Roadside device sensing range determination method and apparatus, and roadside device

Abstract

The application discloses a roadside device sensing range determination method and device and a roadside device. The method is applied to a roadside device, and the roadside device at least comprises a camera. The method comprises the following steps: acquiring lane line detection results of a lower lane according to image information collected by the camera; determining vehicle driving direction detection results or road edge detection results of the lower lane; and determining a sensing range of the camera based on the lane line detection results, in combination with the vehicle driving direction detection results or the road edge detection results of the lower lane. The application realizes automatic determination of the sensing range of the camera in the roadside device.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a method, device and roadside equipment for determining the perception range of roadside equipment. Background Technology

[0002] Roadside systems include roadside equipment, which typically covers the entire scene at intersections and road sections using multiple poles and cameras.

[0003] For two-way lanes, each roadside device's camera only needs to cover one lane in the direction of traffic flow, while the opposite lane is often covered by a different camera.

[0004] Because the camera has a wide field of view, to avoid false detections, traffic flow from the other direction is blocked, and only traffic flow under the camera pole is detected. This blocking process typically involves manually marking an image area and selectively detecting traffic based on that area. However, if external interference (weather) causes the camera / pole to move, the detection range of that area needs to be manually re-marked. Summary of the Invention

[0005] This application provides a method, apparatus, and roadside equipment for determining the sensing range of roadside equipment, so as to realize the automated determination of the sensing range of cameras in roadside equipment.

[0006] The embodiments of this application adopt the following technical solutions:

[0007] In a first aspect, embodiments of this application provide a method, apparatus, and roadside device for determining the sensing range of a roadside device, wherein the method is applied to a roadside device, the roadside device including at least a camera, and the method includes:

[0008] Based on the image information captured by the camera, the lane line detection result of the lower lane is obtained;

[0009] Determine the vehicle travel direction detection result or the curb detection result of the lane below;

[0010] Based on the lane line detection results, combined with the vehicle travel direction detection results or curb detection results of the lower lane, the perception range of the camera is determined.

[0011] In some embodiments, determining the vehicle travel direction detection result or curb detection result of the lower lane includes:

[0012] Based on the image information, target matching and tracking are performed to obtain vehicle trajectory tracking records;

[0013] Based on the vehicle trajectory tracking record, determine the vehicle driving direction detection result in the lower lane;

[0014] And / or,

[0015] Target detection is performed based on the image information to obtain the curb detection result, which is used to determine the solid lines of the left and right lanes in the lane line detection result.

[0016] In some embodiments, the step of performing target detection based on the image information to obtain curb detection results, used to determine the solid lines of the left and right lane lines in the lane line detection results, includes:

[0017] Target detection is performed on the image information to obtain the curb detection result;

[0018] The two right edges that meet the bottom edge of the image with the curb detection result are taken as the left curb and the right curb;

[0019] The solid line of the left lane is determined by moving right from the left road edge, and the solid line of the right lane is determined by moving left from the right road edge.

[0020] In some embodiments, determining the vehicle travel direction detection result of the lower lane based on the vehicle travel trajectory tracking record includes:

[0021] The vehicle's driving direction in the image is calculated by tracking and detecting over multiple consecutive frames. The vehicle's driving direction in the image includes traffic flowing towards the top of the image, traffic flowing towards the bottom of the image, and traffic flowing laterally towards the image.

[0022] After filtering out the lateral traffic flow in the orientation image, the vehicle trajectory tracking record in multiple frames of images is obtained based on the traffic flow above and below the orientation image.

[0023] The trajectory tracking is recorded in the direction of the vehicle on the right side of the image, which is used as the detection result of the vehicle's driving direction in the lower lane.

[0024] In some embodiments, determining the camera's perception range based on the lane line detection results, combined with the vehicle travel direction detection results or curb detection results of the lower lane, includes:

[0025] Based on the results of the solid lines of the left and right lanes in the lane detection results extending on the image, a region that runs through the vertical direction of the image is obtained.

[0026] The camera's sensing range is determined based on the longitudinal region running through the image.

