Crossing trafficability determination method, device, equipment, medium and program product

Abstract

The invention relates to a method, a device, equipment, a medium and a program product for determining the trafficability of an intersection, and the method comprises the steps: carrying out the recognition processing of an obtained intersection environment image, obtaining first signal lamp data, signboard data and traffic marking data, and carrying out the recognition processing of the first signal lamp data, the signboard data and the traffic marking data according to the vehicle driving direction, the vehicle position and the signboard data; and screening the first signal lamp data and adding the number of control lanes to obtain second signal lamp data. Determining a target signal lamp matched with the lane where the vehicle is located according to the vehicle position, the traffic marking data and the second signal lamp data, and determining whether the current intersection can pass or not according to the lamp color of the target signal lamp. Whether the current intersection can pass or not is determined by determining the light color of the target signal light matched with the lane where the vehicle is located, the method can be implemented at various intersections with different types of traffic signal lights, and generalization of intersection passing decisions is improved.

Description

Technical Field

[0001] The present invention relates to the field of vehicle technology, and in particular to a method, device, equipment, medium and program product for determining the passability of an intersection. Background Art

[0002] With the continuous development of technology, assisted driving and autonomous driving have emerged, improving the driver's driving experience and enhancing vehicle safety. When a vehicle reaches an intersection, it needs to determine whether the intersection is passable at the moment in order to decide whether to continue driving.

[0003] In the prior art, the method for determining the passability of an intersection is usually only for intersections with circular traffic lights. When the light color is recognized as green, it is determined that the intersection is passable at the current moment; when the light color is recognized as red, it is determined that the intersection is not passable at the current moment.

[0004] In summary, existing methods for determining the passability of intersections can only be used at intersections with circular traffic lights, resulting in low generalization of intersection traffic decisions. Summary of the Invention

[0005] One of the purposes of the present invention is to provide a method for determining the passability of an intersection to solve the problem that the existing method for determining the passability of an intersection can only be used at intersections with circular traffic lights, resulting in low generalization of intersection traffic decisions; the second purpose is to provide a device for determining the passability of an intersection; the third purpose is to provide an electronic device; the fourth purpose is to provide a readable storage medium; and the fifth purpose is to provide a computer program product.

[0006] In order to achieve the above object, the technical solution adopted by the present invention is as follows:

[0007] In a first aspect, the present invention provides a method for determining the passability of an intersection, comprising:

[0008] Recognize and process the acquired intersection environment image to obtain first signal light data, signboard data, and traffic marking data;

[0009] According to the acquired vehicle driving direction and vehicle position, as well as the signboard data, the first signal light data is filtered and the number of controlled lanes is added to obtain second signal light data;

[0010] Determining a target signal light that matches the lane where the vehicle is located based on the vehicle position, the traffic marking data, and the second signal light data;

[0011] Determine whether the current intersection is passable based on the light color of the target traffic light.

[0012] Furthermore, the first signal light data is filtered and the number of controlled lanes is added based on the acquired vehicle driving direction and vehicle position, as well as the signboard data, to obtain the second signal light data, including:

[0013] filtering the first signal light data according to the vehicle's driving direction and the vehicle's position to obtain third signal light data;

[0014] According to the signboard data, the third signal light data is processed by adding the number of controlled lanes to obtain the second signal light data.

[0015] Furthermore, the first signal light data includes signal light data of at least one first signal light, and the signal light data includes light color, position, direction and signal light type;

[0016] The filtering of the first signal light data according to the vehicle driving direction and the vehicle position to obtain third signal light data includes:

[0017] Determine a screening area based on the vehicle position and the preset screening position calculation information;

[0018] For each first signal light, if the position of the first signal light does not belong to the screening area, and the angle between the orientation of the first signal light and the driving direction of the vehicle does not belong to the preset screening angle range, the first signal light is used as the second signal light;

[0019] The third signal light data is generated based on the signal light data of each second signal light.

[0020] Furthermore, the signboard data includes the location and content of at least one signboard, and the third signal light data includes signal light data of at least one second signal light, and the signal light data includes light color, location, direction, and signal light type;

[0021] The step of adding a controlled lane quantity to the third signal light data according to the signboard data to obtain the second signal light data includes:

[0022] For each second signal light and each signboard, if the distance between the position of the second signal light and the position of the signboard is less than a preset distance threshold, the second signal light and the signboard are considered as a matching pair;

[0023] For each matching pair, if the content of the sign in the matching pair includes the preset single lane control content, adding a first preset number to the signal light data of the second signal light in the matching pair, where the first preset number is 1;

[0024] For each two second signal lights whose signal light type falls within the preset arrow type range, if the distance between the positions of the two second signal lights falls within the preset lane distance range, adding the first preset number to the signal light data of the two second signal lights respectively;

[0025] For each second signal light, if the signal light data of the second signal light does not include the first preset number, adding a second preset number to the signal light data of the second signal light, where the second preset number is greater than 1;

[0026] The second signal light data is generated according to the signal light data of each second signal light after the number of controlled lanes is added.

[0027] Furthermore, the second signal light data includes signal light data of at least one second signal light, and the signal light data includes light color, position, direction, signal light type and number of controlled lanes;

[0028] Determining a target signal light that matches a lane where the vehicle is located according to the vehicle position, the traffic marking data, and the second signal light data includes:

[0029] Determining a lane traffic type of a lane where the vehicle is located based on the traffic marking data and the vehicle position;

[0030] Determining the target signal light type corresponding to the lane traffic type according to a preset correspondence between traffic types and signal light types;

[0031] For each second signal light, if the signal light type of the second signal light is the target signal light type, use the second signal light as the third signal light;

[0032] According to the number of lanes controlled by all third signal lights, a target signal light matching the lane where the vehicle is located is determined.

[0033] Furthermore, the traffic marking data includes the positions of at least two lane lines and the position and guidance type of at least one guide arrow;

[0034] The determining, based on the traffic line data and the vehicle position, the lane traffic type of the lane in which the vehicle is located, includes:

[0035] Determining a lane centerline position of the lane where the vehicle is located based on the vehicle position and the position of each lane line;

[0036] For each guide arrow, if the distance between the position of the guide arrow and the center line of the lane is less than a preset guide distance, the guide type of the guide arrow is used as the lane passage type.

