging point to determine candidate safety hazard points.

[0095] In a possible implementation, based on the connection relationship between the merging point and the road model in the acquired merging point data, a safety hazard assessment is performed on the merging point. Before determining the candidate safety hazard point, the safety hazard point identification method of the embodiment of the present application may further include:

[0096] Based on the connection relationship between the road nodes and the road models in the acquired road network data, the road nodes contained in the road network data that meet the preset road model connection quantity requirement are identified to obtain candidate confluence points;

[0097] Based on the angles between multiple road models connected to the candidate merging point, a candidate merging point that meets the preset road model angle requirements is identified to obtain a target merging point;

[0098] Extract the confluence point data corresponding to the target confluence point from the road network data.

[0099] Among them, the preset road model connection quantity requirement may be that at least three road models are connected to the same road node, and the preset road model angle requirement may be that the angle between the main road model and the ramp road model is less than a specified angle.

[0100] The road network data includes the connection relationship between road nodes and road models, as well as the heading angle of each road model. According to the connection relationship between road nodes and road models and the heading angle of each road model, the road nodes belonging to the confluence points contained in the road network data can be automatically identified to obtain the confluence point data.

[0101] Specifically, the set containing all road nodes can be denoted as A, and the elements in set A can be denoted as a i , the road nodes connected to the three road models will be recorded as diverging points or converging points, and then the road models associated with the diverging points or converging points will be used The heading angle attribute is used to determine the two road models with a heading angle difference of less than 5 degrees as the main road model. Then, the road model with a smaller heading angle is determined from the two main road models. The heading angle difference between the road model with a smaller heading angle and the remaining road model (that is, the ramp road model) is calculated. If the heading angle difference is less than 90 degrees, a can be determined. i is the confluence point, and the specific calculation process can be shown in Formula 1, Formula 2 and Formula 3.

[0102]

[0103] Reference Figure 4 As shown in the figure, it is a schematic diagram of the confluence point provided by this application. As shown in the figure, a1 and the road model Connect, satisfying formula 1, so a1 is a divergence point or a confluence point, then identify the road model with a heading angle difference of less than 5 degrees, because The heading angle difference is 0 degrees, so we can Determine the main road model and then calculate The heading angle difference between the main road model and the main road model with a smaller heading angle is less than 90 degrees, so a1 in the figure is a typical merging point.

[0104] By traversing all elements in set A using the above method, all confluence points in the road network data can be found, and the set containing all confluence points can be denoted as R.

[0105] S302: Based on the number of lanes included in the multiple road models connected to the merging point, a safety hazard assessment is performed on the merging point to determine a candidate safety hazard point.

[0106] In an embodiment of the present application, after identifying the road nodes belonging to the merging point contained in the road network data and obtaining the merging point data, for any merging point contained in the merging point data, it is possible to determine multiple road models connected to the merging point based on the connection relationship between the merging point and the road model, and based on the number of lanes contained in the multiple road models connected to the merging point, perform a safety hazard assessment on the merging point to determine candidate safety hazard points.

[0107] In a possible implementation, based on the number of lanes included in multiple road models connected to the merging point, a safety hazard assessment is performed on the merging point to determine a candidate safety hazard point, which may specifically include:

[0108] Determine a main road model and a ramp road model based on angles between multiple road models connected to the confluence point;

[0109] Determine whether the number of lanes included in the main road model and the ramp road model meets a preset lane number relationship condition;

[0110] If the number of lanes included in the main road model and the ramp road model meets the preset lane number relationship condition, the merging point is determined as a candidate safety hazard point.

[0111] For an element r in the set R j , is the number of lanes contained in the main road model after confluence at the confluence point, is the number of lanes contained in the main road model before the merging point, is the number of lanes contained in the ramp road model before the merging point. If the number of lanes contained in the main road model after merging, the main road model before merging, and the ramp road model before merging satisfy Formula 4, it can be considered that the risk level of this merging point is high, and the merging point can be determined as a candidate safety hazard point. The set containing all candidate safety hazard points can be recorded as C. Formula 4 can be specifically as follows:

[0112]

[0113] S303: Obtain traffic sign image data obtained by photographing road traffic signs at the candidate potential safety hazard point.

