Obstacle distance information generation method, device, equipment and computer readable medium

Abstract

Embodiments of the present disclosure disclose an obstacle distance information generation method, device, equipment and computer readable medium. A specific implementation of the method comprises: acquiring a current time road image; performing obstacle detection on the current time road image to generate current time obstacle detection information, wherein the current time obstacle detection information comprises: obstacle type information, an obstacle detection bounding box equation set and an obstacle detection bounding box vertex coordinate set; in response to determining that the horizontal coordinate values of each obstacle detection bounding box vertex coordinate in the obstacle detection bounding box vertex coordinate set are all greater than the horizontal coordinate value of a preset camera optical center imaging point coordinate, generating a first target obstacle key point coordinate set based on the obstacle detection bounding box vertex coordinate set; and generating obstacle distance information based on the first target obstacle key point coordinate set and the obstacle type information. The implementation can generate obstacle distance information efficiently.

Description

Technical Field

[0001] The embodiments of this disclosure relate to the field of computer technology, and more specifically to methods, apparatus, devices, and computer-readable media for generating obstacle distance information. Background Technology

[0002] Obstacle distance information generation is a technique for determining the distance between obstacles and the current vehicle in an image. Currently, the common approach to generating obstacle distance information is as follows: first, distortion correction is performed on a road image captured by a wide-angle camera; then, obstacle distance information is identified from the distortion-corrected road image.

[0003] However, the inventors discovered that when generating obstacle distance information using the above method, the following technical problems often arise:

[0004] First, in continuous frames of road images, real-time distortion correction of road images requires a lot of computing resources, which reduces the efficiency of generating obstacle distance information.

[0005] Second, even if the distortion correction process does not affect the efficiency of obstacle distance information generation, the minimum bounding rectangle of the obstacle obtained by detecting the obstacle's front or parking space after distortion correction will no longer be the minimum bounding rectangle of the obstacle's front or parking space. Instead, it will become a detection box with pincushion distortion. If such a detection box is directly used to generate obstacle distance information, it is easy to introduce observation errors, which will increase the error of the generated obstacle distance information and thus reduce the accuracy of the generated obstacle distance information.

[0006] The information disclosed in this background section is only intended to enhance the understanding of the background of the inventive concept, and therefore may contain information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0007] The summary portion of this disclosure is intended to provide a brief overview of the concepts, which will be described in detail in the detailed description portion. This summary portion is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions.

[0008] Some embodiments of this disclosure provide methods, apparatus, devices, and computer-readable media for generating obstacle distance information to address one or more of the technical problems mentioned in the background section above.

[0009] In a first aspect, some embodiments of this disclosure provide a method for generating obstacle distance information. The method includes: acquiring a road image at a current time, wherein the road image at the current time is a distorted image; performing obstacle detection on the road image at the current time to generate obstacle detection information at the current time, wherein the obstacle detection information at the current time includes: obstacle type information, a set of obstacle detection bounding box equations, and a set of obstacle detection bounding box vertex coordinates; in response to determining that the abscissa value of each obstacle detection bounding box vertex coordinate in the set of obstacle detection bounding box vertex coordinates is greater than the abscissa value of a preset camera optical center imaging point coordinate, generating a first target obstacle key point coordinate set based on the set of obstacle detection bounding box vertex coordinates; and generating obstacle distance information based on the first target obstacle key point coordinate set and the obstacle type information.

[0010] Secondly, some embodiments of this disclosure provide an obstacle distance information generation apparatus, the apparatus comprising: an acquisition unit configured to acquire a road image at a current time, wherein the road image at the current time is a distorted image; a detection unit configured to perform obstacle detection on the road image at the current time to generate obstacle detection information at the current time, wherein the obstacle detection information at the current time includes: obstacle type information, an obstacle detection bounding box equation set, and an obstacle detection bounding box vertex coordinate set; a first generation unit configured to, in response to determining that the abscissa value of each obstacle detection bounding box vertex coordinate in the obstacle detection bounding box vertex coordinate set is greater than the abscissa value of a preset camera optical center imaging point coordinate, generate a first target obstacle key point coordinate set based on the obstacle detection bounding box vertex coordinate set; and a second generation unit configured to generate obstacle distance information based on the first target obstacle key point coordinate set and the obstacle type information.

[0011] Thirdly, some embodiments of this disclosure provide an electronic device, including: one or more processors; and a storage device having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation of the first aspect above.

[0012] Fourthly, some embodiments of this disclosure provide a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in any of the implementations of the first aspect above.

[0013] The above embodiments of this disclosure have the following beneficial effects: the obstacle distance information generation method of some embodiments of this disclosure can improve the efficiency of generating obstacle distance information. Specifically, the reason for the reduced efficiency of generating obstacle distance information is that in continuous frame road images, real-time distortion correction processing of the road image requires a lot of computing resources, thus leading to a reduction in the efficiency of generating obstacle distance information. Based on this, the obstacle distance information generation method of some embodiments of this disclosure first acquires the road image at the current moment. The road image at the current moment is a distorted image. Then, obstacle detection is performed on the road image at the current moment to generate obstacle detection information at the current moment. The obstacle detection information at the current moment includes: obstacle type information, obstacle detection bounding box equations, and obstacle detection bounding box vertex coordinates. Here, considering that distortion correction processing of the distorted image requires a lot of computing resources, distortion correction processing is not performed, and obstacle detection is performed directly. Next, in response to the determination that the abscissa values ​​of all obstacle detection bounding box vertices in the aforementioned obstacle detection bounding box vertex coordinate set are greater than the abscissa values ​​of the preset camera optical center imaging point coordinates, a first target obstacle key point coordinate set is generated based on the aforementioned obstacle detection bounding box vertex coordinate set. Generating the first target obstacle key point coordinates facilitates the generation of obstacle distance information. Finally, obstacle distance information is generated based on the aforementioned first target obstacle key point coordinate set and the aforementioned obstacle type information. Thus, obstacle distance information is generated without performing distortion correction processing on the image. Furthermore, this reduces the computational resources required for distortion correction processing, thereby improving the efficiency of generating obstacle distance information. Attached Figure Description

[0014] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and elements are not necessarily drawn to scale.