[0037] Furthermore, determining the target signal light that matches the lane where the vehicle is located based on the number of lanes controlled by all third signal lights includes:

[0038] If the number of lanes controlled by all third signal lights is equal to 1, or the number of lanes controlled by all third signal lights is greater than 1, the third signal light closest to the position of the vehicle among all third signal lights is used as the target signal light;

[0039] If there is a signal light with 1 controlled lane number among all third signal lights, and there is a signal light with 1 controlled lane number, then the third signal light with 1 controlled lane number is used as the fourth signal light data;

[0040] The fourth signal light closest to the vehicle position among all the fourth signal lights is used as the target signal light.

[0041] Furthermore, before filtering and adding the number of controlled lanes to the first signal light data based on the acquired vehicle driving direction and vehicle position, and the signboard data, and obtaining the second signal light data, the method further includes:

[0042] Get historical traffic light data;

[0043] updating the first signal light data according to the historical signal light data to obtain updated first signal light color data;

[0044] The method of filtering and marking the first signal light data based on the acquired vehicle driving direction and vehicle position, as well as the signboard data, to obtain the second signal light data includes:

[0045] According to the acquired vehicle driving direction and vehicle position, as well as the signboard data, the updated first signal light data is filtered and the number of controlled lanes is added to obtain the second signal light data.

[0046] In a second aspect, the present invention provides a device for determining the passability of an intersection, comprising:

[0047] Processing module for:

[0048] Recognize and process the acquired intersection environment image to obtain first signal light data, signboard data, and traffic marking data;

[0049] According to the acquired vehicle driving direction and vehicle position, as well as the signboard data, the first signal light data is filtered and the number of controlled lanes is added to obtain second signal light data;

[0050] Determining a target signal light that matches the lane where the vehicle is located based on the vehicle position, the traffic marking data, and the second signal light data;

[0051] The decision module is used to determine whether the current intersection is passable based on the light color of the target traffic light.

[0052] In a third aspect, the present invention provides an electronic device, comprising:

[0053] Processor, memory, communication interface;

[0054] The memory is used to store executable instructions of the processor;

[0055] The processor is configured to execute the method for determining the passability of an intersection as described in any one of the first aspects by executing the executable instructions.

[0056] In a fourth aspect, the present invention provides a readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method for determining the passability of an intersection as described in any one of the first aspects.

[0057] In a fifth aspect, the present invention provides a computer program product, comprising a computer program, which, when executed by a processor, is used to implement the method for determining the passability of an intersection as described in any one of the first aspects.

[0058] Beneficial effects of the present invention:

[0059] (1) This application identifies and processes the acquired intersection environment image to obtain first signal light data, signboard data, and traffic marking data. Then, based on the vehicle's driving direction, vehicle position, and signboard data, the first signal light data is filtered and the number of controlled lanes is added to obtain second signal light data. Then, based on the vehicle's position, traffic marking data, and second signal light data, the target signal light that matches the lane where the vehicle is located is determined, and then based on the color of the target signal light, whether the current intersection is passable is determined. By determining the color of the target signal light that matches the lane where the vehicle is located, whether the current intersection is passable is determined. This can be implemented at multiple intersections with different types of traffic lights, thereby improving the generalization of intersection traffic decisions.

[0060] (2) This application determines the target signal light that matches the lane where the vehicle is located through the first signal light data, signboard data and traffic marking data, which can improve the matching accuracy and thus improve the accuracy of the determined intersection passability. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] 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.

[0062] Figure 1 A schematic diagram of an application scenario of the method for determining the passability of an intersection provided in this application;

[0063] Figure 2a A flowchart of a first embodiment of a method for determining the passability of an intersection provided in this application;

[0064] Figure 2b A schematic diagram of signal light screening provided for this application;

[0065] Figure 2c A schematic diagram of the process for determining the passability of an intersection provided for this application;

[0066] Figure 3 A flowchart of Embodiment 2 of the method for determining the passability of an intersection provided in this application;

[0067] Figure 4 A flowchart of Embodiment 3 of the method for determining the passability of an intersection provided in this application;

[0068] Figure 5 A flowchart of a fourth embodiment of a method for determining the passability of an intersection provided in this application;

[0069] Figure 6 A schematic diagram of the structure of an embodiment of a device for determining the passability of an intersection provided by this application;

[0070] Figure 7 This is a schematic diagram of the structure of an electronic device provided in this application.

[0071] The above drawings illustrate specific embodiments of the present application, which will be described in more detail below. These drawings and the textual description are not intended to limit the scope of the present application in any way, but rather to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0072] The following describes the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art will readily appreciate the other advantages and benefits of the present invention from the disclosure herein. The present invention may also be implemented or applied through various other specific embodiments, and the various details in this specification may be modified or altered based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are intended only to illustrate the present invention and are not intended to limit the scope of protection of the present invention.

[0073] It should be noted that the illustrations provided in the following embodiments are merely schematic illustrations of the basic concept of the present invention. Therefore, the illustrations only show components related to the present invention and are not drawn according to the number, shape, and size of components in actual implementation. In actual implementation, the type, quantity, and proportion of each component may be changed arbitrarily, and the component layout may also be more complex.

[0074] The emergence of assisted driving and autonomous driving technologies not only improves the driver's driving experience but also enhances vehicle safety. When a vehicle reaches an intersection with assisted driving or autonomous driving enabled, it needs to determine whether the intersection is passable at the moment in order to decide whether to continue driving.

[0075] In the prior art, the method for determining the passability of an intersection is usually only for intersections with circular traffic lights. When the light color is recognized as green, it is determined that the intersection is passable at the current moment; when the light color is recognized as red, it is determined that the intersection is not passable at the current moment.

[0076] Existing methods for determining the passability of intersections can only be used at intersections with circular traffic lights and cannot be applied to other intersections, such as intersections with traffic lights with arrows, resulting in low generalization of intersection traffic decisions.

