Road merging scene identification method and device, electronic equipment and storage medium
By using vehicle sensor data to identify roads and enter scenes, the problem that smart vehicles are difficult to accurately identify lanes when missing map information is missing, and the effect of improving vehicle driving safety is achieved.
Patent Information
- Application Number
- CN202510046790.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-13
- Publication Date
- 2025-03-18
AI Technical Summary
When existing smart vehicles lack map information, it is difficult to accurately identify scenes of lanes such as ramps, resulting in low vehicle driving safety.
By obtaining the road sensing data collected by sensors on the vehicle, the target boundary point set on the target boundary line of the road is determined, and based on the relative distance between these point sets and the lane where the vehicle is located, it is determined whether the road incorporation conditions meets the road incorporation conditions, thereby identifying the road incorporation scenario.
In the absence of map information, the scenes of lanes such as ramps can be accurately identified to provide accurate information support for the safe driving of vehicles and improve the safety of vehicle driving.
Smart Images
Figure CN119636751A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of intelligent vehicle technology, and in particular to a method, device, electronic device and storage medium for identifying a road merging scene. Background Art
[0002] After entering the intelligent driving mode, current intelligent vehicles will automatically identify vehicles merging into other lanes or ramps. For example, when using the adaptive cruise control system to control vehicle driving, the module in the system that predicts the merging behavior of vehicles in adjacent lanes will be used. Predicting the merging of vehicles on the ramp is as important as predicting the merging of vehicles in the adjacent lanes. The currently commonly used method for predicting the merging of vehicles on the ramp is mainly to construct a merging relationship between the target vehicle and the vehicle based on map information to determine whether the target vehicle has the possibility of merging into the lane (i.e., the merging probability). However, in some cases, the map is missing or invalid, and it is impossible to identify whether the target vehicle and the vehicle form a merging relationship. In this case, it is more dangerous to rely solely on the cut-in probability to determine the braking timing. Therefore, how to accurately identify vehicle merging scenarios such as ramps and provide necessary information support for vehicle risk avoidance operations is a problem that needs to be solved. Summary of the invention
[0003] In view of this, in order to solve some or all of the above-mentioned technical problems, the embodiments of the present application provide a method, device, electronic device and storage medium for identifying a road merging scene.
[0004] In a first aspect, an embodiment of the present application provides a method for identifying a road merging scene, the method comprising: obtaining road sensing data collected by sensors on a vehicle about the road the vehicle is traveling on; based on the road sensing data, determining a target boundary point set on a target boundary line of the road; determining a relative distance between the boundary points in the target boundary point set and the lane where the vehicle is located; determining whether the target boundary line meets the road merging conditions based on the relative distance; if the road merging conditions are met, determining that the scene the vehicle is currently in is a road merging scene.
[0005] In one possible implementation, determining a target boundary point set on a target boundary line of a road based on road sensing data includes: determining a first initial target boundary point set corresponding to the target boundary line of the road from the sensing data; determining outliers in the first initial target boundary point set based on the lateral coordinates of the boundary points in the first initial target boundary point set, and deleting the outliers from the first initial target boundary point set to obtain a second initial target boundary point set; extracting boundary points from the second initial target boundary point set based on a preset longitudinal distance interval, and determining each extracted boundary point as a target boundary point set.
[0006] In one possible implementation, determining the relative distance between a boundary point in the target boundary point set and a lane where the vehicle is located includes: determining a center line of the lane where the vehicle is located; and determining the distance between the boundary point in the target boundary point set and the center line as the relative distance between the boundary point and the lane where the vehicle is located.
[0007] In one possible implementation, determining whether a target boundary line meets road merging conditions is performed based on relative distance, including: for each boundary point in the target boundary point set, determining a distance change trend between the boundary point and the lane where the vehicle is located based on the relative distance between the boundary point and the lane where the vehicle is located; if the distance change trend is a close trend, determining the boundary point to be a close class boundary point; if the distance change trend is a far away trend, determining the boundary point to be a far away class boundary point; if the number of close class boundary points and the number of far class boundary points meet a preset quantity condition, determining that the target boundary line meets the road merging conditions.
[0008] In one possible implementation, based on the relative distance corresponding to the boundary point, determining the distance change trend between the boundary point and the lane where the vehicle is located, including: if the first relative distance corresponding to the boundary point is less than the second relative distance corresponding to the previous boundary point of the boundary point, and the absolute value of the difference between the first relative distance and the second relative distance is greater than or equal to the first preset length, determining that the boundary point is a first close class boundary point; if the first relative distance corresponding to the boundary point is less than the third relative distance corresponding to the first boundary point in the target boundary point set, and the absolute value of the difference between the first relative distance and the third relative distance is greater than or equal to the second preset length, determining that the boundary point is a second close class boundary point; if the boundary point is a first close class boundary point If the first relative distance corresponding to the boundary point is greater than the second relative distance corresponding to the previous boundary point of the boundary point, and the absolute value of the difference between the first relative distance and the second relative distance is greater than or equal to the third preset length, the boundary point is determined to be a first far-away boundary point; if the first relative distance corresponding to the boundary point is greater than the third relative distance corresponding to the first boundary point in the target boundary point set, and the absolute value of the difference between the first relative distance and the third relative distance is greater than or equal to the fourth preset length, the boundary point is determined to be a second far-away boundary point; if the boundary point is the first far-away boundary point and / or the second far-away boundary point, the distance change trend is determined to be a far-away trend.