[0027] In some embodiments, the perception range of the camera is determined based on the lane line detection results, combined with the vehicle travel direction detection results or curb detection results of the lower lane, including:

[0028] Compare the area enclosed by the solid lane line in the lane line detection results with the vehicle positions that meet the preset traffic flow direction in the vehicle driving direction detection results.

[0029] If the vehicle is located within the area enclosed by the solid lane line, then the area enclosed by the solid lane line is taken as the sensing range of the camera, and the sensing range of the camera includes one or more solid line areas.

[0030] In some embodiments, the perception range of the camera is determined based on the lane line detection results, combined with the vehicle travel direction detection results or curb detection results of the lower lane, including:

[0031] If no lane lines are detected in the lane line detection results, then the region that runs through the vertical direction of the image is obtained based on the result of extending the curb detection results on the image.

[0032] If the lane line found first from the left edge to the right is a dashed line, or the lane line found first from the right edge to the left is a dashed line, then the lane line detection result shall be taken as the solid lane line.

[0033] If the left lane line found by moving from the left curb to the right and the right lane line found by moving from the right curb to the left have the right lane line to the left, then the curb detection result shall be taken as the solid lane line.

[0034] In some embodiments, the method further includes:

[0035] The camera's sensing range is updated and determined according to a preset cycle, and the sensing area is divided according to different pixel values.

[0036] Secondly, embodiments of this application also provide a roadside equipment sensing range determination device, wherein the device is applied to a roadside equipment, the roadside equipment including at least a camera, and the device includes:

[0037] The acquisition module is used to acquire the lane line detection results of the lower lane based on the image information captured by the camera;

[0038] The first determining module is used to determine the vehicle driving direction detection result or the curb detection result of the lower lane;

[0039] The second determining module is used to determine the perception range of the camera based on the lane line detection results, combined with the vehicle driving direction detection results or roadside detection results of the lower lane.

[0040] Thirdly, embodiments of this application also provide a roadside device, including the roadside device sensing range determination device described in the second aspect.

[0041] Fourthly, embodiments of this application also provide an electronic device, including: a processor; and a memory arranged to store computer-executable instructions, which, when executed, cause the processor to perform the above-described method.

[0042] Fifthly, embodiments of this application also provide a computer-readable storage medium that stores one or more programs, which, when executed by an electronic device including multiple applications, cause the electronic device to perform the above-described method.

[0043] The at least one technical solution adopted in this application embodiment can achieve the following beneficial effects: First, based on the image information captured by the camera, the lane line detection result of the lower lane is obtained; then, the vehicle driving direction detection result or the curb detection result of the lower lane is determined; finally, based on the lane line detection result, combined with the vehicle driving direction detection result or the curb detection result of the lower lane, the perception range of the camera is determined. This achieves automated determination of the camera's perception range, eliminating the need for manual recalibration before determining the perception range. It can utilize lane line detection and vehicle driving direction to obtain the current camera's perception range of interest, or it can utilize curb detection and lane line detection to obtain the current camera's perception range of interest, thereby improving the method's adaptability. Attached Figure Description

[0044] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0045] Figure 1 This is a schematic diagram of the method for determining the sensing range of roadside equipment in an embodiment of this application;

[0046] Figure 2 This is a schematic diagram of the roadside equipment sensing range determination device in the embodiments of this application;

[0047] Figure 3 This is a schematic diagram of the camera sensing range obtained in the method for determining the sensing range of roadside equipment in the embodiments of this application;

[0048] Figure 4 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0049] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0050] During their research, the inventors discovered that roadside cameras, due to their wide field of view, would block traffic flow from the other direction to avoid false detections, only detecting traffic flow from the direction directly below the camera pole. Since the blocking process involves manually marking an image area and selectively detecting based on that area, any changes in the position / or orientation of the camera or its pole necessitate recalibration to determine the sensing range.

[0051] To address the aforementioned shortcomings, the embodiments of this application utilize roadside cameras to detect lane lines, curbs, or vehicles within the perception field of view, thereby determining the traffic flow area below the camera pole and automatically generating the perception range without the need for manual labeling. Even if the camera changes, the perception range can be automatically adjusted to a reasonable level, saving time spent on manual labeling. Furthermore, the method can adaptively select whether to detect curbs or vehicle travel directions based on the actual scenario, improving its adaptability to different scenarios.