[0077] To address the problems existing in the prior art, the inventors, while researching methods for determining intersection passability, discovered that, in order to improve the generalizability of such methods and to determine whether a vehicle is passable at both intersections with only circular traffic lights and those with arrow traffic lights, recognition processing can be performed based on the intersection environment image to obtain first traffic light data, signboard data, and traffic marking data. Furthermore, based on the vehicle's direction of travel and position, as well as the signboard data, the first traffic light data is filtered and processed to include the number of controlled lanes, thereby obtaining second traffic light data. Based on the vehicle's position, traffic marking data, and second traffic light data, a target traffic light matching the vehicle's lane is determined. Finally, the intersection's passability is determined based on the color of the target traffic light. By matching lanes with traffic lights and then determining whether a vehicle is passable based on the color of the matching traffic light, the generalizability of intersection traffic decision making is improved. Based on the aforementioned inventive concepts, the intersection passability determination scheme disclosed in this application was designed.

[0078] The execution subject of the method for determining the passability of an intersection in this application can be an electronic control unit (ECU) in a vehicle, or it can be an on-board terminal, server and other equipment. This application does not limit it and will be explained below using ECU as an example.

[0079] For example, Figure 1This is a schematic diagram of an application scenario of the method for determining the passability of an intersection provided in this application, such as Figure 1 As shown, in this application scenario, the autonomous driving vehicle is driving in the left turn lane. There are two traffic lights and a signboard opposite the intersection. The signal light type of the first traffic light is a left turn signal light, and the signal light type of the second traffic light is a round light.

[0080] An autonomous driving vehicle will capture images while driving. When it reaches an intersection, the ECU will identify and process the captured intersection environment images to obtain the first signal light data, signboard data, and traffic marking data.

[0081] Then, based on the acquired vehicle driving direction and vehicle position, as well as the signboard data, the first signal light data is filtered and the number of controlled lanes is added to obtain the second signal light data.

[0082] Based on the vehicle's position, traffic markings, and the second signal light, the ECU determines the target signal light that matches the vehicle's lane. The target signal light is the first signal light. The first signal light is green, indicating that the intersection is passable, and the ECU controls the vehicle to turn left.

[0083] It should be noted that Figure 1 This is only a schematic diagram of an application scenario provided by the embodiment of the present application. Figure 1 The actual form of the various devices included in the Figure 1 The interaction mode between devices is limited, and in the specific application of the solution, it can be set according to actual needs.

[0084] The technical solution of the present application is described in detail below through specific embodiments. It should be noted that the following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0085] Figure 2a This is a flow chart of the first embodiment of the method for determining the passability of an intersection provided by this application. This embodiment of the application describes how the ECU determines the first signal light data, signboard data and traffic marking data based on the intersection environment image, determines the target signal light that matches the lane where the vehicle is located, and then determines whether the current intersection is passable based on the light color of the target signal light. The method in this embodiment can be implemented by software, hardware, or a combination of software and hardware. Figure 2a As shown, the method for determining the passability of the intersection specifically includes the following steps:

[0086] S201: performing recognition processing on the acquired intersection environment image to obtain first signal light data, signboard data, and traffic marking data.

[0087] In this step, when a vehicle approaches an intersection, it captures an image of the intersection. To determine whether the intersection is passable, the ECU uses a trained deep learning model to identify and process the captured image, generating data for the first signal light, signboard, and traffic markings. This deep learning model is called an object detection model.

[0088] The first signal light data includes signal light data of at least one first signal light, and the signal light data includes light color, position, direction, and signal light type. The signal light type can be a round light, a left turn signal light, a straight signal light, a right turn signal light, a U-turn signal light, etc.

[0089] The sign data includes the location and content of at least one sign.

[0090] Traffic marking data includes the positions of at least two lane lines and the position and type of at least one guide arrow. The guide type can be straight ahead, left turn, right turn, U-turn, straight ahead plus left turn, straight ahead plus right turn, left turn plus right turn, etc.

[0091] It should be noted that the intersection environment image includes the vehicle front image and the vehicle surround view image.

[0092] It should be noted that if the first signal light data or traffic line marking data is not detected and identified, a manual takeover prompt message is output.

[0093] S202: Based on the acquired vehicle driving direction and vehicle position, as well as the signboard data, the first signal light data is filtered and the number of controlled lanes is added to obtain second signal light data.

[0094] In this step, after the ECU obtains the first signal light data, signboard data, and traffic marking data, it filters out some of the first signal lights, as they are not intended for vehicles on the road where the vehicle is located, to improve the accuracy of determining drivability. Furthermore, to improve the accuracy of matching lanes with signal lights, it is necessary to add more controlled lanes.

[0095] Specifically, the first signal light data is filtered according to the vehicle's driving direction and vehicle position to obtain the third signal light data.

[0096] The screening area is determined based on the vehicle position and the preset screening position calculation information.

[0097] It should be noted that the preset screening position calculation information includes at least one screening data, each of which includes a screening angle, a screening distance, and a screening range size data. A screening area can be determined based on each screening data.

[0098] The screening center can be determined based on the vehicle's position, screening angle, and screening distance. The distance between the screening center and the vehicle's position is the screening distance, and the straight line formed by the vehicle's position, the screening center, and the vehicle's travel direction is the screening angle. The screening area is then determined based on the screening range size data, with the screening center as the center. For example, if the screening range size data is a preset radius and a preset height, a circle is determined based on the preset radius with the screening center as the center, and then a cylindrical area is generated based on the preset height to obtain the screening area. If the screening range size data is a preset length, preset width, and preset height, a rectangle is determined based on the preset length and preset width with the screening center as the center, and then a cuboid area is generated based on the preset height to obtain the screening area.

[0099] After obtaining the screening area, for each first signal light, if its location does not fall within the screening area and the angle between its orientation and the vehicle's travel direction does not fall within the preset screening angle range, the first signal light is used as the second signal light. First signal lights whose location falls within the screening range and whose orientation falls within the preset screening angle range with the vehicle's travel direction are not first signal lights that control vehicles on the road and need to be eliminated.

[0100] It should be noted that, when there are multiple screening areas, the position of the first signal light not belonging to the screening area means that the position of the first signal light does not belong to the union of all the screening areas.

[0101] It should be noted that the preset screening angle range can be 135 degrees-180 degrees, 145 degrees-180 degrees, 150 degrees-180 degrees, etc. The embodiment of the present application does not limit the preset screening angle range and can be determined according to actual conditions.