[0009] In one possible implementation, if the number of points close to the class boundary and the number of points far from the class boundary meet the preset quantity conditions, determining that the target boundary line meets the road merging conditions includes: if the number of points close to the class boundary and the number of points far from the class boundary meet at least one of the following conditions, determining that the number of points close to the class boundary and the number of points far from the class boundary meet the quantity conditions: Condition one, the number of the first points close to the class boundary is greater than or equal to the first preset number, and the number of the second points close to the class boundary is greater than or equal to the second preset number; Condition two, the ratio of the first number of points close to the class boundary to the total number of boundary points in the target boundary point set is greater than or equal to the preset ratio; Condition three, the number of points close to the class boundary is greater than the number of points far from the class boundary.
[0010] In a possible implementation, condition three includes: the number of the first points close to the class boundary is greater than the number of the first points far from the class boundary, and the number of the second points close to the class boundary is greater than the number of the second points far from the class boundary.
[0011] In a second aspect, an embodiment of the present application provides a device for identifying a road merging scene, the device comprising: an acquisition module, for acquiring road sensing data collected by sensors on a vehicle about the road on which the vehicle is traveling; a first determination module, for determining a target boundary point set on a target boundary line of the road based on the road sensing data; a second determination module, for determining a relative distance between a boundary point in the target boundary point set and a lane where the vehicle is located; a third determination module, for determining whether the target boundary line meets a road merging condition based on the relative distance; and a fourth determination module, for determining that the scene in which the vehicle is currently located is a road merging scene if the road merging condition is met.
[0012] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a memory for storing a computer program; a processor for executing the computer program stored in the memory, and when the computer program is executed, a method of any embodiment of the method for identifying a road merging scene of the first aspect of the present application is implemented.
[0013] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method of any embodiment of the method for identifying a road merging scene as described in the first aspect above is implemented.
[0014] In a fifth aspect, an embodiment of the present application provides a computer program, which includes a computer-readable code. When the computer-readable code is executed on a device, a processor in the device implements a method of any embodiment of the method for identifying a road merging scene as described in the first aspect above.
[0015] The road merging scene recognition method, device, electronic device and storage medium provided in the embodiments of the present application obtain road sensing data collected by sensors on the vehicle, determine the target boundary point set on the target boundary line of the road based on the road sensing data, and then determine the relative distance between each boundary point and the lane where the vehicle is located. According to the relative distance, determine whether the target boundary line meets the road merging conditions. If the road merging conditions are met, determine that the scene the vehicle is currently in is a road merging scene. The embodiments of the present application can accurately identify lane merging scenes such as ramps when map information is missing, provide accurate information support for the safe driving of the vehicle, and improve the safety of vehicle driving. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] 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.
[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0018] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.
[0019] Figure 1 A schematic diagram of a flow chart of a method for identifying a road merging scene provided in an embodiment of the present application;
[0020] Figure 2 A schematic diagram of a road merging scenario on an actual road provided in an embodiment of the present application;
[0021] Figure 3 A schematic diagram of a flow chart of another method for identifying a road merging scenario provided in an embodiment of the present application;
[0022] Figure 4 A schematic diagram of a flow chart of another method for identifying a road merging scenario provided in an embodiment of the present application;
[0023] Figure 5 A schematic diagram of a flow chart of another method for identifying a road merging scenario provided in an embodiment of the present application;
[0024] Figure 6 A schematic diagram of the structure of a device for identifying a road merging scene provided in an embodiment of the present application;
[0025] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0026] Various exemplary embodiments of the present application will now be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. It should be noted that unless otherwise specifically stated, the relative arrangement of the components and steps, the numerical expressions and the numerical values described in these embodiments do not limit the scope of the present application.
[0027] Those skilled in the art will understand that the terms "first" and "second" in the embodiments of the present application are only used to distinguish between different steps, devices, modules and other objects, and do not represent any specific technical meanings, nor do they indicate the logical order between them.
[0028] It should also be understood that in this embodiment, “plurality” may refer to two or more than two, and “at least one” may refer to one, two or more than two.
[0029] It should also be understood that any component, data or structure mentioned in the embodiments of the present application can generally be understood as one or more, unless explicitly limited or otherwise indicated in the context.
[0030] In addition, the term "and / or" in this application is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this application generally indicates that the associated objects before and after are in an "or" relationship.
[0031] It should also be understood that the description of the various embodiments in this application focuses on the differences between the various embodiments, and the same or similar aspects thereof can be referenced to each other, and for the sake of brevity, they will not be described one by one.
[0032] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present application, its application, or uses.
[0033] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the above-mentioned technologies, methods, and equipment should be considered as part of the specification.
[0034] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.
[0035] It should be noted that, in the absence of conflict, the embodiments in this application and the features in the embodiments can be combined with each other. To facilitate the understanding of the embodiments of the present application, the present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.
[0036] In order to solve the technical problem in the prior art that, when map information is missing, lane merging scenarios cannot be accurately identified, resulting in low vehicle driving safety, the present application provides a method for identifying road merging scenarios, which can use sensors to accurately identify road merging scenarios such as ramps in the absence of map information, thereby improving vehicle driving safety.