[0052] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0053] This application provides a method for determining the sensing range of roadside equipment, such as... Figure 1 The diagram shows a flowchart of a method for determining the sensing range of roadside equipment in an embodiment of this application. The method includes at least the following steps S110 to S130:

[0054] Step S110: Obtain the lane line detection result of the lower lane based on the image information captured by the camera.

[0055] Roadside equipment is typically installed at intersections or along road sections to cover different areas. The cameras on roadside equipment usually monitor only one lane in the direction of traffic flow. Based on the image information captured by the camera, lane line detection results for the lane below the camera can be obtained. The detection range for the lane below the camera is related to the position of the camera pole and the camera's orientation; this application does not impose specific limitations, as long as the installation requirements of the roadside equipment are met.

[0056] The lane line detection results for the lower lane include the results of distinguishing between solid and dashed lines after lane line detection. Lane line detection can be performed using deep learning techniques with models trained on a large amount of labeled data. The specific deep convolutional neural network used is not specifically limited in the embodiments of this application.

[0057] The lane detection results obtained at this time do not distinguish the direction of traffic flow, but detect lane lines from all the available image information.

[0058] Step S120: Determine the vehicle driving direction detection result or the curb detection result of the lower lane.

[0059] The curb refers to the boundary of the drivable area of ​​a road. When detecting curbs, they are generally located next to the solid lane lines on either side. It's understandable that both curb detection and lane line detection utilize deep learning techniques to train models with large amounts of labeled data. The reason for detecting both curbs and lane lines is twofold: firstly, to handle situations where lane lines are absent or blurred, the curb detection results are used; secondly, when lane lines are present, the perception range generally extends from the solid lane line next to the curb, so the curb is needed to determine the position of the solid lane line.

[0060] Vehicle detection is primarily performed to match and track vehicles within multiple frames of detected images, thereby calculating their direction of travel on the image through stable tracking over consecutive frames. It's important to note that in road sections, because the camera's orientation is similar to the lane direction, there are generally only two traffic flow directions: outward and inward. Furthermore, in intersection areas, vehicles traveling laterally are filtered out, retaining only vehicles traveling in the inward and outward directions.

[0061] The determination of whether to use vehicle direction detection or curb detection results can be based on the actual detectable targets in the image information. For example, if a curb can be detected in the image information with high confidence, the curb detection result is used. Conversely, if vehicle detection across multiple frames is inaccurate and has low confidence, the curb detection result is used. Alternatively, if vehicle detection across multiple frames is relatively accurate and has high confidence, the vehicle direction detection result is used. Of course, if both detection methods are applicable, either one can be selected.

[0062] Step S130: Based on the lane line detection results, combined with the vehicle driving direction detection results or roadside detection results of the lower lane, determine the perception range of the camera.

[0063] The perception range of the camera is determined by combining the solid lane lines in the lane detection results with the vehicle driving direction detection results or the curb detection results.

[0064] For example, the solid lane lines of the left and right lanes can typically be extended across the image. Based on the extension of the lane lines, at least one region spanning the vertical direction of the image can be obtained; this region is the perception range. This range is then saved for subsequent object detection.

[0065] For example, the solid lane lines that can usually be detected are extended on the image, and multiple enclosing regions that run through the longitudinal direction of the image are obtained based on the extension results of the left and right solid lane lines. Then, based on the traffic flow direction perceived by the roadside equipment's camera, the image position of the vehicle that matches that direction is selected and compared with the enclosing region of the acquired solid lane lines.

[0066] The above method enables the automated determination of a camera's sensing range, eliminating the need for manual recalibration. Furthermore, this method allows for batch processing of results for each camera, effectively saving time spent manually labeling specific ranges for each camera.

[0067] Unlike related technologies that rely on manual recalibration before determining the camera's sensing range, the method described above utilizes lane line detection and vehicle direction of travel to determine the sensing range of interest for the current camera. Alternatively, it can use curb detection and lane line detection to determine the sensing range of interest for the current camera. This effectively saves the time required for manual labeling of specific ranges for each camera.