[0102] The third signal light data is generated based on the signal light data of each second signal light. The third signal light data includes the signal light data of each second signal light.

[0103] For example, Figure 2b The signal light screening diagram provided for this application is as follows: Figure 2b As shown, there are five roads ahead of the vehicle: Road A, Road B, Road C, Road D, and Road E. The angles between the traffic lights on Roads A, D, and E and the vehicle's travel direction do not fall within the preset screening angle range, so the traffic lights on Roads A, D, and E are eliminated. The angles between the traffic lights on Roads B and C and the vehicle's travel direction fall within the preset screening angle range. The dotted circular line in the figure indicates the screening area, and the traffic light on Road B falls within the screening area and is eliminated. Therefore, the traffic light on Road C is the second traffic light.

[0104] After obtaining the third signal light data, the ECU adds the number of controlled lanes to the third signal light data according to the signboard data to obtain the second signal light data.

[0105] For each second signal light and each signboard, if the distance between the position of the second signal light and the position of the signboard is less than a preset distance threshold, it means that the signboard is a signboard describing the second signal light, and the second signal light and the signboard are regarded as a matching pair.

[0106] It should be noted that the preset distance threshold may be 0.5 meters, 1 meter, 1.5 meters, etc. The embodiment of the present application does not limit the preset distance threshold and may be determined according to actual conditions.

[0107] For each matching pair, if the content of the sign in the matching pair includes the preset single lane control content, a first preset number is added to the signal light data of the second signal light in the matching pair, where the first preset number is 1.

[0108] It should be noted that the preset single lane control content may be: "lane", arrow, etc.

[0109] For every two second signal lights whose signal light type falls within the preset arrow type range, if the distance between the positions of the two second signal lights falls within the preset lane distance range, indicating that the two second signal lights each control one lane, the first preset number is added to the signal light data of the two second signal lights respectively.

[0110] It should be noted that the preset arrow types include left turn signal lights, straight ahead signal lights, right turn signal lights, U-turn signal lights, etc.

[0111] It should be noted that the preset lane distance range can be 3 meters to 4 meters, 3.2 meters to 3.8 meters, 3.4 meters to 3.75 meters, etc. The embodiment of this application does not limit the preset lane distance range and can be determined according to actual conditions.

[0112] For each second signal light, if the signal light data of the second signal light does not include the first preset number, the second preset number is added to the signal light data of the second signal light, and the second preset number is greater than 1. The first preset number and the second preset number are the numbers of controlled lanes.

[0113] The second signal light data is generated based on the signal light data of each second signal light after adding the number of controlled lanes. The second signal light data includes the signal light data of each second signal light, and the signal light data includes light color, position, direction, signal light type and the number of controlled lanes.

[0114] It should be noted that if the intersection environment image is recognized and no signboard data is obtained, there is no need to determine a matching pair.

[0115] S203: Determine a target traffic light that matches the lane where the vehicle is located based on the vehicle position, traffic line marking data, and the second traffic light data.

[0116] In this step, after the ECU obtains the second signal light data, in order to determine which signal light can control the vehicle, it needs to determine the target signal light that matches the lane where the vehicle is located based on the vehicle position, traffic marking data and the second signal light data.

[0117] Specifically, the lane type of the vehicle's lane is determined based on traffic marking data and the vehicle's position. Lane types can include straight ahead, left turn, right turn, U-turn, straight ahead plus left turn, straight ahead plus right turn, left turn plus right turn, etc.

[0118] According to the preset correspondence between the traffic type and the signal light type, the target signal light type corresponding to the lane traffic type is determined.

[0119] For example, the correspondence between traffic types and traffic light types may be: left turn corresponds to a left turn signal light and a round light, straight ahead corresponds to a straight ahead signal light and a round light, right turn corresponds to a right turn signal light, U-turn corresponds to a U-turn signal light, straight ahead plus a left turn corresponds to a round light, straight ahead plus a right turn corresponds to a round light, left turn plus a right turn corresponds to a round light, etc. This embodiment of the application does not limit the correspondence between traffic types and traffic light types, and the correspondence may be determined based on actual circumstances.

[0120] For each second signal light, if the signal light type of the second signal light is the target signal light type, the second signal light is used as the third signal light. Then, based on the number of lanes controlled by all the third signal lights, the target signal light matching the lane where the vehicle is located is determined.

[0121] It should be noted that, if there are multiple target signal light types, the signal light type of the second signal light being the target signal light type means that the signal light type of the second signal light is one of the multiple target signal light types.

[0122] It should be noted that if the signal light type of each second signal light is not the target signal light type, a manual takeover prompt message is output.

[0123] S204: Determine whether the current intersection is passable based on the light color of the target traffic light.

[0124] In this step, after the ECU determines the target traffic light (the target traffic light is the one that controls the vehicle's movement), it retrieves the light color from the target traffic light's signal data and then determines whether the current intersection is passable based on the light color. If the light color is green, the current intersection is passable. If the light color is yellow or red, the current intersection is not passable.

[0125] For example, Figure 2c The flow chart for determining the passability of an intersection provided in this application is as follows: Figure 2c As shown, the intersection environment image is recognized and processed to obtain first signal light data, signboard data, and traffic marking data. The first signal light data is filtered based on the vehicle's direction and position to obtain third signal light data. Based on the signboard data, the third signal light data is processed to add the number of controlled lanes to obtain second signal light data. Based on the vehicle's position, traffic marking data, and the second signal light data, a target signal light matching the vehicle's lane is determined. Based on the color of the target signal light, whether the current intersection is passable is determined.

[0126] The method for determining the passability of an intersection provided in this embodiment recognizes and processes a captured image of the intersection environment to obtain first signal light data, signboard data, and traffic marking data. The first signal light data is then filtered and processed to add the number of controlled lanes based on the vehicle's direction of travel, vehicle position, and signboard data to obtain second signal light data. Furthermore, based on the vehicle's position, traffic marking data, and second signal light data, a target signal light matching the vehicle's lane is determined. Based on the color of the target signal light, whether the current intersection is passable is determined. This determination of the passability of the current intersection by determining the color of the target signal light matching the vehicle's lane can be implemented at a variety of intersections with different types of traffic lights, improving the generalizability of intersection traffic decision-making. Furthermore, by determining the target signal light matching the vehicle's lane based on the first signal light data, signboard data, and traffic marking data, matching accuracy can be improved, thereby improving the accuracy of intersection passability.