[0037] Figure 1 A flow chart of a method for identifying a road merging scene provided in an embodiment of the present application. The method can be applied to a vehicle and executed by a controller on the vehicle. The method can also be executed by one or more electronic devices such as a server, a smart phone, and a laptop computer, which are connected to the vehicle in communication, identify the road sensing data uploaded by the vehicle, determine whether the scene the vehicle is currently in is a road merging scene, and feed back the processing results to the vehicle.
[0038] In addition, the execution subject of the present method may be hardware or software. When the execution subject is hardware, the execution subject may be one or more of the electronic devices. For example, a single electronic device may execute the present method, or a plurality of electronic devices may cooperate with each other to execute the present method. When the execution subject is software, the present method may be implemented as a plurality of software or software modules, or as a single software or software module. No specific limitation is made herein.
[0039] like Figure 1 As shown, the method specifically includes:
[0040] Step 101, obtaining road sensing data collected by sensors on a vehicle about the road the vehicle is traveling on.
[0041] In this embodiment, the sensors on the vehicle may include various sensors, such as cameras, laser radars, ultrasonic radars, etc. The sensors may collect data on the road on which the vehicle is traveling in real time, and the obtained road sensing data includes various data such as images and point clouds.
[0042] Step 102: determining a target boundary point set on a target boundary line of the road based on the road sensing data.
[0043] In this embodiment, the electronic device executing this method can identify various road sensing data to determine the boundary of the road on which the vehicle is currently traveling. For example, a machine vision method can be used to identify the road image captured by the camera on the vehicle, extract the road features in the image, and then determine the road area from the road image to obtain the road boundary line. For another example, the point cloud data collected by the laser radar can be used to determine the position of the road edge, and then obtain the road boundary line representing the road edge.
[0044] Since in the road merging scenario, ramps, auxiliary roads and other roads usually merge into the main road from one side (right side), the road boundary line analyzed in the embodiment of the present application is the target boundary line on one side (right side) of the road. The target boundary line usually represents the outermost edge of the road, so the target boundary line can also be called the hard boundary of the road. The points on the target boundary line are the target boundary point set. Figure 2 As shown, a vehicle (marked as ego) is traveling on a main road, and there is a ramp on the right side of the main road. The two outermost edges of the ramp and the main road are hard boundaries, and a hard boundary L on the right side is the target boundary line. The set of points on the target boundary line is the target boundary point set.
[0045] Optionally, the original boundary point set obtained after identifying the road sensing data can be directly determined as the target boundary point set, or the original boundary point set can be screened (for example, sampled at equal intervals) to extract boundary points that meet the screening conditions as the target boundary point set.
[0046] Step 103, determining the relative distance between the boundary points in the target boundary point set and the lane where the vehicle is located.
[0047] In this embodiment, each boundary point in the target boundary point set may correspond to a coordinate representing the position of the point, and the coordinate system of the coordinate may be a world coordinate system or a vehicle coordinate system with the vehicle as the origin. In this coordinate system, the distance between each boundary point and the reference line representing the lane where the vehicle is located may be calculated by a geometric method. The reference line may be a lane line of the lane or the center line of the lane.
[0048] Step 104: Determine whether the target boundary line meets the road merging condition based on the relative distance.
[0049] In this embodiment, it is possible to determine whether the target boundary line meets the road merging conditions based on the change in relative distance. Usually, the target boundary line will gradually approach the main road, so the above relative distance will gradually decrease. In this embodiment, the relative distances recorded at each time can be statistically calculated. If each relative distance follows a gradually decreasing trend, it can be determined that the target boundary line meets the road merging conditions. For example, the average relative distance in each time period can be calculated in multiple time periods. If the average relative distance follows a gradually decreasing trend, it is determined that the road merging conditions are met.
[0050] Step 105: If the road merging condition is met, determine that the scene the vehicle is currently in is a road merging scene.
[0051] In this embodiment, the road merging scenario may include ramp merging, the main road with more lanes changing to fewer lanes, etc. After determining that the vehicle is currently in a road merging scenario, the scenario may be used as a basis for the intelligent driving algorithm to continue controlling the vehicle to drive according to the corresponding strategy.
[0052] For example, if it is determined that the vehicle is currently in a road merging scenario, the corresponding intelligent driving algorithm for the scenario can continue to be executed to calculate the vehicle's cut-in probability for the scenario.
[0053] Since the vehicle road merging scenarios may include ramp merging, the main road with more lanes becoming fewer lanes, etc., after initially determining that the vehicle is currently in a road merging scenario, other methods can be used to determine whether it is a ramp merging scenario. For example, by determining whether the target vehicle in other lanes (such as Figure 2 The target vehicle (represented by the target shown) is determined based on the angle between its driving direction and the main road, the target vehicle's driving trajectory and other status information to determine whether the target vehicle meets the status of the ramp merging scenario.
[0054] The method for identifying a road merging scene provided in the embodiment of the present application obtains road sensing data collected by sensors on the vehicle, determines a target boundary point set on a target boundary line of the road based on the road sensing data, and then determines the relative distance between each boundary point and the lane where the vehicle is located. Based on the relative distance, it is determined whether the target boundary line meets the road merging conditions. If the road merging conditions are met, it is determined that the scene the vehicle is currently in is a road merging scene. The embodiment of the present application enables accurate identification of lane merging scenes such as ramps when map information is missing, provides accurate information support for safe driving of the vehicle, and improves the safety of vehicle driving.