[0068] Unlike related technologies that employ manual, passive updating methods, the above method achieves proactive updating by periodically updating and determining the sensing range without requiring recalibration. Furthermore, it can be applied to camera configuration files, enabling batch, automated processing to update the sensing range of roadside equipment.

[0069] In one embodiment of this application, determining the vehicle driving direction detection result or curb detection result of the lower lane includes: performing target matching and tracking based on the image information to obtain a vehicle driving trajectory tracking record; determining the vehicle driving direction detection result of the lower lane based on the vehicle driving trajectory tracking record; and / or, performing target detection based on the image information to obtain a curb detection result, which is used to determine the solid lines of the left and right lane lines in the lane line detection result.

[0070] Based on the image information, target matching and tracking can be performed. When the target is a vehicle, a vehicle trajectory tracking record is obtained. This record records the vehicle's direction of travel on the image, categorizing traffic flows into two types: upwards and downwards. Vehicles not traveling in either of these directions are removed.

[0071] Furthermore, based on the vehicle trajectory tracking records, when determining the vehicle travel direction detection results for the lower lane, if it is in a road segment area, since the camera's installation orientation is similar to the lane direction, there are generally only two traffic flow directions: outward and inward. If it is in an intersection area, vehicles traveling laterally in the image are filtered out, and only vehicles traveling in the inward and outward directions are retained. This can filter out interference and reduce the amount of previous calculations.

[0072] Target detection can be performed based on the image information. When the target is a roadside, the roadside detection result can be obtained. The reason for detecting both roadside and lane lines is to accommodate situations where there are no lane lines or the lane lines are blurred, in which case the roadside result is used. Secondly, when lane lines are present, the perception range generally extends from the solid lane line next to the roadside, so it is also necessary to use the roadside to determine the position of the solid lane line.

[0073] Furthermore, the curb detection results are used to determine the solid lines of the left and right lanes in the lane line detection results. When determining the solid lines of the lanes based on the curb detection results, the two right edges where the curb touches the bottom edge of the image (continuous detection results across multiple image frames) need to be taken. This is because if a two-way lane curb is detected, since the camera is mounted above the lane to be detected, taking the two right curb edges in the image includes the area to be detected. Finally, based on the curb detection results, the left lane solid line is determined by moving right from the left curb, and the right lane solid line is determined by moving left from the right curb. This method performs well when detecting a single lane below the camera of a roadside device.

[0074] It is understandable that the same method can be used to make judgments in complex scenarios, such as multi-lane intersections or multi-lane road segments.

[0075] In one embodiment of this application, the step of performing target detection based on the image information to obtain curb detection results, and using these results to determine the solid lines of the left and right lane lines in the lane line detection results, includes: performing target detection on the image information to obtain curb detection results; taking the two right edges of the curb detection results that contact the bottom edge of the image as the left curb and the right curb; determining the solid line of the left lane line to the right based on the left curb, and determining the solid line of the right lane line to the left based on the right curb.

[0076] In practice, the solid lane lines are determined based on the curb detection results. The two line segments on the right side (following the convention that vehicles usually drive on the right) where the curb touches the bottom edge of the image are taken. This is because if the curb of a two-way lane is detected, since the camera is mounted above the lane to be detected, taking the two right edges of the image as the curb includes the area to be detected.

[0077] Next, based on the curb detection results, the solid line for the left lane is determined by extending it from the left curb to the right, and the solid line for the right lane is determined by extending it from the right curb to the left. These lane lines are then extended across the image, resulting in a region that spans the entire length of the image; this region is the perception range. This range is saved for subsequent object detection, such as... Figure 3 The non-gray area shown.

[0078] This can be understood as follows: when the solid lines of the left and right lanes are extended on the image, points on the lane lines are sampled to fit a cubic curve equation. Then, by inputting continuous coordinates within the image height, the x and y coordinates of all horizontal and vertical directions on the cubic curve equation are obtained. In other words, all coordinates of the lane lines on the image and all coordinates of their extensions are obtained. In practice, only the vertical coordinates on the image need to be input for extension.