[0015] Figure 1 This is a flowchart of some embodiments of the obstacle distance information generation method according to the present disclosure;

[0016] Figure 2 This is a schematic diagram of the structure of some embodiments of the obstacle distance information generation device according to the present disclosure;

[0017] Figure 3 This is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. Detailed Implementation

[0018] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0019] It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.

[0020] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0021] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0022] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0023] This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0024] Figure 1 A flow 100 of some embodiments of an obstacle distance information generation method according to the present disclosure is shown. The obstacle distance information generation method includes the following steps:

[0025] Step 101: Obtain the road image at the current moment.

[0026] In some embodiments, the entity executing the obstacle distance information generation method can acquire the current-time road image via wired or wireless means. The current-time road image is a distorted image. Furthermore, the current-time road image can be an image captured by the vehicle-mounted camera in the current frame.

[0027] It should be noted that the aforementioned wireless connection methods may include, but are not limited to, 3G / 4G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other currently known or future wireless connection methods.

[0028] Step 102: Perform obstacle detection on the road image at the current time to generate obstacle detection information at the current time.

[0029] In some embodiments, the execution entity can perform obstacle detection on the current-time road image to generate obstacle detection information at the current time. This obstacle detection information may include: obstacle type information, obstacle detection bounding box equations, and obstacle detection bounding box vertex coordinates. Alternatively, a preset obstacle detection algorithm can be used to perform obstacle detection on the current-time road image to generate the current-time obstacle detection information. The obstacle type information may be the type of vehicle obstructing the obstacle. The obstacle detection bounding box equations may be the edge equations of each side on the obstacle's three-dimensional minimum bounding rectangle in the detected camera coordinate system. The obstacle detection bounding box vertex coordinates may be the vertex coordinates of the obstacle's two-dimensional minimum bounding rectangle (front or rear) in the image coordinate system of the detected road image.

[0030] As an example, obstacle detection algorithms may include, but are not limited to, at least one of the following: G-CRF (Gauss-conditional random field) model, DenseCRF (Fully-connected Conditional Random Fields) model, MRF (MRF-Markov Random Field) model, etc.

[0031] Step 103: In response to the determination that the abscissa value of each obstacle detection bounding box vertex coordinate in the obstacle detection bounding box vertex coordinate group is greater than the abscissa value of the preset camera optical center imaging point coordinate, a first target obstacle key point coordinate group is generated based on the obstacle detection bounding box vertex coordinate group.

[0032] In some embodiments, the execution entity may, in response to determining that the abscissa value of each obstacle detection bounding box vertex coordinate in the obstacle detection bounding box vertex coordinate group is greater than the abscissa value of a preset camera optical center imaging point coordinate, generate a first target obstacle key point coordinate group based on the obstacle detection bounding box vertex coordinate group. The camera optical center imaging point coordinate can be the coordinate of the optical center of the vehicle-mounted camera in the road image coordinate system. The fact that the abscissa value of each obstacle detection bounding box vertex coordinate in the obstacle detection bounding box vertex coordinate group is greater than the preset camera optical center imaging point coordinate indicates that the obstacle detection box is located in the right half of the road image coordinate system.

[0033] In some optional implementations of certain embodiments, the execution entity generates a first target obstacle key point coordinate set based on the obstacle detection bounding box vertex coordinate set, which may include the following steps:

[0034] The first step involves selecting the obstacle detection border vertex coordinates located at the upper left corner of the border from the obstacle detection border vertex coordinate set, in response to the determination that the set of obstacle detection border vertex coordinates satisfies the first preset position condition. The first preset position condition can be: the 2-norm of the difference between the ordinate of the obstacle detection border vertex coordinate at the lower left corner of the corresponding two-dimensional minimum bounding rectangle and the ordinate of the camera optical center imaging point; the 2-norm of the difference between the ordinate of the obstacle detection border vertex coordinate at the upper left corner of the corresponding two-dimensional minimum bounding rectangle and the ordinate of the camera optical center imaging point; and the ordinate of the obstacle detection border vertex coordinate at the lower left corner of the corresponding two-dimensional minimum bounding rectangle being greater than or equal to the ordinate of the camera optical center imaging point, and the ordinate of the camera optical center imaging point being greater than or equal to the ordinate of the obstacle detection border vertex coordinate at the upper left corner of the corresponding two-dimensional minimum bounding rectangle. The obstacle detection bounding box vertex coordinates satisfy the first preset position condition, which can characterize that the upper edge of the two-dimensional minimum bounding rectangle is above the midline (i.e., the horizontal line where the ordinate of the camera optical center imaging point is located), the lower edge is below the midline, and the upper edge intersects the midline with the lower edge being farther from the midline.

[0035] In practice, under the aforementioned first preset position condition, the boundary vertex coordinates with minimal image distortion impact can be the boundary vertex coordinates of the obstacle detection boundary located at the upper left corner of the boundary. Therefore, these coordinates are selected as the filtering boundary vertex coordinates. Furthermore, when generating obstacle distance information, it is necessary to assume that the viewing direction of the vehicle-mounted (forward-looking) camera is horizontal or approximately horizontal to the ground, i.e., the viewing direction is approximately perpendicular to the front and rear of the obstacle.