[0127] Figure 3 This is a flow chart of the second embodiment of the method for determining the passability of an intersection provided by this application. Based on the above embodiment, this embodiment of the application describes how the ECU determines the lane traffic type of the lane where the vehicle is located based on traffic marking data and vehicle position. Figure 3 As shown, the method for determining the passability of the intersection specifically includes the following steps:

[0128] S301: Determine the centerline position of the lane where the vehicle is located based on the vehicle position and the position of each lane line.

[0129] In this step, in order to determine the lane traffic type of the lane where the vehicle is located, the lane centerline position of the lane where the vehicle is located needs to be determined.

[0130] For each lane line, the distance between the lane line and the vehicle is calculated based on the lane line's position and the vehicle's position. The two lane lines closest to the vehicle are then used as target lane lines. The lane centerline position is then calculated based on the positions of the two target lane lines.

[0131] The position of the lane line and the position of the lane centerline can be represented by a set of coordinate points, so the position of the lane centerline can be obtained by averaging the positions of the two target lane lines.

[0132] The distance between the lane line and the vehicle is calculated by fitting a lane line curve based on the position of the lane line, and then calculating the distance between the vehicle position and the lane line curve to obtain the distance between the lane line and the vehicle.

[0133] S302: For each guide arrow, if the distance between the position of the guide arrow and the center line of the lane is less than a preset guide distance, the guide type of the guide arrow is used as the lane passage type.

[0134] In this step, after the ECU obtains the lane centerline position, for each guide arrow, if the distance between the position of the guide arrow and the lane centerline position is less than the preset guide distance, it means that the guide arrow is the guide arrow for controlling the driving of the vehicle, then the guide type of the guide arrow is used as the lane passage type.

[0135] It should be noted that the preset guiding distance can be 1.5 meters, 1.8 meters, 2 meters, etc. The embodiment of the present application does not limit the preset guiding distance and can be determined according to actual conditions.

[0136] It should be noted that if there are multiple guide arrows whose distance from the lane centerline is less than the preset guide distance, the guide arrow with the smallest distance from the lane centerline is selected, and the guide type of the guide arrow is used as the lane passage type.

[0137] The method for determining the passability of an intersection provided in this embodiment improves the accuracy of the lane traffic type by determining the lane traffic type of the vehicle's lane based on traffic marking data and vehicle position, thereby improving the accuracy of the determined intersection passability.

[0138] Figure 4 This is a flow chart of the third embodiment of the method for determining the passability of an intersection provided by this application. Based on the above embodiment, this embodiment of the application describes the situation where the ECU determines the target signal light that matches the lane where the vehicle is located based on the number of lanes controlled by all third signal lights. Figure 4 As shown, the method for determining the passability of the intersection specifically includes the following steps:

[0139] S401: Determine whether the number of controlled lanes of all third signal lights is equal to 1; if the number of controlled lanes of all third signal lights is equal to 1, execute step S404; if the number of controlled lanes of all third signal lights is greater than 1, execute step S405.

[0140] In this step, after the ECU determines the third signal light, in order to determine the target signal light, it is necessary to determine whether the number of controlled lanes of all the third signal lights is equal to 1.

[0141] S402: Determine whether the number of controlled lanes of all third signal lights is greater than 1; if the number of controlled lanes of all third signal lights is greater than 1, execute step S405; if the number of controlled lanes of all third signal lights is equal to 1, execute steps S403-S404.

[0142] In this step, if the ECU determines that the number of controlled lanes among all the third signal lights is greater than 1, it is also necessary to determine whether the number of controlled lanes of all the third signal lights is greater than 1.

[0143] S403: The third signal light whose number of controlled lanes is 1 is used as the fourth signal light data.

[0144] S404: The fourth signal light closest to the vehicle position among all the fourth signal lights is used as the target signal light.

[0145] In the above steps, if the ECU determines that among all the third signal lights, the number of controlled lanes is equal to 1, it means that the signal light type of multiple signal lights matches the lane traffic type, and there are signal lights that control vehicles in only one lane, and there are signal lights that control vehicles in multiple lanes. In this case, the signal light that controls vehicles in only one lane has a higher priority and is more likely to be the signal light that controls this vehicle. Therefore, the third signal light that controls the number of controlled lanes equal to 1 is used as the fourth signal light data, and then the fourth signal light that is closest to the vehicle position among all the fourth signal lights is used as the target signal light. This signal light is the signal light that controls the driving of this vehicle.

[0146] S405: The third signal light closest to the vehicle position among all the third signal lights is used as the target signal light.

[0147] In this step, if the ECU determines that the number of controlled lanes of all third signal lights is equal to 1, it means that there are multiple signal lights whose signal light types match the lane traffic types and only control vehicles in one lane. Then, the third signal light closest to the vehicle position among all third signal lights is used as the target signal light, and this signal light is the signal light that controls the driving of this vehicle.

[0148] If the ECU determines that the number of lanes controlled by all third signal lights is greater than 1, it means that there are multiple signal lights whose signal light types match the lane traffic types and control vehicles in multiple lanes. Then, the third signal light closest to the vehicle position among all third signal lights will be used as the target signal light. This signal light is the signal light that controls the driving of this vehicle.

[0149] It should be noted that the ECU may first determine whether the number of controlled lanes for all third signal lights is greater than 1. If it is determined that the number of controlled lanes for all third signal lights is equal to 1, the ECU may then determine whether the number of controlled lanes for all third signal lights is equal to 1. Alternatively, the ECU may determine whether the number of controlled lanes for all third signal lights is greater than 1 and simultaneously determine whether the number of controlled lanes for all third signal lights is equal to 1. If the ECU determines that the number of controlled lanes for all third signal lights is equal to 1, or that the number of controlled lanes for all third signal lights is greater than 1, the ECU uses the third signal light closest to the vehicle's position among all third signal lights as the target signal light. If the ECU determines that there is a signal light with a controlled lane equal to 1 among all third signal lights, and there is a signal light with a controlled lane equal to 1, the ECU uses the third signal light with a controlled lane equal to 1 as the fourth signal light data and uses the fourth signal light closest to the vehicle's position among all fourth signal lights as the target signal light.