[0079] In one embodiment of this application, determining the vehicle driving direction detection result of the lower lane based on the vehicle driving trajectory tracking record includes: calculating the vehicle's driving direction in the image through tracking detection of multiple consecutive frames, wherein the vehicle's driving direction in the image includes traffic flow towards the upper part of the image, traffic flow towards the lower part of the image, and traffic flow towards the lateral part of the image; after filtering out the traffic flow towards the lateral part of the image, obtaining the vehicle's trajectory tracking record in multiple frames of the image based on the traffic flow towards the upper part of the image and the traffic flow towards the lower part of the image; and using the vehicle direction on the right side of the image where the trajectory tracking record is located as the vehicle driving direction detection result of the lower lane.

[0080] The direction of travel of the vehicles in the image is calculated through stable tracking over multiple consecutive frames. Based on the direction of travel, vehicles are categorized into two types: those moving upwards and downwards from the image. Vehicles not in either of these directions are removed. In road sections, since the camera's orientation is similar to the lane direction, there are generally only two traffic directions: outwards and inwards. In intersections, vehicles traveling laterally are filtered out, retaining only those moving in and outwards.

[0081] In one embodiment of this application, determining the camera's sensing range based on the lane line detection results, combined with the vehicle driving direction detection results or curb detection results of the lower lane, includes: obtaining a region that runs through the longitudinal direction of the image based on the extension of the solid lines of the left and right lanes in the lane line detection results; and determining the camera's sensing range based on the region that runs through the longitudinal direction of the image.

[0082] Based on the extension of the solid left and right lane lines in the lane detection results onto the image, a region traversing the vertical direction of the image is obtained. If the extension is based on the solid left and right lane lines, a single region traversing the vertical direction of the image is obtained. This region constitutes the sensing range. If the extension is based on the detected solid lane lines (clustering results of multiple image frames), multiple regions traversing the vertical direction of the image are obtained. It is further necessary to determine whether the vehicle positions within these multiple regions traversing the vertical direction are within the areas enclosed by the solid lane lines. If the vehicle positions are within these areas, then these enclosed areas are added to the sensing range of the camera.

[0083] In one embodiment of this application, the perception range of the camera is determined based on the lane line detection result, combined with the vehicle driving direction detection result or the curb detection result of the lower lane, including: comparing the area enclosed by the solid lane line in the lane line detection result with the vehicle position that meets the preset traffic flow direction in the vehicle driving direction detection result; if the vehicle position is within the area enclosed by the solid lane line, then the area enclosed by the solid lane line is taken as the perception range of the camera, and the perception range of the camera includes one or more solid line areas.

[0084] In practice, the trajectories of vehicles traveling in both directions (coming and going) are recorded over multiple frames based on their positions in the image. Since the directions are typically clearly defined on either side of the image, the direction of vehicles on the right side of the image (where vehicles usually travel on the right) is taken as the current traffic flow direction that the camera needs to perceive. At this point, lateral vehicles are not required; only the current longitudinal perception range is captured.

[0085] Based on the detected solid lane lines (clustering results from multiple image frames), the images are extended, resulting in multiple regions spanning the vertical direction of the image. Using the previously obtained camera-perceived traffic flow direction, the image positions of vehicles matching that direction are selected and compared with the previously acquired lane line-enclosed regions. Finally, if a vehicle is located within a lane line-enclosed region, that region is added to the camera's sensing range. The camera's sensing range may include one or more solid lane line regions.

[0086] In one embodiment of this application, the perception range of the camera is determined based on the lane line detection result, combined with the vehicle driving direction detection result or the curb detection result of the lower lane. This includes: if no lane line is detected in the lane line detection result, a region running vertically through the image is obtained based on the extension result of the curb detection result on the image; if the lane line found first from the left curb to the right is a dashed line, or the lane line found first from the right curb to the left is a dashed line, the curb detection result is used as the solid lane line; if the left lane line found from the left curb to the right and the right lane line found from the right curb to the left are both located to the left of the left lane line, the curb detection result is used as the solid lane line.