[0036] The second step involves projecting the obstacle detection bounding box equation corresponding to the right bounding box in the aforementioned obstacle detection bounding box equation set onto the image coordinate system of the road image to generate the first projected detection bounding box curve equation. The obstacle detection bounding box equation corresponding to the right bounding box in the obstacle detection bounding box equation set can be the equation of the right edge line on the front rectangle of the 3D detection box. Furthermore, the obstacle detection bounding box equation can be projected from the camera coordinate system to the image coordinate system using an inverse projection transformation.

[0037] The third step is to determine the right bounding box equation for the two obstacle detection bounding box vertices located at the upper right and lower right corners of the bounding box, as described above. Specifically, the equation of the line connecting the two obstacle detection bounding box vertices at the upper left and lower right corners of the corresponding two-dimensional minimum bounding rectangle can be determined using a two-point equation; this line serves as the right bounding box equation.

[0038] Fourth, the coordinates of the intersection point of the first projected detection bounding box curve equation and the right bounding box equation are determined as the key point coordinates of the detection box. The abscissa of the key point coordinates is the same as the abscissa of the obstacle detection bounding box vertex at the upper right corner of the corresponding two-dimensional minimum bounding rectangle. The ordinate of the key point coordinates can be the same as the ordinate of the camera optical center imaging point.

[0039] The fifth step is to determine the coordinates of the vertex of the above-mentioned filtering border and the coordinates of the key points of the above-mentioned detection box as the coordinates of the key points of the first target obstacle, so as to generate the coordinate set of the key points of the first target obstacle.

[0040] Step 104: Generate obstacle distance information based on the coordinates of the key points of the first target obstacle and the obstacle type information.

[0041] In some embodiments, the executing entity can generate obstacle distance information based on the coordinate set of key points of the first target obstacle and the obstacle type information. First, the target obstacle width and height values ​​corresponding to the obstacle type information can be obtained from a preset obstacle data table. The obstacle data table may include various types of standard obstacles and their corresponding size information.

[0042] Secondly, obstacle distance values ​​can be generated as obstacle distance information using the following formula:

[0043] .

[0044] in, This indicates the distance to the obstacle. This represents the width of the target obstacle. This indicates the lateral focal length of the vehicle-mounted camera. This indicates the preset distortion correction operation. This indicates the coordinates of the key points of the first target obstacle. This indicates the coordinates of the first target obstacle key point, which corresponds to the vertex coordinates of the filter border in the first target obstacle key point coordinate group. The x-coordinate value of the key point coordinates of the first target obstacle, which corresponds to the key point coordinates of the detection box in the key point coordinate group of the first target obstacle. The ordinate value of the first target obstacle key point coordinates is the coordinate of the key point corresponding to the detection box in the first target obstacle key point coordinate group, which is equal to the ordinate value of the camera optical center imaging point coordinate. This indicates taking the first element of the vector within the parentheses.

[0045] Optionally, in response to determining that the above-mentioned obstacle detection bounding box vertex coordinate set satisfies the second preset position condition, obstacle distance information is generated based on the above-mentioned obstacle detection bounding box vertex coordinate set, the above-mentioned target obstacle width value, and the above-mentioned camera optical center imaging point coordinates. The above-mentioned second preset condition may be: in the obstacle detection bounding box vertex coordinate set, the 2-norm of the difference between the ordinate value of the obstacle detection bounding box vertex at the lower left corner of the two-dimensional minimum bounding rectangle and the ordinate value of the camera optical center imaging point; greater than or equal to the 2-norm of the difference between the ordinate value of the obstacle detection bounding box vertex at the upper left corner of the two-dimensional minimum bounding rectangle and the ordinate value of the camera optical center imaging point; and the ordinate value of the obstacle detection bounding box vertex at the lower left corner of the two-dimensional minimum bounding rectangle being greater than or equal to the ordinate value of the camera optical center imaging point, and the ordinate value of the camera optical center imaging point being greater than or equal to the ordinate value of the obstacle detection bounding box vertex at the upper left corner of the two-dimensional minimum bounding rectangle. The obstacle detection bounding box vertex coordinates satisfying the second preset position condition can be characterized by the top edge of the two-dimensional minimum bounding rectangle being above the midline (i.e., the horizontal line containing the ordinate of the camera's optical center imaging point), the bottom edge being below the midline, and the top edge intersecting the midline while the bottom edge is closer to the midline. In practice, under the condition of satisfying the above second preset position condition, the bounding box vertex coordinates with less image distortion impact can be the obstacle detection bounding box vertex coordinates located at the upper right corner of the bounding box. Therefore, this coordinate is selected as the filtering bounding box vertex coordinate.

[0046] Specifically, firstly, the obstacle detection bounding box equation corresponding to the left bounding box in the above obstacle detection bounding box equation set can be projected onto the image coordinate system of the road image to generate the first projected detection bounding box curve equation. Next, the left bounding box equation is determined for the coordinates of the two obstacle detection bounding box vertices located at the upper left and lower left corners of the bounding box. Then, the coordinates of the intersection of the first projected detection bounding box curve equation and the left bounding box equation are determined as the key point coordinates of the detection box. Then, the coordinates of the filtering bounding box vertices and the key point coordinates of the detection box are determined as the key point coordinates of the first target obstacle to generate the first target obstacle key point coordinate set. Finally, obstacle distance information is generated based on the first target obstacle key point coordinate set and the obstacle type information using the above formula. Here, the method for generating obstacle distance information is the same as that in the embodiments of steps 103-104 above, and will not be described in detail again.