[0114] In an embodiment of the present application, after a safety hazard assessment is performed on all merging points and candidate safety hazard points are determined, an image data acquisition instruction can be generated so that the vehicle can photograph road traffic signs at the candidate safety hazard points based on the image data acquisition instruction to obtain corresponding traffic sign image data.

[0115] For example, the vehicle-mounted photographing device may be placed on a collection vehicle for data collection to photograph road traffic signs to obtain traffic sign image data.

[0116] S304: Based on the traffic sign image data, perform safety hazard assessment on the candidate safety hazard points and identify the target safety hazard points.

[0117] In a possible implementation, based on the traffic sign image data, performing safety hazard assessment on candidate safety hazard points and identifying target safety hazard points may specifically include:

[0118] For any candidate potential safety hazard point, a specified type of traffic sign recognition is performed based on the traffic sign image data corresponding to the candidate potential safety hazard point to obtain a traffic sign recognition result;

[0119] Based on the traffic sign recognition results, determine the relative position relationship between the specified type of traffic sign and the candidate safety hazard point;

[0120] Based on the relative position relationship, the candidate safety hazard points are evaluated and the target safety hazard points are identified.

[0121] The traffic sign recognition result includes data of a specified type of traffic sign, such as geographic location information of a specified type of traffic sign.

[0122] In this embodiment, for the acquired traffic sign image data, a target detection algorithm, such as YOLO (You Only Look Once), can be used to detect the position of the traffic sign in the original image. Based on the position of the traffic sign in the original image, the detected traffic sign can be cut out from the original image to obtain a cut-out image containing the traffic sign. Then, a pre-trained classification model, such as a classification model based on a convolutional neural network, can be used to perform image recognition on the cut-out image to determine the type of traffic sign contained in the cut-out image, specifically, whether the traffic sign is a "Attention Merge" sign. Next, the camera intrinsic and extrinsic parameters pre-calibrated by the vehicle-mounted shooting device can be obtained, and the camera intrinsic and extrinsic parameters can be used to determine the exact geographical location of the traffic sign using three-dimensional reconstruction technology.

[0123] In this embodiment, after performing designated type of traffic sign recognition and obtaining the traffic sign recognition result, the relative position relationship between the designated type of traffic sign and the candidate safety hazard point can be determined based on the geographic location information of the designated type of traffic sign contained in the traffic sign recognition result. Based on the relative position relationship, a safety hazard assessment can be performed on the candidate safety hazard points to determine the final safety hazard point.

[0124] In a possible implementation, based on the traffic sign recognition result, determining the relative position relationship between the specified type of traffic sign and the candidate potential safety hazard point may specifically include:

[0125] Extract local road network based on candidate potential safety hazards and obtain local road network extraction results;

[0126] Import traffic sign recognition results and local road network extraction results into the map platform;

[0127] The spatial relationship between traffic signs and road networks is analyzed through the map platform to obtain the relative position relationship between the specified type of traffic signs and candidate safety hazard points.

[0128] The local road network extraction result contains local road network data.

[0129] In this embodiment, based on the location of the candidate potential safety hazard point, the scope of local road network extraction can be determined, and the road network data within the scope can be acquired to obtain the local road network data.

[0130] The traffic sign recognition results and local road network extraction results can be imported into the map platform, and the spatial relationship analysis between traffic signs and road networks can be performed using the spatial analysis tools of the map platform. Common spatial relationships include distance calculation, proximity analysis, buffer zone analysis, etc. By performing spatial relationship analysis, it can be determined whether a specified type of traffic sign exists within the road network range of the extracted local road network, and if it is determined that a specified type of traffic sign exists, the relative distance between the specified type of traffic sign and the candidate safety hazard point can be determined.

[0131] Reference Figure 5 As shown, it is a schematic diagram of the process of spatial relationship analysis provided by the present application. As shown in the figure, for any candidate safety hazard point P in the set C, its upstream direction can be determined according to the directional data. Starting from the candidate safety hazard point P, the specified distance D, for example, 500m, is calculated along the upstream direction, and the specified distance D range from the candidate safety hazard point P along the upstream direction is marked, and all road segments within the range are extracted to obtain the local road network extraction result. The traffic sign recognition result and the local road network extraction result can be imported into the map platform to obtain two layers. The spatial analysis tool of the map platform is used to determine whether there is data correlation between the two layers. If there is no data intersection, it can be determined that there is no specified type of traffic sign within the road network range of the extracted local road network, and the candidate safety hazard point can be marked as: attention to the missing merging sign; if there is data intersection, the relative distance between the candidate safety hazard point and the nearest attention to merging sign can be determined. If the relative distance is greater than 250m, the candidate safety hazard point can be marked as: attention to the reasonable setting of the merging sign; if the relative distance is less than 250m, the candidate safety hazard point can be marked as: attention to the merging sign is set too close.