[0087] If lane lines cannot be detected, the detection results of the curb are extended, resulting in a region that runs vertically through the image. If the lane line found first from the left curb to the right is a dashed line, or the lane line found first from the right curb to the left is a dashed line, the curb is used as the reference. If the left lane line found from the left curb to the right and the right lane line found from the right curb to the left are on the left side of the image, the curb is used as the reference. In other words, if there are no lane lines, the curb is detected and used as the reference, because the curb is relatively far out.

[0088] In one embodiment of this application, the method further includes: updating and determining the sensing range of the camera according to a preset period, wherein the sensing area is divided according to different pixel values.

[0089] like Figure 3 As shown, the process of obtaining the perception range described above only needs to be performed once a day or once every few days to generate the corresponding perception range. Figure 3 The image is represented by 0 or 255 pixel values ​​(corresponding to gray and white respectively). When using this range, only non-zero areas (non-gray areas) are taken, and image perception processing is performed. The configuration files of the roadside equipment cameras are then updated and distributed in batches.

[0090] It is understandable that the process of obtaining the perception range described above requires multiple consecutive frames and a continuous day to ensure that all ranges can be accurately covered.

[0091] This application embodiment also provides a roadside equipment sensing range determination device 200, such as... Figure 2 As shown, a schematic diagram of the roadside equipment sensing range determination device 200 in this application embodiment is provided. The roadside equipment sensing range determination device 200 includes at least: an acquisition module 210, a first determination module 220, and a second determination module 230, wherein:

[0092] In one embodiment of this application, the acquisition module 210 is specifically used to: acquire lane line detection results of the lower lane based on the image information acquired by the camera.

[0093] Roadside equipment is typically installed at intersections or along road sections to cover different areas. The cameras on roadside equipment usually monitor only one lane in the direction of traffic flow. Based on the image information captured by the camera, lane line detection results for the lane below the camera can be obtained. The detection range for the lane below the camera is related to the position of the camera pole and the camera's orientation; this application does not impose specific limitations, as long as the installation requirements of the roadside equipment are met.

[0094] The lane line detection results for the lower lane include the results of distinguishing between solid and dashed lines after lane line detection. Lane line detection can be performed using deep learning techniques with models trained on a large amount of labeled data. The specific deep convolutional neural network used is not specifically limited in the embodiments of this application.

[0095] The lane detection results obtained at this time do not distinguish the direction of traffic flow, but detect lane lines from all the available image information.

[0096] In one embodiment of this application, the first determining module 220 is specifically used to: determine the vehicle driving direction detection result or the curb detection result of the lower lane.

[0097] The detection of road edges is performed, and road edges are generally located next to the solid lane lines on both sides. It's understandable that both road edge detection and lane line detection utilize deep learning techniques to train models with large amounts of labeled data. The reason for detecting both road edges and lane lines is to accommodate situations where there are no lane lines or the lane lines are blurred. Road edge detection is used in these cases, and secondly, when lane lines are present, the perception range generally extends from the solid lane lines next to the road edge, so the road edge is used to determine the position of the solid lane lines.

[0098] Vehicle detection is primarily performed to match and track vehicles within multiple frames of detected images, thereby calculating their direction of travel on the image through stable tracking over consecutive frames. It's important to note that in road sections, because the camera's orientation is similar to the lane direction, there are generally only two traffic flow directions: outward and inward. Furthermore, in intersection areas, vehicles traveling laterally are filtered out, retaining only vehicles traveling in the inward and outward directions.

[0099] The determination of whether to use vehicle direction detection or curb detection results can be based on the actual detectable targets in the image information. For example, if a curb can be detected in the image information with high confidence, the curb detection result is used. Conversely, if vehicle detection across multiple frames is inaccurate and has low confidence, the curb detection result is used. Alternatively, if vehicle detection across multiple frames is relatively accurate and has high confidence, the vehicle direction detection result is used. Of course, if both detection methods are applicable, either one can be selected.

[0100] In one embodiment of this application, the second determining module 230 is specifically used to: determine the perception range of the camera based on the lane line detection result, combined with the vehicle driving direction detection result or the curb detection result of the lower lane.

[0101] The perception range of the camera is determined by combining the solid lane lines in the lane detection results with the vehicle driving direction detection results or the curb detection results.