[0047] Optionally, in response to determining that the above-mentioned obstacle detection bounding box vertex coordinate set satisfies a third preset position condition, obstacle distance information is generated based on the above-mentioned obstacle detection bounding box vertex coordinate set, the above-mentioned target obstacle width value, the above-mentioned target obstacle height value, and the above-mentioned camera optical center imaging point coordinates. The third preset position condition may be: the ordinate value of the obstacle detection bounding box vertex coordinates corresponding to the lower left corner of the two-dimensional minimum bounding rectangle is greater than or equal to the ordinate value of the obstacle detection bounding box vertex coordinates corresponding to the upper left corner of the two-dimensional minimum bounding rectangle, and the ordinate value of the obstacle detection bounding box vertex coordinates corresponding to the upper left corner of the two-dimensional minimum bounding rectangle is greater than or equal to the ordinate value of the camera optical center imaging point coordinates. The obstacle detection bounding box vertex coordinate set satisfying the third preset position condition indicates that the entire two-dimensional minimum bounding rectangle is below the ordinate value of the camera optical center imaging point coordinates. In practice, when the above-mentioned third preset position condition is satisfied, the bounding box vertex coordinates with less image distortion impact may be the obstacle detection bounding box vertex coordinates located at the lower left and upper right corners of the bounding box. Therefore, obstacle distance values ​​can be generated using the following formula to serve as obstacle distance information:

[0048] .

[0049] in, Let represent the objective function that minimizes the distance to obstacles. Here, It can be a preset initial distance value. This indicates the longitudinal focal length of the vehicle-mounted camera. This indicates the height value of the aforementioned target obstacle. This indicates the error value. This represents the preset size error covariance matrix. This represents the Mahalanobis distance. This indicates the bottom left corner position. This indicates the top right corner position. This represents the coordinates of the lower left corner vertex of the obstacle detection border in the above obstacle detection border vertex coordinate group. This represents the coordinates of the top right corner of the obstacle detection bounding box in the above obstacle detection bounding box vertex coordinate group.

[0050] Optionally, the aforementioned implementing entity may also perform the following steps:

[0051] The first step involves generating a second set of target obstacle keypoint coordinates based on the obstacle detection bounding box vertex coordinates. Since the abscissa values ​​of all obstacle detection bounding box vertices in the aforementioned obstacle detection bounding box vertex coordinate set are less than the abscissa values ​​of the camera optical center imaging point coordinates, the fact that the abscissa values ​​of all obstacle detection bounding box vertices in the obstacle detection bounding box vertex coordinate set are less than the abscissa values ​​of the camera optical center imaging point coordinates indicates that the obstacle detection box is located in the left half of the road image coordinate system. Therefore, the 2D minimum bounding rectangle relative to the ordinate values ​​of the camera optical center imaging point coordinates also has three possible positions: 1) The 2D minimum bounding rectangle intersects the horizontal line containing the ordinate value of the camera optical center imaging point coordinates, and the upper edge of the 2D minimum bounding rectangle is far from the horizontal line containing the ordinate value. 2) The 2D minimum bounding rectangle intersects the horizontal line containing the ordinate value of the camera optical center imaging point coordinates, and the lower edge of the 2D minimum bounding rectangle is far from the horizontal line containing the ordinate value. The case where the smallest 2D bounding rectangle is completely below the horizontal line containing the ordinate of the camera's optical center imaging point.

[0052] In practice, for the first positional scenario, the vertex coordinates of the bounding box with minimal image distortion can be the vertex coordinates of the obstacle detection bounding box located at the upper right corner of the bounding box. Furthermore, the process of generating the second set of target obstacle keypoint coordinates can be the same as the method described above for generating the second set of target obstacle keypoint coordinates when the second preset positional condition is met, and will not be elaborated further. For the second positional scenario, the vertex coordinates of the bounding box with minimal image distortion can be the vertex coordinates of the obstacle detection bounding box located at the upper left corner of the bounding box. Furthermore, the process of generating the second set of target obstacle keypoint coordinates can be the same as the method described above for generating the second set of target obstacle keypoint coordinates when the first preset positional condition is met, and will not be elaborated further. Here, for the third positional scenario, the vertex coordinates of the bounding box with minimal image distortion can be the vertex coordinates of the obstacle detection bounding box located at the lower right and upper left corners of the bounding box.

[0053] Optionally, the execution entity may generate a second set of key point coordinates for the target obstacle based on the aforementioned set of obstacle detection bounding box vertex coordinates, which may include the following:

[0054] The first step is to select the coordinates of the top right corner of the obstacle detection border from the set of coordinates of the obstacle detection border vertex in response to the determination that the set of coordinates of the obstacle detection border vertex satisfies the first preset position condition, and use them as the vertex coordinates of the filtering border.

[0055] The second step is to project the obstacle detection bounding box equation corresponding to the left bounding box in the above obstacle detection bounding box equation set onto the image coordinate system of the above road image to generate the second projected detection bounding box curve equation.

[0056] The third step is to determine the equation of the left border for the two obstacle detection border vertex coordinates located at the top left and bottom left corners of the border from the above obstacle detection border vertex coordinate group.

[0057] The fourth step is to determine the coordinates of the intersection of the second projection detection border curve equation and the left border equation as the key point coordinates of the detection box.

[0058] The fifth step is to determine the coordinates of the vertex of the above-mentioned filtering border and the coordinates of the key points of the above-mentioned detection box as the coordinates of the key points of the second target obstacle, so as to generate the coordinate set of the key points of the second target obstacle.

[0059] In some embodiments, the specific implementation methods of the first to fifth steps above and the resulting technical effects can be referred to the embodiments in step 103 above, and will not be described in detail here.

[0060] The second step involves generating obstacle distance information based on the aforementioned key point coordinates of the second target obstacle and the obstacle type information. For the first location scenario, the method for generating obstacle distance information and its resulting technical effects can be referenced from the steps after the obstacle detection bounding box vertex coordinates satisfy the second preset position condition, and will not be elaborated further. For the second location scenario, the method for generating obstacle distance information and its resulting technical effects can be referenced from the steps in the embodiments corresponding to steps 103-104, and will not be elaborated further. For the third location scenario, obstacle distance information can be generated using the aforementioned second formula.