[0132] In a possible implementation, based on the relative position relationship, performing a safety hazard assessment on the candidate safety hazard points and identifying the target safety hazard points may specifically include:

[0133] Based on the number of lanes respectively included in the multiple road models connected to the candidate safety hazard point, a safety hazard assessment is performed on the candidate safety hazard point to obtain a first assessment score;

[0134] Based on the relative position relationship, a safety hazard assessment is performed on the candidate safety hazard points to obtain a second assessment score;

[0135] Based on the first evaluation score and the second evaluation score, a total score of the candidate potential safety hazard point is calculated;

[0136] If the total score meets the preset score conditions, the candidate safety hazard point is determined as the target safety hazard point.

[0137] For an element c in the set C k, the structural risk level can be evaluated using formula (5), h k That is point c k Structural risk level:

[0138]

[0139] exist Figure 4 In the example, if the road model The number of lanes included is 3, The number of lanes included is 3, The number of lanes included is 2, and according to formula (5), the structural risk level of this point can be calculated to be 0.2.

[0140] Remember element c in set C k The risk of the attention merge sign is set to s k , it is stipulated that when the merging sign is set reasonably k = 0, when the merging sign is set too close s k = 1, when attention merge flag setting is missing s k =2. Combined with the above calculation, the structural risk level h k , element c k The final safety hazard assessment score is k It can be calculated using formula (6):

[0141] r k =s k +h k (Formula 6)

[0142] exist Figure 4 In the example, if there is no attention merge sign around point a1, then r1 = 2.2; if the attention merge sign is set at Figure 6 M, then point a1 belongs to the point where the attention merge sign is set too close, so r1 = 1.2; if the attention merge sign is set at Figure 6 At point N, point a1 belongs to the point where the merging sign is set reasonably, r1=0.2.

[0143] According to the above calculation process, the safety hazard assessment score of the merging point can be reduced by setting the attention merging sign and standardizing the location of the attention merging sign. i >1 is considered as a point to be rectified, i.e. i The confluence points with a score >1 are safety hazard points. The rectification priority within the set of safety hazard points can be determined by sorting them according to their assessment scores.

[0144] The safety hazard point identification method provided in the embodiment of the present application can evaluate the safety hazard of the merging point based on the connection relationship between the merging point and the road model in the merging point data, and preliminarily screen out the merging points with potential safety hazards. These merging points are candidate safety hazard points. Candidate safety hazard points are not the final safety hazard points, but objects that need further analysis and verification. For the candidate safety hazard points, traffic sign image data obtained by photographing road traffic signs at the candidate safety hazard points can be obtained. Based on the traffic sign image data, the candidate safety hazard points can be evaluated for safety hazards, and finally the merging points with actual safety hazards are confirmed. These merging points are the target safety hazard points. Compared with the prior art that all merging points of highways with ramps are regarded as safety hazard points, the present application combines road network data and traffic sign image data to identify merging points with potential safety hazards from all merging points, that is, to distinguish merging points with actual safety hazards from normal merging points, so as to achieve the effect of improving the recognition accuracy of safety hazard points.

[0145] This application constructs an automatic identification method for merging safety hazard points. This method uses road network data to identify all merging points, then calculates and scores the risk level of the merging points through the lane number attribute of the road model connected to the merging points, and extracts high-risk merging points from them; then, vehicles are used to collect the setting of attention merging signs at high-risk merging points to obtain traffic sign image data, and the setting position of attention merging signs is identified and located through image recognition technology. Finally, the merging safety hazard points are extracted based on the risk level of the merging points and the sign setting.

[0146] Figure 7 The schematic diagram of the structure of the safety hazard point identification device provided in this application is as follows: Figure 7 As shown, the safety hazard point identification device 70 provided in this embodiment includes:

[0147] The first evaluation module 701 is used to evaluate the safety hazard of the merging point based on the connection relationship between the merging point and the road model in the acquired merging point data, and determine the candidate safety hazard point;

[0148] An acquisition module 702 is used to acquire traffic sign image data obtained by photographing road traffic signs at candidate potential safety hazards points;

[0149] The second evaluation module 703 is used to perform safety hazard evaluation on candidate safety hazard points based on the traffic sign image data, and identify target safety hazard points.