[0150] The method for determining the passability of an intersection provided in this embodiment determines the target signal light by the number of lanes controlled by the third signal light and the distance between the signal light and the vehicle, thereby improving the accuracy of the target signal light.

[0151] Figure 5 This is a flow chart of the fourth embodiment of the method for determining the passability of an intersection provided by this application. Based on the above embodiment, this embodiment of the application describes the situation where the ECU updates the first signal light data based on the historical signal light data. Figure 5 As shown, the method for determining the passability of the intersection specifically includes the following steps:

[0152] S501: Acquire historical traffic light data.

[0153] In this step, after the ECU obtains the first signal light data, in order to improve the accuracy of the first signal light data, it may be updated, and it is necessary to obtain historical signal light data.

[0154] While the vehicle is driving, it can capture an environmental image at each acquisition moment. The ECU then detects whether the image contains traffic lights. If it does, it detects and determines historical traffic light data. This historical traffic light data is then associated with the acquisition moment and stored in a historical dataset. Therefore, historical traffic light data can be obtained from the historical dataset.

[0155] Each historical signal light data includes the location and identification of at least one historical signal light; the first signal light data includes signal light data of at least one first signal light, and the signal light data includes light color, location, direction, signal light type and identification.

[0156] It should be noted that there is a preset collection time interval between every two collection times, and the preset collection time interval can be 1 second, 2 seconds, 5 seconds, etc. The embodiment of the present application does not limit the preset collection time interval, and it can be determined according to actual conditions.

[0157] It should be noted that after detecting and determining historical traffic light data, it is first determined whether the interval between the latest collection time in the historical data set and the current collection time is greater than or equal to a preset multiple of the preset collection time. If the interval is greater than or equal to the preset multiple of the preset collection time, the historical data set is cleared, and the historical traffic light data is then associated with the current collection time and stored in the historical data set. If the interval is less than the preset multiple of the preset collection time, the historical traffic light data is then associated with the current collection time and stored in the historical data set.

[0158] The preset multiple can be 3, 5, 6, etc. The embodiment of the present application does not limit the preset multiple and can be determined according to actual conditions.

[0159] It should be noted that when the vehicle is stationary, the historical data set is not processed.

[0160] S502: Update the first signal light data according to the historical signal light data to obtain updated first signal light color data.

[0161] In this step, after the ECU obtains the historical signal light data, it updates the first signal light data according to the historical signal light data to obtain updated first signal light color data.

[0162] Specifically, since the position of each first signal light is a position in the current vehicle coordinate system, the position of each historical signal light is first converted to the current vehicle coordinate system to obtain the updated position of the historical signal light.

[0163] For each first signal light, the following process is performed:

[0164] It is determined whether there is a historical signal light having an identifier identical to that of the first signal light among all historical signal lights.

[0165] If there is a historical signal light with the same identifier as the first signal light among all historical signal lights, the position of the first signal light is updated according to the updated position of the historical signal light with the same identifier as the first signal light, thereby completing the update of the signal light data of the first signal light.

[0166] If no historical traffic light has the same identifier as the first traffic light among all historical traffic lights, the distance between each historical traffic light and the first traffic light is calculated based on the updated position of each historical traffic light and the position of the first traffic light. A determination is then made as to whether any historical traffic light has a distance from the first traffic light that is less than a preset fusion distance.

[0167] It should be noted that the preset fusion distance can be 0.3 meters, 0.5 meters, 1 meter, etc. The embodiment of the present application does not limit the preset fusion distance and can be determined according to actual conditions.

[0168] If there is a historical signal light among all historical signal lights whose distance from the first signal light is less than the preset fusion distance, the position of the first signal light is updated according to the updated position of the historical signal light whose distance from the first signal light is less than the preset fusion distance, thereby completing the update of the signal light data of the first signal light.

[0169] If there is no historical signal light whose distance from the first signal light is less than the preset fusion distance among all historical signal lights, the signal light data of the first signal light is not modified and the signal light data of the first signal light is updated.

[0170] Once the signal light data of each first signal light is updated, the updated first signal light color data can be obtained.

[0171] The position of the first signal light is updated based on the updated position of at least one historical signal light. The signal light data for the first signal light is updated by calculating the distance between each of the at least one historical signal light and the first signal light, normalizing the distances to obtain a weight for each historical signal light. Based on the weight of each historical signal light, a weighted sum is taken of the updated positions of each historical signal light to obtain a reference position. The midpoint between the reference position and the position of the first signal light is used as the updated position of the first signal light.

[0172] S503: Based on the acquired vehicle driving direction and vehicle position, as well as the signboard data, the updated first signal light data is filtered and the number of controlled lanes is added to obtain the second signal light data.

[0173] It should be noted that this step is similar to step S202 in the first embodiment and will not be described again here.

[0174] The method for determining the passability of an intersection provided in this embodiment updates the first signal light color data through historical signal light data, thereby improving the accuracy of the first signal light color data and further improving the accuracy of the determined passability of the intersection.

[0175] The following are device embodiments of the present application, which can be used to implement the method embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the method embodiments of the present application.

[0176] Figure 6 This is a schematic diagram of the structure of an embodiment of the device for determining the passability of an intersection provided by this application. Figure 4 As shown, the intersection accessibility determination device 60 includes:

[0177] The processing module 61 is configured to:

[0178] Recognize and process the acquired intersection environment image to obtain first signal light data, signboard data, and traffic marking data;

[0179] According to the acquired vehicle driving direction and vehicle position, as well as the signboard data, the first signal light data is filtered and the number of controlled lanes is added to obtain second signal light data;

[0180] Determining a target signal light that matches the lane where the vehicle is located based on the vehicle position, the traffic marking data, and the second signal light data;

[0181] The decision module 62 is used to determine whether the current intersection is passable according to the light color of the target traffic light.

[0182] Furthermore, the processing module 61 is specifically configured to:

[0183] filtering the first signal light data according to the vehicle's driving direction and the vehicle's position to obtain third signal light data;

[0184] According to the signboard data, the third signal light data is processed by adding the number of controlled lanes to obtain the second signal light data.