[0061] Optionally, the aforementioned implementing entity may also perform the following steps:

[0062] The first step involves determining the coordinates of obstacle detection border vertices in the aforementioned obstacle detection border vertex coordinate set that simultaneously contain x-coordinate values ​​greater than and less than the x-coordinate values ​​of the camera optical center imaging point, and the coordinates of obstacle detection border vertices in the aforementioned obstacle detection border vertex coordinate set that simultaneously contain y-coordinate values ​​greater than and less than the y-coordinate values ​​of the camera optical center imaging point. Then, each obstacle detection border equation in the aforementioned obstacle detection border equation set is projected onto the image coordinate system of the aforementioned road image to generate a third projected detection border curve equation set. Specifically, the obstacle detection border vertex coordinates in the obstacle detection border vertex coordinate set that simultaneously contain x-coordinate values ​​greater than and less than the x-coordinate values ​​of the camera optical center imaging point represent that the two-dimensional minimum bounding rectangle is located in the middle position of the road image. The obstacle detection border vertex coordinates in the obstacle detection border vertex coordinate set that simultaneously contain y-coordinate values ​​greater than and less than the y-coordinate values ​​of the camera optical center imaging point represent that the upper edge of the two-dimensional minimum bounding rectangle is above the midline (i.e., the x-line containing the y-coordinate of the camera optical center imaging point) and the lower edge is below the midline. Secondly, the obstacle detection bounding box equation can be projected from the camera coordinate system to the image coordinate system through inverse projection transformation.

[0063] The second step involves generating a set of obstacle detection box edge equations based on the vertex coordinates of each obstacle detection bounding box in the aforementioned set of obstacle detection bounding box vertex coordinates. Specifically, for each side of the two-dimensional minimum bounding rectangle, the obstacle detection box edge equation can be generated using the corresponding two obstacle detection bounding box vertex coordinates and a two-point formula.

[0064] The third step involves determining the coordinates of the intersection point between the obstacle detection edge line equation corresponding to the upper border position in the aforementioned obstacle detection edge line equation set and the third projected detection border curve equation corresponding to the upper border position in the aforementioned third projected detection border curve equation set. These intersection points are then used as the coordinates of the key points in the first detection frame. Specifically, the abscissa of the key point coordinates in the first detection frame is the same as the abscissa of the obstacle detection border vertex at the lower left corner of the corresponding two-dimensional minimum bounding rectangle. The ordinate of the key point coordinates in the first detection frame can be the same as the ordinate of the aforementioned camera optical center imaging point coordinates.

[0065] The fourth step involves determining the coordinates of the intersection point between the obstacle detection edge line equation corresponding to the lower border position in the aforementioned obstacle detection edge line equation set and the third projected detection border curve equation corresponding to the lower border position in the aforementioned third projected detection border curve equation set. These intersection points are then used as the coordinates of the key points in the second detection box. The abscissa of the key point coordinates in the second detection box can be the same as the abscissa of the obstacle detection border vertex at the lower right corner of the corresponding two-dimensional minimum bounding rectangle. The ordinate of the key point coordinates in the second detection box can be the same as the ordinate of the camera optical center imaging point coordinates.

[0066] The fifth step involves determining the coordinates of the intersection point between the obstacle detection edge line equation corresponding to the left border position in the aforementioned obstacle detection edge line equation set and the third projected detection border curve equation corresponding to the front left border position in the aforementioned third projected detection border curve equation set. These intersection points are then used as the coordinates of the key points in the third detection box. The abscissa of the key point coordinates in the third detection box can be the same as the abscissa of the camera optical center imaging point coordinates. The ordinate of the key point coordinates in the third detection box can be the same as the ordinate of the obstacle detection border vertex coordinates corresponding to the upper left corner of the two-dimensional minimum bounding rectangle.

[0067] Step 6: Determine the coordinates of the intersection point between the obstacle detection edge line equation corresponding to the right frame position in the above obstacle detection edge line equation set and the third projected detection border curve equation corresponding to the rear right frame position in the above third projected detection border curve equation set. These coordinates will be used as the key point coordinates of the fourth detection frame. The abscissa of the key point coordinates of the fourth detection frame can be the same as the abscissa of the camera optical center imaging point coordinates. The ordinate of the key point coordinates of the fourth detection frame can be the same as the ordinate of the obstacle detection border vertex coordinates corresponding to the lower left corner of the two-dimensional minimum bounding rectangle.

[0068] In practice, under the above conditions, the coordinates with minimal image distortion impact when positioning the 2D minimum bounding rectangle can be the following four: the coordinates of the tangent point in the distorted image where the top edge of the 2D minimum bounding rectangle projects onto the curve of the front top edge of the 3D minimum bounding rectangle; the coordinates of the tangent point in the distorted image where the bottom edge of the 2D minimum bounding rectangle projects onto the curve of the rear bottom edge of the 3D minimum bounding rectangle; the coordinates of the tangent point in the distorted image where the left edge of the 2D minimum bounding rectangle projects onto the curve of the front left edge of the 3D minimum bounding rectangle; and the coordinates of the tangent point in the distorted image where the right edge of the 2D minimum bounding rectangle projects onto the curve of the rear right edge of the 3D minimum bounding rectangle.

[0069] Step 7: Based on the key point coordinates of the first, second, third, and fourth detection boxes, and the obstacle type information, generate obstacle distance information. The obstacle distance value can be generated as obstacle distance information using the following formula:

[0070] .

[0071] in, This represents the coordinates of the key points in the first detection box after distortion removal. This represents the coordinates of the key points in the second detection frame after distortion removal. This represents the coordinates of the key points in the third detection frame after distortion removal. This represents the coordinates of the key points in the fourth detection frame after distortion removal. This represents the x-coordinate value of the key point coordinates in the first detection box. This represents the x-coordinate value of the key point coordinates in the second detection frame. This represents the ordinate value of the key point coordinates in the third detection frame. This represents the ordinate value of the key point coordinates in the fourth detection frame. This represents the x-coordinate of the camera's optical center imaging point.