[0055] In some optional implementations of this embodiment, such as Figure 3 As shown, step 102 includes:
[0056] Step 1021: Determine a first initial target boundary point set corresponding to a target boundary line of the road from the sensing data.
[0057] The first initial target boundary point set is an original boundary point set representing the target boundary line identified from the sensing data.
[0058] Step 1022: determine outlier points in the first initial target boundary point set based on the horizontal coordinates of the boundary points in the first initial target boundary point set, and delete the outlier points from the first initial target boundary point set to obtain a second initial target boundary point set.
[0059] The above-mentioned horizontal coordinates are coordinates on the coordinate axis perpendicular to the driving direction of the vehicle, and correspondingly, the longitudinal coordinates are coordinates on the coordinate axis consistent with the driving direction of the vehicle. The above-mentioned outliers are points whose horizontal coordinate values are far from the horizontal coordinate values of other points. As an example, it can be determined in sequence whether the difference between the horizontal coordinate of each boundary point and the horizontal coordinate of the previous boundary point (or the average value of the horizontal coordinates of the first N boundary points) is greater than a preset threshold. If it is greater than the preset threshold, the boundary point is determined to be an outlier.
[0060] Step 1023: extract boundary points from the second initial target boundary point set based on the preset longitudinal distance interval, and determine the extracted boundary points as the target boundary point set.
[0061] The longitudinal distance interval may be a fixed value, such as 1 m.
[0062] This embodiment deletes outliers based on the horizontal coordinates and samples boundary points at preset intervals based on the vertical coordinates, thereby deleting the noise in the target boundary point set and reducing the number of boundary points used for calculation, thereby improving the accuracy and calculation efficiency of road scene recognition.
[0063] In some optional implementations of this embodiment, step 103 may be performed as follows: determining the center line of the lane where the vehicle is located; and determining the distance between the boundary point in the target boundary point set and the center line as the relative distance between the boundary point and the lane where the vehicle is located.
[0064] The center line is a line formed by a series of points in the lane where the vehicle is located that are equidistant from the two lane lines. The electronic device can determine the lane area where the vehicle is located from the road image by image recognition method and draw a center line in the lane area. The distance between the boundary point in the target boundary point set and the center line is the length of the line segment passing through the boundary point and perpendicular to the center line.
[0065] This embodiment uses the lane centerline as a reference for determining the relative distance between the boundary point and the lane, thereby avoiding interference in the calculated distance caused by numerous lines on the road, making the calculated relative distance more accurate, and helping to improve the accuracy of judging road merging scenarios.
[0066] In some optional implementations of this embodiment, such as Figure 4 As shown, step 104 includes:
[0067] Step 1041, for each boundary point in the target boundary point set, based on the relative distance between the boundary point and the lane where the vehicle is located, determine the distance change trend between the boundary point and the lane where the vehicle is located; if the distance change trend is a closing trend, determine that the boundary point is a closing class boundary point; if the distance change trend is a moving away trend, determine that the boundary point is a moving away class boundary point.
[0068] Specifically, for a boundary point, the relative distance corresponding to the boundary point can be compared with the relative distance corresponding to the boundary point arranged before the boundary point, and the distance change trend can be determined according to the comparison result. The order between the boundary points here can be determined according to the arrangement order of the boundary points in the target boundary point set. That is, according to the driving direction of the vehicle, a serial number is assigned to each boundary point in turn, and each boundary point is arranged according to the serial number. If the serial number of a boundary point is x, the serial number of the boundary point before it is x-1.
[0069] For example, if the relative distance corresponding to the boundary point is smaller than the relative distances corresponding to one or more boundary points before it, the change trend corresponding to the boundary point can be determined to be an approaching trend, that is, as the vehicle travels, the boundary line gradually approaches the lane where the vehicle is located. Similarly, if the relative distance corresponding to the boundary point is larger than the relative distances corresponding to one or more boundary points before it, the change trend corresponding to the boundary point can be determined to be a moving away trend, that is, as the vehicle travels, the boundary line gradually moves away from the lane where the vehicle is located.
[0070] Step 1042: If the number of points close to the class boundary and the number of points far from the class boundary meet the preset quantity conditions, it is determined that the target boundary line meets the road merging condition.
[0071] Among them, the road merging scenario is related to the number of points close to the class boundary and the number of points far from the class boundary. Therefore, the quantity condition can be set according to the characteristics of the actual scenario to determine whether the number of points close to the class boundary and the number of points far from the class boundary meet the quantity condition. As an example, if the number of points close to the class boundary is greater than the number of points far from the class boundary, it can be determined that the road merging condition is met; for another example, if the number of points close to the class boundary is greater than the number of points far from the class boundary, and the proportion of points close to the class boundary to the total number of boundary points in the target boundary point set is greater than a preset proportion, and the proportion of points far from the class boundary to the total number of boundary points in the target boundary point set is less than a preset proportion, it can be determined that the road merging condition is met.
[0072] This embodiment determines the distance change trend of each boundary point in the target boundary point set, and determines whether the road merging conditions are met according to the number of boundary points with different distance change trends, so that the road merging scene is associated with the distance change trend of the boundary points, thereby improving the accuracy and efficiency of judging the road merging scene.