[0150] In a possible implementation, the first evaluation module is specifically configured to:

[0151] For any confluence point, based on the connection relationship between the confluence point and the road model, multiple road models connected to the confluence point are determined, and the road model represents a road segment between two road nodes;

[0152] Based on the number of lanes contained in multiple road models connected to the merging point, a safety hazard assessment is performed on the merging point to determine candidate safety hazard points.

[0153] In a possible implementation manner, the second evaluation module is specifically used to:

[0154] For any candidate potential safety hazard point, a specified type of traffic sign recognition is performed based on the traffic sign image data corresponding to the candidate potential safety hazard point to obtain a traffic sign recognition result;

[0155] Based on the traffic sign recognition results, determine the relative position relationship between the specified type of traffic sign and the candidate safety hazard point;

[0156] Based on the relative position relationship, the candidate safety hazard points are evaluated and the target safety hazard points are identified.

[0157] In a possible implementation manner, the second evaluation module is specifically used to:

[0158] Extract local road network based on candidate potential safety hazards and obtain local road network extraction results;

[0159] Import traffic sign recognition results and local road network extraction results into the map platform;

[0160] The spatial relationship between traffic signs and road networks is analyzed through the map platform to obtain the relative position relationship between the specified type of traffic signs and candidate safety hazard points.

[0161] In a possible implementation manner, the second evaluation module is specifically used to:

[0162] Based on the number of lanes respectively included in the multiple road models connected to the candidate safety hazard point, a safety hazard assessment is performed on the candidate safety hazard point to obtain a first assessment score;

[0163] Based on the relative position relationship, a safety hazard assessment is performed on the candidate safety hazard points to obtain a second assessment score;

[0164] Based on the first evaluation score and the second evaluation score, a total score of the candidate potential safety hazard point is calculated;

[0165] If the total score meets the preset score conditions, the candidate safety hazard point is determined as the target safety hazard point.

[0166] In a possible implementation, the safety hazard point identification device is further used to:

[0167] Based on the connection relationship between the road nodes and the road models in the acquired road network data, the road nodes contained in the road network data that meet the preset road model connection quantity requirement are identified to obtain candidate confluence points;

[0168] Based on the angles between multiple road models connected to the candidate merging point, a candidate merging point that meets the preset road model angle requirements is identified to obtain a target merging point;

[0169] Extract the confluence point data corresponding to the target confluence point from the road network data.

[0170] In a possible implementation, the first evaluation module is specifically configured to:

[0171] Determine a main road model and a ramp road model based on angles between multiple road models connected to the confluence point;

[0172] Determine whether the number of lanes included in the main road model and the ramp road model meets a preset lane number relationship condition;

[0173] If the number of lanes included in the main road model and the ramp road model meets the preset lane number relationship condition, the merging point is determined as a candidate safety hazard point.

[0174] The safety hazard point identification device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and this embodiment will not be described in detail here.

[0175] Figure 8 This is a schematic diagram of the structure of the safety hazard point identification device provided in this application. Figure 8 As shown, the safety hazard point identification device 80 provided in this embodiment includes: at least one processor 801 and a memory 802. Optionally, the device 80 also includes a communication component 803. The processor 801, the memory 802 and the communication component 803 are connected via a bus.

[0176] In a specific implementation process, at least one processor 801 executes the computer-executable instructions stored in the memory 802, so that at least one processor 801 executes the above method.

[0177] The specific implementation process of the processor 801 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0178] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0179] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (Non-volatile Memory, NVM), such as at least one disk memory.

[0180] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0181] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0182] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.

[0183] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0184] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0185] The division of units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0186] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0187] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0188] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0189] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0190] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention, which follow the general principles of the present invention and include common knowledge or customary technical means in the art not disclosed by the present invention, are not limited to the precise structure described above and shown in the drawings, and may be modified and changed in various ways without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A method for identifying potential safety hazards, characterized in that: include: Based on the connection relationship between the merging point and the road model in the acquired merging point data, the safety hazard of the merging point is evaluated to determine the candidate safety hazard points; Acquire traffic sign image data obtained by photographing a road traffic sign at the candidate potential safety hazard point; Based on the traffic sign image data, a safety hazard assessment is performed on the candidate safety hazard points to identify target safety hazard points.