[0072] Optionally, the aforementioned implementing entity may also perform the following steps:

[0073] The first step involves determining the obstacle detection bounding box vertex coordinates that simultaneously contain x-coordinates greater than and less than the x-coordinates of the camera optical center imaging point, and the obstacle detection bounding box vertex coordinates where all vertex coordinates are greater than the y-coordinates of the camera optical center imaging point. Then, the obstacle detection bounding box vertex coordinates located at the upper left and upper right corners of the bounding box are selected as the filtered bounding box vertex coordinate group. Specifically, the condition that all vertex coordinates in the obstacle detection bounding box vertex coordinate group are greater than the y-coordinates of the camera optical center imaging point indicates that all two-dimensional minimum bounding boxes are located below the midline. The bounding box vertex coordinates with minimal image distortion can be the upper left and upper right corner vertex coordinates of the two-dimensional minimum bounding box.

[0074] The second step involves generating obstacle distance information based on the aforementioned filtered border vertex coordinate group and obstacle type information. The obstacle distance value can be generated using the following formula:

[0075] .

[0076] in, This indicates the coordinates of the top-left corner of the filter border vertex in the filter border vertex coordinate group. This indicates the vertex coordinates of the filter border corresponding to the upper right corner of the filter border vertex coordinate group.

[0077] The above formulas and related contents serve as an inventive point of this disclosure, solving the second technical problem mentioned in the background: "Even if the distortion removal process does not affect the efficiency of obstacle distance information generation, the minimum bounding rectangle of the obstacle obtained by obstacle box detection in the distorted road image will no longer be the minimum bounding rectangle of the obstacle's front or parking space after distortion removal, but will become a detection box with pincushion distortion. If such a detection box is directly used to generate obstacle distance information, it is easy to introduce observation errors, which will increase the error of the generated obstacle distance information, thereby reducing the accuracy of the generated obstacle distance information." Factors that reduce the accuracy of generated obstacle distance information often include: even if the distortion correction process does not affect the efficiency of obstacle distance information generation, the minimum bounding rectangle of obstacles obtained from obstacle bounding box detection in distorted road images will no longer be the distorted minimum bounding rectangle of the obstacle's front or parking space after distortion correction, but will become a detection box with pincushion distortion. If such a detection box is directly used to generate obstacle distance information, it is easy to introduce observation errors, leading to an increase in the error of the generated obstacle distance information. If the above factors are solved, the accuracy of the generated obstacle distance information can be improved. To achieve this effect, firstly, by distinguishing the positional relationship between the two-dimensional minimum bounding rectangle detected from the road image and the horizontal and vertical lines corresponding to the camera's optical center imaging point coordinates, the vertex coordinates of the obstacle detection bounding box with the least distortion influence, or other coordinates on the two-dimensional minimum bounding rectangle, can be selected from the obstacle detection bounding box vertex coordinate set. This greatly eliminates the influence of the undistorted road image on the obstacle distance information generation process, reducing the error of the generated obstacle distance. Furthermore, corresponding formulas are introduced for different location scenarios to further remove the effects of distortion. Here, since distortion correction is performed on only a small number of coordinates, not only is the consumption of computational resources greatly reduced, but the error in the generated obstacle distances is also further reduced. Thus, the accuracy of the generated obstacle distance information is significantly improved.

[0078] Optionally, the aforementioned execution entity may also send the obstacle distance information to a display terminal for display.

[0079] The above embodiments of this disclosure have the following beneficial effects: the obstacle distance information generation method of some embodiments of this disclosure can improve the efficiency of generating obstacle distance information. Specifically, the reason for the reduced efficiency of generating obstacle distance information is that in continuous frame road images, real-time distortion correction processing of the road image requires a lot of computing resources, thus leading to a reduction in the efficiency of generating obstacle distance information. Based on this, the obstacle distance information generation method of some embodiments of this disclosure first acquires the road image at the current moment. The road image at the current moment is a distorted image. Then, obstacle detection is performed on the road image at the current moment to generate obstacle detection information at the current moment. The obstacle detection information at the current moment includes: obstacle type information, obstacle detection bounding box equations, and obstacle detection bounding box vertex coordinates. Here, considering that distortion correction processing of the distorted image requires a lot of computing resources, distortion correction processing is not performed, and obstacle detection is performed directly. Next, in response to the determination that the abscissa values ​​of all obstacle detection bounding box vertices in the aforementioned obstacle detection bounding box vertex coordinate set are greater than the abscissa values ​​of the preset camera optical center imaging point coordinates, a first target obstacle key point coordinate set is generated based on the aforementioned obstacle detection bounding box vertex coordinate set. Generating the first target obstacle key point coordinates facilitates the generation of obstacle distance information. Finally, obstacle distance information is generated based on the aforementioned first target obstacle key point coordinate set and the aforementioned obstacle type information. Thus, obstacle distance information is generated without performing distortion correction processing on the image. Furthermore, this reduces the computational resources required for distortion correction processing, thereby improving the efficiency of generating obstacle distance information.

[0080] Further reference Figure 2 As an implementation of the methods shown in the above figures, this disclosure provides some embodiments of an obstacle distance information generation device, which are similar to... Figure 1 Corresponding to the method embodiments shown, the device can be specifically applied to various electronic devices.