[0073] In some optional implementations of this embodiment, such as Figure 5 As shown, in step 1041, for each boundary point in the target boundary point set, the distance change trend between the boundary point and the lane where the vehicle is located can be determined according to the following steps:
[0074] Step 10411, if the first relative distance corresponding to the boundary point is smaller than the second relative distance corresponding to the previous boundary point of the boundary point, and the absolute value of the difference between the first relative distance and the second relative distance is greater than or equal to the first preset length, determine that the boundary point is a first close class boundary point.
[0075] In this embodiment, the boundary points in the target boundary point set are arranged in the order of the vehicle's driving direction, each boundary point corresponds to a serial number, and the boundary points in the target boundary point set are arranged in the order of the serial numbers.
[0076] As an example, let a boundary point be Curb_x, and the previous boundary point be Curb_x-1. The first relative distance corresponding to Curb_x is D1, the second relative distance corresponding to Curb_x-1 is D2, and the first preset length is 0.05m. Then, when D1<D2, and |D1-D2|≥0.05m, Curb_x is determined to be the first close class boundary point. Setting the preset length can eliminate the errors that occur when collecting the target boundary point set and reduce the risk of misidentification.
[0077] Here, the variable count_for_small is used to represent the number of points that are first close to the class boundary.
[0078] Step 10412: If the first relative distance corresponding to the boundary point is smaller than the third relative distance corresponding to the first boundary point in the target boundary point set, and the absolute value of the difference between the first relative distance and the third relative distance is greater than or equal to the second preset length, the boundary point is determined to be a second close class boundary point.
[0079] The second preset length can be set according to actual needs. Continuing the above example, assuming that the second preset length is also 0.05m, the first boundary point in the target boundary point set is Curb_1, and the third relative distance corresponding to Curb_1 is D3, then when D1<D3, |D1-D3|≥0.05m, Curb_x is determined to be the second closest class boundary point.
[0080] Here, the variable count_for_small_ComparedWithFirst is used to represent the number of points that are second closest to the class boundary.
[0081] Step 10413: If the boundary point is a first close class boundary point and / or a second close class boundary point, determine that the distance change trend is a close trend.
[0082] Optionally, in order to make the judgment of the approach trend more accurate, when the boundary point is both a first approach class boundary point and a second approach class boundary point, the distance change trend corresponding to the boundary point can be determined as an approach trend.
[0083] Step 10414: If the first relative distance corresponding to the boundary point is greater than the second relative distance corresponding to the previous boundary point of the boundary point, and the absolute value of the difference between the first relative distance and the second relative distance is greater than or equal to the third preset length, determine that the boundary point is a first away class boundary point.
[0084] The third preset length can be set according to actual needs. Continuing with the above example, when D1>D2, and |D1-D2|≥0.05m, Curb_x is determined to be the first far-from-class boundary point.
[0085] Here, the variable count_for_large is used to represent the number of points that are farthest from the class boundary.
[0086] Step 10415, if the first relative distance corresponding to the boundary point is greater than the third relative distance corresponding to the first boundary point in the target boundary point set, and the absolute value of the difference between the first relative distance and the third relative distance is greater than or equal to the fourth preset length, determine that the boundary point is a second far-class boundary point.
[0087] The fourth preset length can be set according to actual needs. Continuing with the above example, when D1>D3, and |D1-D3|≥0.05m, Curb_x is determined to be the second farthest class boundary point.
[0088] Here, the variable count_for_large_ComparedWithFirst is used to represent the number of points that are second farthest from the class boundary.
[0089] Step 10416: If the boundary point is a first far-away class boundary point and / or a second far-away class boundary point, determine that the distance change trend is a far-away trend.
[0090] Optionally, in order to make the determination of the away trend more accurate, when the boundary point is both a first away class boundary point and a second away class boundary point, the distance change trend corresponding to the boundary point can be determined as the away trend.
[0091] This embodiment can more accurately represent the type of distance change trend of each boundary point by comparing the relative distance corresponding to a boundary point with the relative distances corresponding to the previous boundary point and the first boundary point, so that the distance change trend can be judged with higher accuracy according to the type, which helps to further improve the recognition accuracy of the road merging scene.
[0092] In some optional implementations of this embodiment, step 1042 may be performed as follows:
[0093] If the number of points close to the class boundary and the number of points far from the class boundary meet at least one of the following conditions, it is determined that the number of points close to the class boundary and the number of points far from the class boundary meet the quantity condition:
[0094] Condition 1: the number of the first points close to the class boundary is greater than or equal to a first preset number, and the number of the second points close to the class boundary is greater than or equal to a second preset number.
[0095] Assuming that the first preset number and the second preset number are 5, according to the variables in the above embodiment, when count_for_small and count_for_small_ComparedWithFirst are both greater than 5, it is determined that condition 1 is met. Condition 1 Setting the first preset number and the second preset number can prevent the situation where the number of boundary points that meet the trend approaching is too small and causes misjudgment.
[0096] Condition 2: The ratio of the number of boundary points of the first close class to the total number of boundary points in the target boundary point set is greater than or equal to a preset ratio.
[0097] For example, if the preset ratio is 20%, then according to the variables in the above embodiment, if count_for_small>20% of the total number of boundary points in the target boundary point set, it is determined that condition 2 is met. The purpose of this condition is to ensure that there are enough points with a close trend in the target boundary point set to improve the judgment accuracy.
