Obstacle position detection method and device

Abstract

The present disclosure provides a method and device for detecting the position of an obstacle, wherein the method comprises: obtaining a target image captured by an on-board camera on a target vehicle at a target time, and performing target detection on the target image to obtain a detection frame containing the target obstacle; based on the actual width of the target obstacle and the pixel width of the target obstacle in the image coordinate system of the target image, converting the center coordinate point of the detection frame to the vehicle coordinate system of the target vehicle to obtain a first mapping coordinate point; based on the actual height of the target obstacle and the pixel height of the target obstacle in the image coordinate system, converting the center coordinate point to the vehicle coordinate system to obtain a second mapping coordinate point; based on the first mapping coordinate point and the second mapping coordinate point, determining the target position of the target obstacle at the target time, thereby obtaining more comprehensive position information of the target obstacle and improving the accuracy of the position detection of the target obstacle.

Description

Technical Field

[0001] The present disclosure relates to the field of autonomous driving technology, and in particular to a method and device for detecting the position of an obstacle. Background Art

[0002] At present, with the development of autonomous driving related technologies, autonomous driving vehicles are gradually coming into people's view. Among them, the autonomous driving function of autonomous driving vehicles is of great significance to improving personal travel methods, promoting the upgrading of the automobile industry, and reducing traffic accidents.

[0003] In order to ensure the safety of autonomous vehicles during automatic driving, autonomous vehicles need to detect the positions of surrounding obstacles and avoid or slow down based on the detected obstacle position information. Therefore, how to realize obstacle position detection is very important. Summary of the invention

[0004] The present disclosure aims to solve one of the technical problems in the related art at least to some extent.

[0005] To this end, the present disclosure proposes a method and device for detecting the position of an obstacle, by simultaneously considering the actual width and actual height of the target obstacle, mapping the center point of a detection frame obtained by performing target detection on a target image captured by a vehicle-mounted camera at a target time to a vehicle coordinate system, and obtaining a first mapping coordinate point and a second mapping coordinate point. By combining the first mapping coordinate point and the second mapping coordinate point, more comprehensive target obstacle position information can be obtained, thereby improving the accuracy of target obstacle position detection.

[0006] In one aspect, an embodiment of the present disclosure provides a method for detecting the position of an obstacle, comprising: acquiring a target image captured by an on-board camera of a target vehicle at a target time, and performing target detection on the target image to obtain a detection frame containing the target obstacle; based on an actual width of the target obstacle and a pixel width of the target obstacle in an image coordinate system of the target image, converting a center coordinate point of the detection frame to a vehicle coordinate system of the target vehicle to obtain a first mapping coordinate point; based on an actual height of the target obstacle and a pixel height of the target obstacle in the image coordinate system, converting the center coordinate point to the vehicle coordinate system to obtain a second mapping coordinate point; and determining a target position of the target obstacle at the target time based on the first mapping coordinate point and the second mapping coordinate point.

[0007] In another aspect, an embodiment of the present disclosure provides an obstacle position detection device, comprising: an acquisition module, used to acquire a target image captured by an on-board camera on a target vehicle at a target time, and perform target detection on the target image to obtain a detection frame containing the target obstacle; a first conversion module, used to convert a center coordinate point of the detection frame to a vehicle coordinate system of the target vehicle based on an actual width of the target obstacle and a pixel width of the target obstacle in the image coordinate system of the target image to obtain a first mapping coordinate point; a second conversion module, used to convert the center coordinate point to the vehicle coordinate system based on an actual height of the target obstacle and a pixel height of the target obstacle in the image coordinate system to obtain a second mapping coordinate point; and a determination module, used to determine a target position of the target obstacle at the target time based on the first mapping coordinate point and the second mapping coordinate point.

[0008] Another aspect of the present disclosure provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the obstacle location detection method as described in the aforementioned aspect is implemented.

[0009] Another aspect of the present disclosure provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the obstacle position detection method as described in the aforementioned aspect is implemented.

[0010] Another aspect of the present disclosure provides a computer program product having a computer program stored thereon, which implements the obstacle position detection method as described in the aforementioned aspect when the program is executed by a processor.

[0011] The obstacle position detection method and device proposed in the present disclosure obtain a target image captured by an on-board camera on a target vehicle at a target time, and perform target detection on the target image to obtain a detection frame containing the target obstacle; based on the actual width of the target obstacle and the pixel width of the target obstacle in the image coordinate system of the target image, the center coordinate point of the detection frame is converted to the vehicle coordinate system of the target vehicle to obtain a first mapping coordinate point; according to the actual height of the target obstacle and the pixel height of the target obstacle in the image coordinate system, the center coordinate point is converted to the vehicle coordinate system to obtain a second mapping coordinate point; based on the first mapping coordinate point and the second mapping coordinate point, the target position of the target obstacle at the target time is determined, thereby, by simultaneously considering the actual width and the actual height of the target obstacle, the center point of the detection frame obtained by performing target detection on the target image captured by the on-board camera is mapped to the vehicle coordinate system to obtain the first mapping coordinate point and the second mapping coordinate point, and the first mapping coordinate point and the second mapping coordinate point are combined to obtain more comprehensive target obstacle position information, thereby improving the accuracy of target obstacle position detection.