[0081] like Figure 2As shown, an obstacle distance information generation device 200 in some embodiments includes: an acquisition unit 201, a detection unit 202, a first generation unit 203, and a second generation unit 204. The acquisition unit 201 is configured to acquire a road image at a current time, wherein the road image at the current time is a distorted image; the detection unit 202 is configured to perform obstacle detection on the road image at the current time to generate obstacle detection information at the current time, wherein the obstacle detection information at the current time includes: obstacle type information, an obstacle detection bounding box equation set, and an obstacle detection bounding box vertex coordinate set; the first generation unit 203 is configured to generate a first target obstacle key point coordinate set based on the obstacle detection bounding box vertex coordinate set in response to determining that the abscissa value of each obstacle detection bounding box vertex coordinate in the obstacle detection bounding box vertex coordinate set is greater than the abscissa value of a preset camera optical center imaging point coordinate; the second generation unit 204 is configured to generate obstacle distance information based on the first target obstacle key point coordinate set and the obstacle type information.

[0082] It is understandable that the units described in the device 200 are related to the reference. Figure 1 The steps in the described method correspond to each other. Therefore, the operations, features, and beneficial effects described above for the method also apply to the device 200 and the units contained therein, and will not be repeated here.

[0083] The following is for reference. Figure 3 It shows a schematic diagram of the structure of an electronic device 300 suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this disclosure.

[0084] like Figure 3 As shown, the electronic device 300 may include a processing unit 301 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. The RAM 303 also stores various programs and data required for the operation of the electronic device 300. The processing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0085] Typically, the following devices can be connected to I / O interface 305: input devices 306 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 307 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 308 including, for example, magnetic tapes, hard disks, etc.; and communication devices 309. Communication device 309 allows electronic device 300 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 3 An electronic device 300 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 3 Each box shown can represent a device or multiple devices as needed.

[0086] In particular, according to some embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 309, or installed from storage device 308, or installed from ROM 302. When the computer program is executed by processing device 301, it performs the functions defined in the methods of some embodiments of this disclosure.

[0087] It should be noted that, in some embodiments of this disclosure, the computer-readable medium described above may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In some embodiments of this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0088] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0089] The aforementioned computer-readable medium may be included in the aforementioned device; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: acquire a road image at a current time, wherein the road image at the current time is a distorted image; perform obstacle detection on the road image at the current time to generate obstacle detection information at the current time, wherein the obstacle detection information at the current time includes: obstacle type information, a set of obstacle detection bounding box equations, and a set of obstacle detection bounding box vertex coordinates; in response to determining that the abscissa value of each obstacle detection bounding box vertex coordinate in the obstacle detection bounding box vertex coordinate set is greater than the abscissa value of a preset camera optical center imaging point coordinate, generate a first target obstacle key point coordinate set based on the obstacle detection bounding box vertex coordinate set; and generate obstacle distance information based on the first target obstacle key point coordinate set and the obstacle type information.

[0090] Computer program code for performing operations of some embodiments of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0091] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0092] The units described in some embodiments of this disclosure can be implemented in software or hardware. The described units can also be housed in a processor; for example, a processor may be described as including an acquisition unit, a detection unit, a first generation unit, and a second generation unit. The names of these units do not necessarily limit the specific unit; for example, the acquisition unit may also be described as "a unit that acquires a road image at the current time."

[0093] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0094] The above description is merely a selection of preferred embodiments of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in the embodiments of this disclosure.

Claims

1. A method for generating obstacle distance information, comprising: Obtain the road image at the current moment, wherein the road image at the current moment is a distorted image; Obstacle detection is performed on the road image at the current time to generate obstacle detection information at the current time, wherein the obstacle detection information at the current time includes: obstacle type information, obstacle detection bounding box equation set, and obstacle detection bounding box vertex coordinate set; In response to determining that the abscissa value of each obstacle detection bounding box vertex coordinate in the obstacle detection bounding box vertex coordinate group is greater than the abscissa value of the preset camera optical center imaging point coordinate, a first target obstacle key point coordinate group is generated based on the obstacle detection bounding box vertex coordinate group. Based on the coordinate set of the key points of the first target obstacle and the obstacle type information, obstacle distance information is generated; The step of generating the first target obstacle key point coordinate set based on the obstacle detection bounding box vertex coordinate set includes: In response to determining that the set of vertex coordinates of the obstacle detection border satisfies the first preset position condition, the vertex coordinates of the obstacle detection border located at the upper left corner of the border are selected from the set of vertex coordinates of the obstacle detection border as the vertex coordinates of the filtering border. Project the obstacle detection bounding box equation corresponding to the right bounding box in the obstacle detection bounding box equation set onto the image coordinate system of the road image to generate the first projected detection bounding box curve equation. Determine the right bounding box equation for the coordinates of two obstacle detection bounding box vertices located at the upper right and lower right corners of the bounding box in the obstacle detection bounding box vertex coordinate group; The coordinates of the intersection point of the first projected detection border curve equation and the right border equation are determined as the coordinates of the key points of the detection box. The vertex coordinates of the filtering border and the key point coordinates of the detection box are respectively determined as the key point coordinates of the first target obstacle to generate the key point coordinate group of the first target obstacle; The method further includes: In response to determining that the abscissa value of each obstacle detection bounding box vertex coordinate in the obstacle detection bounding box vertex coordinate group is less than the abscissa value of the camera optical center imaging point coordinate, a second target obstacle key point coordinate group is generated based on the obstacle detection bounding box vertex coordinate group. Based on the coordinates of the key points of the second target obstacle and the obstacle type information, obstacle distance information is generated.

2. The method according to claim 1, wherein, The method further includes: The obstacle distance information is sent to the display terminal for display.