[0185] Furthermore, the first signal light data includes signal light data of at least one first signal light, and the signal light data includes light color, position, direction, and signal light type. The processing module 61 is further configured to:

[0186] Determine a screening area based on the vehicle position and the preset screening position calculation information;

[0187] For each first signal light, if the position of the first signal light does not belong to the screening area, and the angle between the orientation of the first signal light and the driving direction of the vehicle does not belong to the preset screening angle range, the first signal light is used as the second signal light;

[0188] The third signal light data is generated based on the signal light data of each second signal light.

[0189] Furthermore, the signboard data includes the location and content of at least one signboard, the third signal light data includes signal light data of at least one second signal light, and the signal light data includes light color, location, direction, and signal light type. The processing module 61 is further specifically configured to:

[0190] For each second signal light and each signboard, if the distance between the position of the second signal light and the position of the signboard is less than a preset distance threshold, the second signal light and the signboard are considered as a matching pair;

[0191] For each matching pair, if the content of the sign in the matching pair includes the preset single lane control content, adding a first preset number to the signal light data of the second signal light in the matching pair, where the first preset number is 1;

[0192] For each two second signal lights whose signal light type falls within the preset arrow type range, if the distance between the positions of the two second signal lights falls within the preset lane distance range, adding the first preset number to the signal light data of the two second signal lights respectively;

[0193] For each second signal light, if the signal light data of the second signal light does not include the first preset number, adding a second preset number to the signal light data of the second signal light, where the second preset number is greater than 1;

[0194] The second signal light data is generated according to the signal light data of each second signal light after the number of controlled lanes is added.

[0195] Furthermore, the second signal light data includes signal light data of at least one second signal light, and the signal light data includes light color, position, direction, signal light type, and number of controlled lanes. The processing module 61 is further configured to:

[0196] Determining a lane traffic type of a lane where the vehicle is located based on the traffic marking data and the vehicle position;

[0197] Determining the target signal light type corresponding to the lane traffic type according to a preset correspondence between traffic types and signal light types;

[0198] For each second signal light, if the signal light type of the second signal light is the target signal light type, use the second signal light as the third signal light;

[0199] According to the number of lanes controlled by all third signal lights, a target signal light matching the lane where the vehicle is located is determined.

[0200] Furthermore, the traffic marking data includes the positions of at least two lane lines and the position and guidance type of at least one guide arrow. The processing module 61 is further configured to:

[0201] Determining a lane centerline position of the lane where the vehicle is located based on the vehicle position and the position of each lane line;

[0202] For each guide arrow, if the distance between the position of the guide arrow and the center line of the lane is less than a preset guide distance, the guide type of the guide arrow is used as the lane passage type.

[0203] Furthermore, the processing module 61 is further configured to:

[0204] If the number of lanes controlled by all third signal lights is equal to 1, or the number of lanes controlled by all third signal lights is greater than 1, the third signal light closest to the position of the vehicle among all third signal lights is used as the target signal light;

[0205] If there is a signal light with 1 controlled lane number among all third signal lights, and there is a signal light with 1 controlled lane number, then the third signal light with 1 controlled lane number is used as the fourth signal light data;

[0206] The fourth signal light closest to the vehicle position among all the fourth signal lights is used as the target signal light.

[0207] Furthermore, the first signal light data is filtered and the number of controlled lanes is added based on the acquired vehicle driving direction and vehicle position, as well as the signboard data, before obtaining the second signal light data, the acquisition module 63 is used to obtain historical signal light data;

[0208] The processing module 61 is further configured to:

[0209] updating the first signal light data according to the historical signal light data to obtain updated first signal light color data;

[0210] The method of filtering and marking the first signal light data based on the acquired vehicle driving direction and vehicle position, as well as the signboard data, to obtain the second signal light data includes:

[0211] According to the acquired vehicle driving direction and vehicle position, as well as the signboard data, the updated first signal light data is filtered and the number of controlled lanes is added to obtain the second signal light data.

[0212] The device for determining the passability of an intersection provided in this embodiment is used to execute the technical solution in any of the aforementioned method embodiments. Its implementation principles and technical effects are similar and will not be described in detail here.

[0213] Figure 7 This is a schematic diagram of the structure of an electronic device provided by this application. Figure 7 As shown, the electronic device 70 includes:

[0214] Processor 71, memory 72, and communication interface 73;

[0215] The memory 72 is used to store executable instructions of the processor 71;

[0216] The processor 71 is configured to execute the technical solution in any of the aforementioned method embodiments by executing the executable instructions.

[0217] Optionally, the memory 72 can be independent or integrated with the processor 71.

[0218] Optionally, when the memory 72 is a device independent of the processor 71, the electronic device 70 may further include:

[0219] The bus 74 , the memory 72 and the communication interface 73 are connected to the processor 71 via the bus 74 and communicate with each other. The communication interface 73 is used to communicate with other devices.

[0220] Optionally, communication interface 73 may be implemented using a transceiver. The communication interface is used to enable communication between the database access device and other devices (e.g., clients, read-write libraries, and read-only libraries). The memory may include random access memory (RAM) and may also include non-volatile memory, such as at least one disk storage device.

[0221] Bus 74 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. Buses can be categorized as address buses, data buses, and control buses. For ease of illustration, the figure uses only one thick line, but this does not imply that there is only one bus or only one type of bus.

[0222] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components.

[0223] The electronic device is used to execute the technical solution in any of the aforementioned method embodiments, and its implementation principles and technical effects are similar and will not be repeated here.

[0224] An embodiment of the present application also provides a computer program product, including a computer program, which, when executed by a processor, is used to implement the technical solution provided by any of the aforementioned method embodiments.

[0225] An embodiment of the present application further provides a readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the technical solution provided by any of the aforementioned method embodiments.

[0226] The readable storage medium may be implemented by any type of volatile or non-volatile memory 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 storage, flash memory, magnetic disk, or optical disk. The readable storage medium may be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0227] 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 an integral part of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0228] The division of units is merely a logical functional division; actual implementations may employ alternative divisions, such as combining or integrating multiple units or components into another system, or omitting or disabling certain features. Furthermore, any direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between devices or units, either through an interface, electrical, mechanical, or other means.

[0229] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0230] 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.