[0098] Condition three: the number of points close to the class boundary is greater than the number of points far from the class boundary.
[0099] According to the variables in the above embodiment, when (count_for_small+count_for_small_ComparedWithFirst)>(count_for_large+count_for_large_ComparedWithFirst), it is determined that condition 3 is met. The purpose of this condition is to make more points in the target boundary point set meet the requirements of being close to the lane rather than far away from the lane, thereby improving the judgment accuracy.
[0100] The above conditions one, two and three can be combined arbitrarily to determine whether the target boundary line meets the road merging condition. Optionally, in order to improve the judgment accuracy, when all three conditions are met, it is judged whether the target boundary line meets the road merging condition.
[0101] This embodiment sets three conditions to determine whether the road merging conditions are met, and can comprehensively judge the road merging scene from more dimensions, thereby improving the accuracy of road merging scene judgment.
[0102] In some optional implementations of this embodiment, the above condition three includes: the number of the first points close to the class boundary is greater than the number of the first points far from the class boundary, and the number of the second points close to the class boundary is greater than the number of the second points far from the class boundary.
[0103] According to the variables in the above embodiment, when count_for_small>count_for_large, and count_for_small_ComparedWithFirst>count_for_large_ComparedWithFirst, it is determined that condition three is satisfied.
[0104] The third condition can make the boundary points that meet the approaching trend exceed the boundary points that meet the moving away trend in two dimensions, so that the boundary points that meet the approaching trend are more consistent with the actual scene, further improving the accuracy of identifying the road merging scene.
[0105] Figure 6 A schematic diagram of a device for identifying a road merging scene provided in an embodiment of the present application. Specifically comprising:
[0106] An acquisition module 601 is used to acquire road sensing data collected by sensors on the vehicle about the road the vehicle is traveling on;
[0107] A first determination module 602 is used to determine a target boundary point set on a target boundary line of the road based on the road sensing data;
[0108] A second determination module 603 is used to determine the relative distance between the boundary point in the target boundary point set and the lane where the vehicle is located;
[0109] The third determination module 604 is used to determine whether the target boundary line meets the road merging condition according to the relative distance;
[0110] The fourth determination module 605 is used to determine that the scene where the vehicle is currently located is a road merging scene if the road merging condition is met.
[0111] In one possible implementation, the first determination module includes: a first determination unit, used to determine a first initial target boundary point set corresponding to a target boundary line of the road from the sensing data; a second determination unit, used to determine outlier points in the first initial target boundary point set based on the lateral coordinates of the boundary points in the first initial target boundary point set, and delete the outlier points from the first initial target boundary point set to obtain a second initial target boundary point set; an extraction unit, used to extract boundary points from the second initial target boundary point set based on a preset longitudinal distance interval, and determine each extracted boundary point as a target boundary point set.
[0112] In one possible implementation, the second determination module includes: a third determination unit, used to determine the center line of the lane where the vehicle is located; and a fourth determination unit, used to determine the distance between the boundary point in the target boundary point set and the center line as the relative distance between the boundary point and the lane where the vehicle is located.
[0113] In one possible embodiment, the third determination module includes: a fifth determination unit, which is used to determine, for each boundary point in the target boundary point set, a distance change trend between the boundary point and the lane where the vehicle is located based on the relative distance between the boundary point and the lane where the vehicle is located; if the distance change trend is a closing trend, the boundary point is determined to be a close class boundary point; if the distance change trend is a moving away trend, the boundary point is determined to be a moving away class boundary point; a sixth determination unit, which is used to determine that the target boundary line meets the road merging condition if the number of close class boundary points and the number of moving away class boundary points meet a preset quantity condition.
[0114] In one possible implementation, the fifth determination unit includes: a first determination subunit, which is used to determine that the boundary point is a first close class boundary point if the first relative distance corresponding to the boundary point is less than the second relative distance corresponding to the previous boundary point of the boundary point, and the absolute value of the difference between the first relative distance and the second relative distance is greater than or equal to the first preset length; a second determination subunit, which is used to determine that the boundary point is a second close class boundary point if the first relative distance corresponding to the boundary point is less than the third relative distance corresponding to the first boundary point in the target boundary point set, and the absolute value of the difference between the first relative distance and the third relative distance is greater than or equal to the second preset length; a third determination subunit, which is used to determine the distance if the boundary point is a first close class boundary point and / or a second close class boundary point. The distance change trend is a approaching trend; a fourth determining subunit is used to determine that the boundary point is a first far-away class boundary point if the first relative distance corresponding to the boundary point is greater than the second relative distance corresponding to the previous boundary point of the boundary point, and the absolute value of the difference between the first relative distance and the second relative distance is greater than or equal to the third preset length; a fifth determining subunit is used to determine that the boundary point is a second far-away class boundary point if the first relative distance corresponding to the boundary point is greater than the third relative distance corresponding to the first boundary point in the target boundary point set, and the absolute value of the difference between the first relative distance and the third relative distance is greater than or equal to the fourth preset length; a sixth determining subunit is used to determine that the distance change trend is a far-away trend if the boundary point is a first far-away class boundary point and / or a second far-away class boundary point.