[0102] For example, the solid lane lines of the left and right lanes can typically be extended across the image. Based on the extension of the lane lines, at least one region spanning the vertical direction of the image can be obtained; this region is the perception range. This range is then saved for subsequent object detection.

[0103] For example, the solid lane lines that can usually be detected are extended on the image, and multiple enclosing regions that run through the longitudinal direction of the image are obtained based on the extension results of the left and right solid lane lines. Then, based on the traffic flow direction perceived by the roadside equipment's camera, the image position of the vehicle that matches that direction is selected and compared with the enclosing region of the acquired solid lane lines.

[0104] It is understood that the aforementioned roadside equipment sensing range determination device can implement each step of the roadside equipment sensing range determination method provided in the foregoing embodiments. The relevant explanations of the roadside equipment sensing range determination method are applicable to the roadside equipment sensing range determination device, and will not be repeated here.

[0105] Figure 4 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Please refer to it. Figure 4 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and memory. The memory may include main memory, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk drive. Of course, the electronic device may also include other hardware required for other business operations.

[0106] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 4 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0107] Memory is used to store programs. Specifically, programs may include program code, which includes computer operation instructions. Memory may include main memory and non-volatile memory, and provides instructions and data to the processor.

[0108] The processor reads the corresponding computer program from non-volatile memory into main memory and then executes it, forming a roadside equipment sensing range determination device at the logical level. The processor executes the program stored in memory and specifically performs the following operations:

[0109] Based on the image information captured by the camera, the lane line detection result of the lower lane is obtained;

[0110] Determine the vehicle travel direction detection result or the curb detection result of the lane below;

[0111] Based on the lane line detection results, combined with the vehicle travel direction detection results or curb detection results of the lower lane, the perception range of the camera is determined.

[0112] The above is as stated in this application. Figure 1The method for determining the sensing range of roadside equipment disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The 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, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of this application can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0113] The electronic device can also perform Figure 1 The method for determining the sensing range of roadside equipment is described, and the method for implementing the sensing range determination device of roadside equipment is described. Figure 1 The functions of the embodiments shown are not described in detail here.

[0114] This application also proposes a computer-readable storage medium that stores one or more programs, the programs including instructions that, when executed by an electronic device including multiple applications, enable the electronic device to perform... Figure 1 The method executed by the roadside equipment sensing range determination device in the illustrated embodiment is specifically used to perform the following:

[0115] Based on the image information captured by the camera, the lane line detection result of the lower lane is obtained;

[0116] Determine the vehicle travel direction detection result or the curb detection result of the lane below;

[0117] Based on the lane line detection results, combined with the vehicle travel direction detection results or curb detection results of the lower lane, the perception range of the camera is determined.

[0118] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0119] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0120] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0121] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0122] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0123] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0124] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0125] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0126] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0127] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for determining the sensing range of roadside equipment, wherein, Applied to roadside equipment, wherein the roadside equipment includes at least a camera, the method includes: Based on the image information captured by the camera, the lane line detection result of the lower lane is obtained; Determine the vehicle travel direction detection result or the curb detection result of the lane below; Target detection is performed on the image information to obtain the curb detection result; The two right edges that meet the bottom edge of the image with the curb detection result are taken as the left curb and the right curb; The solid line of the left lane is determined by moving right from the left road edge, and the solid line of the right lane is determined by moving left from the right road edge. Based on the lane line detection results, combined with the vehicle driving direction detection results or roadside detection results of the lower lane, the perception range of the camera is determined. The step of determining the vehicle travel direction detection result in the lower lane based on the vehicle travel trajectory tracking record includes: The vehicle's driving direction in the image is calculated by tracking and detecting over multiple consecutive frames. The vehicle's driving direction in the image includes traffic flowing towards the top of the image, traffic flowing towards the bottom of the image, and traffic flowing laterally towards the image. After filtering out the lateral traffic flow in the orientation image, the vehicle trajectory tracking record in multiple frames of images is obtained based on the traffic flow above and below the orientation image. The trajectory tracking is recorded in the direction of the vehicle on the right side of the image, which is used as the detection result of the vehicle's driving direction in the lower lane; Based on the lane line detection results, combined with the vehicle travel direction detection results or curb detection results of the lower lane, the perception range of the camera is determined, including: Compare the area enclosed by the solid lane line in the lane line detection results with the vehicle positions that meet the preset traffic flow direction in the vehicle driving direction detection results. If the vehicle is located within the area enclosed by the solid lane line, then the area enclosed by the solid lane line is taken as the sensing range of the camera, wherein the sensing range of the camera includes one or more solid line ranges.