[0231] If a function is implemented as 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 portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the method of the present invention. The aforementioned storage medium includes various media that can store program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0232] Those skilled in the art will appreciate that all or part of the steps in the above-described method embodiments can be implemented using hardware associated with program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0233] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for determining the traversability of an intersection, characterized in that: include: Recognize and process the acquired intersection environment image to obtain first signal light data, signboard data, and traffic marking data; According to the acquired vehicle driving direction and vehicle position, as well as the signboard data, the first signal light data is filtered and the number of controlled lanes is added to obtain second signal light data; Determining a target signal light that matches the lane where the vehicle is located based on the vehicle position, the traffic marking data, and the second signal light data; Determine whether the current intersection is passable based on the light color of the target traffic light.

2. The method according to claim 1, characterized in that The method of filtering the first signal light data and adding a control lane quantity process based on the acquired vehicle driving direction and vehicle position, as well as the signboard data, to obtain the second signal light data includes: filtering the first signal light data according to the vehicle's driving direction and the vehicle's position to obtain third signal light data; According to the signboard data, the third signal light data is processed by adding the number of controlled lanes to obtain the second signal light data.

3. The method according to claim 2, characterized in that The first signal light data includes signal light data of at least one first signal light, and the signal light data includes light color, position, direction and signal light type; The filtering of the first signal light data according to the vehicle driving direction and the vehicle position to obtain third signal light data includes: Determine a screening area based on the vehicle position and the preset screening position calculation information; For each first signal light, if the position of the first signal light does not belong to the screening area, and the angle between the orientation of the first signal light and the driving direction of the vehicle does not belong to the preset screening angle range, the first signal light is used as the second signal light; The third signal light data is generated based on the signal light data of each second signal light.

4. The method according to claim 2, characterized in that The signboard data includes the location and content of at least one signboard, and the third signal light data includes signal light data of at least one second signal light, and the signal light data includes light color, location, direction and signal light type; The step of adding a controlled lane quantity to the third signal light data according to the signboard data to obtain the second signal light data includes: For each second signal light and each signboard, if the distance between the position of the second signal light and the position of the signboard is less than a preset distance threshold, the second signal light and the signboard are considered as a matching pair; For each matching pair, if the content of the sign in the matching pair includes the preset single lane control content, adding a first preset number to the signal light data of the second signal light in the matching pair, where the first preset number is 1; For each two second signal lights whose signal light type falls within the preset arrow type range, if the distance between the positions of the two second signal lights falls within the preset lane distance range, adding the first preset number to the signal light data of the two second signal lights respectively; For each second signal light, if the signal light data of the second signal light does not include the first preset number, adding a second preset number to the signal light data of the second signal light, where the second preset number is greater than 1; The second signal light data is generated according to the signal light data of each second signal light after the number of controlled lanes is added.

5. The method according to claim 1, wherein The second signal light data includes signal light data of at least one second signal light, and the signal light data includes light color, position, direction, signal light type and number of controlled lanes; Determining a target signal light that matches a lane where the vehicle is located according to the vehicle position, the traffic marking data, and the second signal light data includes: Determining a lane traffic type of a lane where the vehicle is located based on the traffic marking data and the vehicle position; Determining the target signal light type corresponding to the lane traffic type according to a preset correspondence between traffic types and signal light types; For each second signal light, if the signal light type of the second signal light is the target signal light type, use the second signal light as the third signal light; According to the number of lanes controlled by all third signal lights, a target signal light matching the lane where the vehicle is located is determined.

6. The method according to claim 5, characterized in that The traffic marking data includes the positions of at least two lane lines and the position and guidance type of at least one guide arrow; The determining, based on the traffic line data and the vehicle position, the lane traffic type of the lane in which the vehicle is located, includes: Determining a lane centerline position of the lane where the vehicle is located based on the vehicle position and the position of each lane line; For each guide arrow, if the distance between the position of the guide arrow and the center line of the lane is less than a preset guide distance, the guide type of the guide arrow is used as the lane passage type.

7. The method according to claim 5, characterized in that The step of determining a target signal light that matches the lane where the vehicle is located based on the number of lanes controlled by all third signal lights includes: If the number of lanes controlled by all third signal lights is equal to 1, or the number of lanes controlled by all third signal lights is greater than 1, the third signal light closest to the position of the vehicle among all third signal lights is used as the target signal light; If there is a signal light with 1 controlled lane number among all third signal lights, and there is a signal light with 1 controlled lane number, then the third signal light with 1 controlled lane number is used as the fourth signal light data; The fourth signal light closest to the vehicle position among all the fourth signal lights is used as the target signal light.

8. The method according to any one of claims 1 to 7, characterized in that Before obtaining the second signal light data by filtering and adding a control lane quantity process to the first signal light data based on the acquired vehicle driving direction and vehicle position and the signboard data, the method further includes: Get historical traffic light data; updating the first signal light data according to the historical signal light data to obtain updated first signal light color data; The method of filtering and marking the first signal light data based on the acquired vehicle driving direction and vehicle position, as well as the signboard data, to obtain the second signal light data includes: According to the acquired vehicle driving direction and vehicle position, as well as the signboard data, the updated first signal light data is filtered and the number of controlled lanes is added to obtain the second signal light data.

9. A device for determining the passability of an intersection, characterized in that: include: Processing module for: Recognize and process the acquired intersection environment image to obtain first signal light data, signboard data, and traffic marking data; According to the acquired vehicle driving direction and vehicle position, as well as the signboard data, the first signal light data is filtered and the number of controlled lanes is added to obtain second signal light data; Determining a target signal light that matches the lane where the vehicle is located based on the vehicle position, the traffic marking data, and the second signal light data; The decision module is used to determine whether the current intersection is passable based on the light color of the target traffic light.

10. An electronic device, characterized in that: include: Processor, memory, communication interface; The memory is used to store executable instructions of the processor; The processor is configured to execute the method for determining the passability of an intersection according to any one of claims 1 to 8 by executing the executable instructions.

11. A readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for determining the passability of an intersection according to any one of claims 1 to 8 is implemented.

12. A computer program product, characterized in that The method comprises a computer program, which is used to implement the method for determining the passability of an intersection according to any one of claims 1 to 8 when executed by a processor.

Images