[0115] In one possible embodiment, the sixth determination unit is further used to: if the number of points close to the class boundary and the number of points far from the class boundary meet at least one of the following conditions, determine that the number of points close to the class boundary and the number of points far from the class boundary meet the quantity condition: Condition one, the first number of points close to the class boundary is greater than or equal to the first preset number, and the second number of points close to the class boundary is greater than or equal to the second preset number; Condition two, the ratio of the first number of points close to the class boundary to the total number of boundary points in the target boundary point set is greater than or equal to the preset ratio; Condition three, the number of points close to the class boundary is greater than the number of points far from the class boundary.
[0116] In a possible implementation, condition three includes: the number of the first points close to the class boundary is greater than the number of the first points far from the class boundary, and the number of the second points close to the class boundary is greater than the number of the second points far from the class boundary.
[0117] The road merging scene recognition device provided in this embodiment can be as follows: Figure 6 The road merging scene recognition device shown in can execute all steps of the above road merging scene recognition methods, thereby achieving the technical effects of the above road merging scene recognition methods. Please refer to the above related description for details. For the sake of brevity, it will not be repeated here.
[0118] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application, Figure 7 The electronic device 700 shown includes: at least one processor 701, a memory 702, at least one network interface 704 and other user interfaces 703. The various components in the electronic device 700 are coupled together via a bus system 705. It is understood that the bus system 705 is used to achieve connection and communication between these components. In addition to the data bus, the bus system 705 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, the bus system 705 is not described in detail. Figure 7 Various buses are labeled as bus system 705 .
[0119] The user interface 703 may include a display, a keyboard, or a pointing device (eg, a mouse, a trackball, a touch pad, or a touch screen).
[0120] It can be understood that the memory 702 in the embodiment of the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct RAM bus random access memory (DRRAM). The memory 702 described herein is intended to include, but is not limited to, these and any other suitable types of memory.
[0121] In some implementations, the memory 702 stores the following elements, executable units or data structures, or a subset thereof, or an extended set thereof: an operating system 7021 and an application program 7022 .
[0122] The operating system 7021 includes various system programs, such as a framework layer, a core library layer, a driver layer, etc., which are used to implement various basic services and process hardware-based tasks. The application 7022 includes various application programs, such as a media player (Media Player), a browser (Browser), etc., which are used to implement various application services. The program for implementing the method of the embodiment of the present application can be included in the application 7022.
[0123] In this embodiment, by calling the program or instruction stored in the memory 702, specifically, the program or instruction stored in the application 7022, the processor 701 is used to execute the method steps provided by each method embodiment, for example, including:
[0124] Acquire road sensing data collected by sensors on the vehicle about the road the vehicle is traveling on; determine a target boundary point set on a target boundary line of the road based on the road sensing data; determine the relative distance between the boundary points in the target boundary point set and the lane where the vehicle is located; determine whether the target boundary line meets the road merging conditions based on the relative distance; if the road merging conditions are met, determine that the scene the vehicle is currently in is a road merging scene.
[0125] The method disclosed in the above embodiment of the present application can be applied to the processor 701, or implemented by the processor 701. The processor 701 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit in the processor 701 or the instruction in the form of software. The above processor 701 can be a general processor, a digital signal processor (Digital Signal Processor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiment of the present application can be directly embodied as a hardware decoding processor to execute, or the hardware and software units in the decoding processor can be executed. The software unit can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 702, and the processor 701 reads the information in the memory 702 and completes the steps of the above method in combination with its hardware.
[0126] It is understood that the embodiments described herein may be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit may be implemented in one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPDevice, DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), general purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the above functions of the present application, or a combination thereof.
[0127] For software implementation, the technology described above in this article can be implemented by a unit that performs the functions described above in this article. The software code can be stored in a memory and executed by a processor. The memory can be implemented in the processor or outside the processor.
[0128] The electronic device provided in this embodiment may be Figure 7 The electronic device shown in can execute all steps of the above-mentioned method for identifying each road merging scene, thereby achieving the technical effect of the above-mentioned method for identifying each road merging scene. Please refer to the above related description for details. For the sake of brevity, it will not be repeated here.
[0129] The embodiment of the present application also provides a storage medium (computer-readable storage medium). The storage medium here stores one or more programs. The storage medium may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a read-only memory, a flash memory, a hard disk or a solid-state drive; the memory may also include a combination of the above-mentioned types of memory.
[0130] When one or more programs in the storage medium can be executed by one or more processors, the method for identifying the road merging scene executed on the electronic device side can be implemented.
[0131] The processor is used to execute the program stored in the memory to implement the following steps of the road merging scene recognition method performed on the electronic device side:
[0132] Acquire road sensing data collected by sensors on the vehicle about the road the vehicle is traveling on; determine a target boundary point set on a target boundary line of the road based on the road sensing data; determine the relative distance between the boundary points in the target boundary point set and the lane where the vehicle is located; determine whether the target boundary line meets the road merging conditions based on the relative distance; if the road merging conditions are met, determine that the scene the vehicle is currently in is a road merging scene.
[0133] The professionals should also be further aware that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0134] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
[0135] It should be understood that the terms used herein are only for the purpose of describing specific example embodiments and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used herein may also be meant to include plural forms. The terms "include", "comprise", "contain", and "have" are inclusive, and therefore specify the existence of stated features, steps, operations, elements and / or parts, but do not exclude the existence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof. The method steps, processes, and operations described herein are not interpreted as necessarily requiring them to be performed in the specific order described or illustrated, unless the execution order is clearly indicated. It should also be understood that additional or alternative steps may be used.