2. The method as described in claim 1, wherein, The determination of the vehicle travel direction detection result or curb detection result of the lower lane includes: Based on the image information, target matching and tracking are performed to obtain vehicle trajectory tracking records; Based on the vehicle trajectory tracking record, determine the vehicle driving direction detection result in the lower lane; And / or, Target detection is performed based on the image information to obtain the curb detection result, which is used to determine the solid lines of the left and right lanes in the lane line detection result.

3. The method as described in claim 1, wherein, The determination of the camera's sensing range based on the lane line detection results, combined with the vehicle travel direction detection results or curb detection results of the lower lane, includes: Based on the results of the solid lines of the left and right lanes in the lane detection results extending on the image, a region that runs through the vertical direction of the image is obtained. The camera's sensing range is determined based on the longitudinal region running through the image.

4. The method as described in claim 1, wherein, Based on the lane line detection results, combined with the vehicle travel direction detection results or curb detection results of the lower lane, the perception range of the camera is determined, including: If no lane lines are detected in the lane line detection results, then the region that runs through the vertical direction of the image is obtained based on the result of extending the curb detection results on the image. If the lane line found first from the left edge to the right is a dashed line, or the lane line found first from the right edge to the left is a dashed line, then the lane line detection result shall be taken as the solid lane line. If, after finding the left lane line from the left edge to the right and the right lane line from the right edge to the left, the right lane line is to the left of the left lane line, then the edge detection result shall be taken as the solid lane line.

5. The method according to any one of claims 1 to 4, wherein, The method further includes: The camera's sensing range is updated and determined according to a preset cycle, and the sensing range is divided according to different pixel values.

6. A device for determining the sensing range of roadside equipment, wherein, Applied to roadside equipment, the roadside equipment including at least a camera, the device comprising: The acquisition module is used to acquire the lane line detection results of the lower lane based on the image information captured by the camera; The first determining module is used to determine the vehicle driving direction detection result or the curb detection result of the lower lane; Target detection is performed on the image information to obtain the curb detection result; The two right edges that meet the bottom edge of the image with the curb detection result are taken as the left curb and the right curb; The solid line of the left lane is determined by moving right from the left road edge, and the solid line of the right lane is determined by moving left from the right road edge. The second determining module is used to determine the perception range of the camera based on the lane line detection results and in combination with the vehicle driving direction detection results or roadside detection results of the lower lane. The step of determining the vehicle travel direction detection result in the lower lane based on the vehicle travel trajectory tracking record includes: The vehicle's driving direction in the image is calculated by tracking and detecting over multiple consecutive frames. The vehicle's driving direction in the image includes traffic flowing towards the top of the image, traffic flowing towards the bottom of the image, and traffic flowing laterally towards the image. After filtering out the lateral traffic flow in the orientation image, the vehicle trajectory tracking record in multiple frames of images is obtained based on the traffic flow above and below the orientation image. The trajectory tracking is recorded in the direction of the vehicle on the right side of the image, which is used as the detection result of the vehicle's driving direction in the lower lane; Based on the lane line detection results, combined with the vehicle travel direction detection results or curb detection results of the lower lane, the perception range of the camera is determined, including: Compare the area enclosed by the solid lane line in the lane line detection results with the vehicle positions that meet the preset traffic flow direction in the vehicle driving direction detection results. If the vehicle is located within the area enclosed by the solid lane line, then the area enclosed by the solid lane line is taken as the sensing range of the camera, wherein the sensing range of the camera includes one or more solid line ranges.

7. A roadside device, comprising the roadside device sensing range determination device as described in claim 6.

Images