2. The method according to claim 1, characterized in that: The method of evaluating the safety hazard of the merging point based on the connection relationship between the merging point and the road model in the acquired merging point data and determining the candidate safety hazard point includes: For any confluence point, based on a connection relationship between the confluence point and a road model, determining a plurality of road models connected to the confluence point, wherein the road model represents a road segment between two road nodes; Based on the number of lanes included in multiple road models connected to the merging point, a safety hazard assessment is performed on the merging point to determine a candidate safety hazard point.

3. The method according to claim 2, characterized in that The step of performing safety hazard assessment on the candidate safety hazard points based on the traffic sign image data and identifying target safety hazard points includes: For any candidate potential safety hazard point, performing traffic sign recognition of a specified type based on the traffic sign image data corresponding to the candidate potential safety hazard point to obtain a traffic sign recognition result; Based on the traffic sign recognition result, determining the relative position relationship between the designated type of traffic sign and the candidate safety hazard point; Based on the relative position relationship, a safety hazard assessment is performed on the candidate safety hazard points to identify target safety hazard points.

4. The method according to claim 3, characterized in that The determining, based on the traffic sign recognition result, the relative position relationship between the designated type of traffic sign and the candidate potential safety hazard point comprises: Extracting a local road network based on the candidate potential safety hazard points to obtain a local road network extraction result; Importing the traffic sign recognition result and the local road network extraction result into a map platform; The spatial relationship between traffic signs and road networks is analyzed through the map platform to obtain the relative position relationship between the specified type of traffic signs and the candidate safety hazard points.

5. The method according to claim 3, characterized in that: The step of performing safety hazard assessment on the candidate safety hazard points based on the relative position relationship and identifying target safety hazard points includes: Based on the number of lanes respectively included in a plurality of lane models connected to the candidate potential safety hazard point, performing a potential safety hazard assessment on the candidate potential safety hazard point to obtain a first assessment score; Based on the relative position relationship, performing a safety hazard assessment on the candidate safety hazard point to obtain a second assessment score; Calculating a total score of the candidate potential safety hazard point based on the first evaluation score and the second evaluation score; If the total score meets the preset score condition, the candidate potential safety hazard point is determined as the target potential safety hazard point.

6. The method according to any one of claims 1 to 5, characterized in that: Before performing safety hazard assessment on the merging point based on the connection relationship between the merging point and the road model in the acquired merging point data and determining the candidate safety hazard point, the method further includes: Based on the connection relationship between the road nodes and the road models in the acquired road network data, identifying the road nodes contained in the road network data that meet the preset road model connection quantity requirement, and obtaining the candidate confluence point; Based on the angles between multiple road models connected to the candidate merging point, a candidate merging point that meets the preset road model angle requirement is identified to obtain a target merging point; The confluence point data corresponding to the target confluence point is extracted from the road network data.

7. The method according to any one of claims 2 to 5, characterized in that: The step of performing safety hazard assessment on the merging point based on the number of lanes included in the multiple road models connected to the merging point and determining a candidate safety hazard point includes: Determining a main road model and a ramp road model based on angles between a plurality of road models connected to the confluence point; Determining whether the number of lanes included in the main road model and the ramp road model meets a preset lane number relationship condition; If the number of lanes included in the main road model and the ramp road model meets a preset lane number relationship condition, the merging point is determined as a candidate safety hazard point.

8. A device for identifying potential safety hazards, characterized in that: include: A first evaluation module is used to evaluate the safety hazard of the merging point based on the connection relationship between the merging point and the road model in the acquired merging point data, and determine the candidate safety hazard point; An acquisition module, used to acquire traffic sign image data obtained by photographing a road traffic sign at the candidate potential safety hazard point; The second evaluation module is used to perform safety hazard evaluation on the candidate safety hazard points based on the traffic sign image data and identify target safety hazard points.

9. A device for identifying potential safety hazards, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 7.

10. A computer-readable storage medium / computer program product, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 7 when executed by a processor; and / or, The computer program product comprises a computer program, which implements the method according to any one of claims 1 to 7 when executed by a processor.

Images