3. The method according to claim 1, wherein, The step of generating a second target obstacle key point coordinate set based on the obstacle detection bounding box vertex coordinate set includes: In response to determining that the set of vertex coordinates of the obstacle detection border satisfies the first preset position condition, the vertex coordinates of the obstacle detection border located at the upper right corner of the border are selected from the set of vertex coordinates of the obstacle detection border as the vertex coordinates of the filter border. Project the obstacle detection bounding box equation corresponding to the left bounding box in the obstacle detection bounding box equation set onto the image coordinate system of the road image to generate the second projected detection bounding box curve equation. Determine the equation of the left border for the two obstacle detection border vertex coordinates located at the upper left and lower left corners of the border from the obstacle detection border vertex coordinate group; The coordinates of the intersection point of the second projected detection border curve equation and the left border equation are determined as the coordinates of the key points of the detection box; The vertex coordinates of the filtering border and the key point coordinates of the detection box are respectively determined as the key point coordinates of the second target obstacle to generate the key point coordinate group of the second target obstacle.

4. The method according to claim 1, wherein, The method further includes: In response to determining that the obstacle detection bounding box vertex coordinates in the obstacle detection bounding box vertex coordinate set have x-coordinate values ​​that are both greater than and less than the x-coordinate values ​​of the camera optical center imaging point, and the obstacle detection bounding box vertex coordinates in the obstacle detection bounding box vertex coordinate set have y-coordinate values ​​that are both greater than and less than the y-coordinate values ​​of the camera optical center imaging point, each obstacle detection bounding box equation in the obstacle detection bounding box equation set is projected onto the image coordinate system of the road image to generate a third projected detection bounding box curve equation set; Based on the vertex coordinates of each obstacle detection bounding box in the obstacle detection bounding box vertex coordinate group, generate a set of obstacle detection bounding box edge line equations; The coordinates of the intersection point of the obstacle detection edge line equation corresponding to the upper border position in the obstacle detection edge line equation set and the third projection detection border curve equation corresponding to the front upper border position in the third projection detection border curve equation set are determined as the coordinates of the key point of the first detection box. The coordinates of the intersection point of the obstacle detection edge line equation corresponding to the lower border position in the obstacle detection edge line equation set and the third projection detection border curve equation corresponding to the lower border position in the third projection detection border curve equation set are determined and used as the coordinates of the key points of the second detection box. The coordinates of the intersection point of the obstacle detection edge line equation corresponding to the left border position in the obstacle detection edge line equation set and the third projection detection border curve equation corresponding to the front left border position in the third projection detection border curve equation set are used as the coordinates of the key points of the third detection box. The coordinates of the intersection point of the obstacle detection edge line equation corresponding to the right frame position in the obstacle detection edge line equation set and the third projection detection border curve equation corresponding to the rear right frame position in the third projection detection border curve equation set are determined and used as the coordinates of the key point of the fourth detection frame. Based on the key point coordinates of the first detection box, the key point coordinates of the second detection box, the key point coordinates of the third detection box, the key point coordinates of the fourth detection box, and the obstacle type information, obstacle distance information is generated.

5. The method according to claim 1, wherein, The method further includes: In response to determining that there are obstacle detection border vertex coordinates in the obstacle detection border vertex coordinate group that simultaneously have x-coordinate values ​​greater than and less than the x-coordinate values ​​of the camera optical center imaging point coordinates, and that the y-coordinate values ​​of each obstacle detection border vertex coordinate in the obstacle detection border vertex coordinate group are all greater than the y-coordinate values ​​of the camera optical center imaging point coordinates, the obstacle detection border vertex coordinates located at the upper left and upper right corners of the border are selected from the obstacle detection border vertex coordinate group as the filter border vertex coordinate group; Based on the set of vertex coordinates of the filtered border and the obstacle type information, obstacle distance information is generated.

6. An obstacle distance information generation device, comprising: The acquisition unit is configured to acquire a road image at the current time, wherein the road image at the current time is a distorted image; The detection unit is configured to perform obstacle detection on the road image at the current time to generate obstacle detection information at the current time, wherein the obstacle detection information at the current time includes: obstacle type information, obstacle detection bounding box equation set, and obstacle detection bounding box vertex coordinate set; The first generation unit is configured to generate a first target obstacle key point coordinate group based on the obstacle detection frame vertex coordinate group in response to determining that the abscissa value of each obstacle detection frame vertex coordinate in the obstacle detection frame vertex coordinate group is greater than the abscissa value of the preset camera optical center imaging point coordinate. The second generation unit is configured to generate obstacle distance information based on the first target obstacle key point coordinate group and the obstacle type information; The step of generating the first target obstacle key point coordinate set based on the obstacle detection bounding box vertex coordinate set includes: In response to determining that the set of vertex coordinates of the obstacle detection border satisfies the first preset position condition, the vertex coordinates of the obstacle detection border located at the upper left corner of the border are selected from the set of vertex coordinates of the obstacle detection border as the vertex coordinates of the filtering border. Project the obstacle detection bounding box equation corresponding to the right bounding box in the obstacle detection bounding box equation set onto the image coordinate system of the road image to generate the first projected detection bounding box curve equation. Determine the right bounding box equation for the coordinates of two obstacle detection bounding box vertices located at the upper right and lower right corners of the bounding box in the obstacle detection bounding box vertex coordinate group; The coordinates of the intersection point of the first projected detection border curve equation and the right border equation are determined as the coordinates of the key points of the detection box. The vertex coordinates of the filtering border and the key point coordinates of the detection box are respectively determined as the key point coordinates of the first target obstacle to generate the key point coordinate group of the first target obstacle; The device further includes: In response to determining that the abscissa value of each obstacle detection bounding box vertex coordinate in the obstacle detection bounding box vertex coordinate group is less than the abscissa value of the camera optical center imaging point coordinate, a second target obstacle key point coordinate group is generated based on the obstacle detection bounding box vertex coordinate group. Based on the coordinates of the key points of the second target obstacle and the obstacle type information, obstacle distance information is generated.

7. An electronic device, comprising: One or more processors; Storage device, on which one or more programs are stored, When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-5.

8. A computer-readable medium having a computer program stored thereon, wherein, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-5.

Images