[0136] The above description is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest range consistent with the principles and novel features applied for herein.
Claims
1. A method for identifying a road merging scene, characterized in that: The method comprises: Acquire road sensing data collected by sensors on the vehicle about the road on which the vehicle is traveling; Determining a target boundary point set on a target boundary line of the road based on the road sensing data; Determining a relative distance between a boundary point in the target boundary point set and a lane where the vehicle is located; Determining whether the target boundary line meets the road merging condition according to the relative distance; If the road merging condition is met, it is determined that the scene the vehicle is currently in is a road merging scene.
2. The method according to claim 1, characterized in that: The step of determining a target boundary point set of the road based on the road sensing data includes: Determining a first initial target boundary point set corresponding to a target boundary line of the road from the sensing data; Determine outliers in the first initial target boundary point set based on the horizontal coordinates of the boundary points in the first initial target boundary point set, and delete the outliers from the first initial target boundary point set to obtain a second initial target boundary point set; Based on a preset longitudinal distance interval, boundary points are extracted from the second initial target boundary point set, and each extracted boundary point is determined as the target boundary point set.
3. The method according to claim 1, characterized in that The determining of the relative distance between the boundary point in the target boundary point set and the lane where the vehicle is located includes: determining a center line of a lane in which the vehicle is located; The distance between the boundary point in the target boundary point set and the center line is determined as the relative distance between the boundary point and the lane where the vehicle is located.
4. The method according to claim 1, characterized in that: The determining, based on the relative distance, whether the target boundary line meets the road merging condition includes: For each boundary point in the target boundary point set, based on the relative distance between the boundary point and the lane where the vehicle is located, determine the distance change trend between the boundary point and the lane where the vehicle is located; if the distance change trend is a close trend, determine the boundary point as a close class boundary point; if the distance change trend is a far away trend, determine the boundary point as a far away class boundary point; If the number of the points close to the class boundary and the number of the points far from the class boundary meet the preset quantity conditions, it is determined that the target boundary line meets the road merging condition.
5. The method according to claim 4, characterized in that The determining, based on the relative distance corresponding to the boundary point, a distance change trend between the boundary point and the lane where the vehicle is located, includes: If the first relative distance corresponding to the boundary point is smaller than the second relative distance corresponding to the previous boundary point of the boundary point, and the absolute value of the difference between the first relative distance and the second relative distance is greater than or equal to a first preset length, the boundary point is determined to be a first close-type boundary point; If the first relative distance corresponding to the boundary point is less than the third relative distance corresponding to the first boundary point in the target boundary point set, and the absolute value of the difference between the first relative distance and the third relative distance is greater than or equal to a second preset length, the boundary point is determined to be a second close class boundary point; If the boundary point is a first close class boundary point and / or a second close class boundary point, determining the distance change trend as a close trend; If the first relative distance corresponding to the boundary point is greater than the second relative distance corresponding to the previous boundary point of the boundary point, and the absolute value of the difference between the first relative distance and the second relative distance is greater than or equal to a third preset length, the boundary point is determined to be a first away boundary point; If the first relative distance corresponding to the boundary point is greater than the third relative distance corresponding to the first boundary point in the target boundary point set, and the absolute value of the difference between the first relative distance and the third relative distance is greater than or equal to a fourth preset length, the boundary point is determined to be a second far-away boundary point; If the boundary point is a first far-away class boundary point and / or a second far-away class boundary point, it is determined that the distance change trend is a far-away trend.
6. The method according to claim 5, characterized in that If the number of the points close to the class boundary and the number of the points far from the class boundary meet the preset number condition, determining that the target boundary line meets the road merging condition includes: If the number of points close to the class boundary and the number of points far from the class boundary meet at least one of the following conditions, it is determined that the number of points close to the class boundary and the number of points far from the class boundary meet the quantity condition: Condition 1: the number of the first points close to the class boundary is greater than or equal to a first preset number, and the number of the second points close to the class boundary is greater than or equal to a second preset number; Condition 2: the ratio of the number of the first close-type boundary points to the total number of boundary points in the target boundary point set is greater than or equal to a preset ratio; Condition three: the number of points close to the class boundary is greater than the number of points far from the class boundary.
7. The method according to claim 6, characterized in that The third condition includes: the number of the first points close to the class boundary is greater than the number of the first points far from the class boundary, and the number of the second points close to the class boundary is greater than the number of the second points far from the class boundary.
8. A device for identifying a road merging scene, characterized in that: The device comprises: An acquisition module, used to acquire road sensing data collected by a sensor on a vehicle from the road on which the vehicle is traveling; A first determination module, configured to determine a target boundary point set on a target boundary line of the road based on the road sensing data; A second determination module is used to determine the relative distance between the boundary point in the target boundary point set and the lane where the vehicle is located; A third determination module, used to determine whether the target boundary line meets the road merging condition according to the relative distance; The fourth determination module is used to determine that the scene where the vehicle is currently located is a road merging scene if the road merging condition is met.
9. An electronic device, characterized in that: include: Memory for storing computer programs; A processor is used to execute the computer program stored in the memory, and when the computer program is executed, the method for identifying the road merging scene described in any one of claims 1 to 7 above is implemented.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for identifying a road merging scene as described in any one of claims 1 to 7 is implemented.