[0012] Additional aspects and advantages of the present disclosure will be given in part in the following description and in part will be obvious from the following description or learned through practice of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The above and / or additional aspects and advantages of the present disclosure will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0014] Figure 1 A schematic diagram of a flow chart of a method for detecting the position of an obstacle provided in an embodiment of the present disclosure;

[0015] Figure 2 A schematic diagram of a flow chart of another obstacle location detection method proposed in an embodiment of the present disclosure;

[0016] Figure 3 A schematic diagram of a flow chart of another obstacle location detection method proposed in an embodiment of the present disclosure;

[0017] Figure 4 A schematic diagram of a flow chart of another obstacle location detection method proposed in an embodiment of the present disclosure;

[0018] Figure 5 A schematic diagram of the implementation principle of the central coordinate point conversion to the camera coordinate system provided in the embodiment of the present disclosure;

[0019] Figure 6 A schematic diagram of the structure of an obstacle position detection device provided in an embodiment of the present disclosure;

[0020] Figure 7 A block diagram of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0021] Embodiments of the present disclosure are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present disclosure, and should not be construed as limiting the present disclosure.

[0022] In the automated driving scenario, in the existing tracking solutions for the vehicle ahead, if the vehicle ahead or the oncoming vehicle changes lanes or the vehicle itself changes lanes, a "snake-like movement" situation will occur, causing the camera and sensor's observation of the vehicle ahead to change dramatically, resulting in a jump in the estimate of the target vehicle's position or the target being lost.

[0023] Therefore, in order to solve the above problems, the present disclosure proposes a method and device for detecting the position of an obstacle.

[0024] The following describes the obstacle position detection method and device according to the embodiments of the present disclosure with reference to the accompanying drawings.

[0025] Figure 1 A flowchart of a method for detecting the position of an obstacle provided in an embodiment of the present disclosure.

[0026] The execution subject of the obstacle position detection method of the embodiment of the present disclosure is an obstacle position detection device, which can be set in any electronic device so that the electronic device can perform the obstacle position detection function.

[0027] Among them, the electronic device can be any device with computing capabilities, such as a personal computer, a mobile terminal, a server, etc. The mobile terminal can be, for example, a vehicle-mounted device, a mobile phone, a tablet computer, a personal digital assistant, a wearable device, and other hardware devices with various operating systems, touch screens and / or display screens.

[0028] like Figure 1 As shown, the obstacle position detection method may include the following steps:

[0029] Step 101, obtaining a target image captured by a vehicle-mounted camera on a target vehicle at a target time, and performing target detection on the target image to obtain a detection frame containing a target obstacle.

[0030] As a possible implementation method, a vehicle-mounted camera is used to shoot the environment around the target vehicle at a target time to obtain a target image, and target detection is performed on the target image to obtain a detection frame containing the target obstacle. The target time can be any time, for example, the target time is the current time, and the target obstacle can be, for example, a vehicle.

[0031] Step 102 : based on the actual width of the target obstacle and the pixel width of the target obstacle in the image coordinate system of the target image, the center coordinate point of the detection frame is converted to the vehicle coordinate system of the target vehicle to obtain a first mapping coordinate point.

[0032] In order to improve the accuracy of the position detection of the target obstacle, the center point of the detection frame obtained by performing target detection on the target image captured by the vehicle camera can be mapped to the vehicle coordinate system by considering the actual width and actual height of the target obstacle at the same time.

[0033] As a possible implementation method, the pixel width of the target obstacle in the image coordinate system of the target image can be obtained, and based on the actual width of the target obstacle and the pixel width of the target obstacle in the image coordinate system of the target image, the center coordinate point of the detection frame is converted to the vehicle coordinate system of the target vehicle to obtain the first mapping coordinate point. The actual width of the target obstacle can be obtained by querying, for example, if the target obstacle is a certain type of vehicle, the actual width of the vehicle (e.g., 1.8 meters) can be obtained by querying.

[0034] Step 103 : According to the actual height of the target obstacle and the pixel height of the target obstacle in the image coordinate system, the center coordinate point is converted to the vehicle coordinate system to obtain a second mapping coordinate point.

[0035] As another possible implementation, the pixel height of the target obstacle in the image coordinate system may be obtained, and the center coordinate point may be converted to the vehicle coordinate system according to the actual height of the target obstacle and the pixel height of the target obstacle in the image coordinate system to obtain the second mapping coordinate point. The actual height of the target obstacle may be obtained by querying, for example, if the target obstacle is a certain type of vehicle, the actual height of the vehicle (e.g., 1.4 meters) may be obtained by querying.

[0036] Step 104 : determining a target position of the target obstacle at a target time based on the first mapped coordinate point and the second mapped coordinate point.

[0037] In order to obtain more comprehensive position information of the target obstacle and improve the accuracy of the position detection of the target obstacle, as a possible implementation method, the target position of the target obstacle at the target time can be jointly determined based on the first mapping coordinate point and the second mapping coordinate point.

[0038] Among them, after determining the target position of the target obstacle at the target time, the target vehicle can perform path planning, navigation, etc. based on the target position of the target obstacle at the target time.

[0039] In summary, the target image captured by the on-board camera of the target vehicle at the target time is acquired, and the target image is subjected to target detection to obtain a detection frame containing the target obstacle; based on the actual width of the target obstacle and the pixel width of the target obstacle in the image coordinate system of the target image, the center coordinate point of the detection frame is converted to the vehicle coordinate system of the target vehicle to obtain a first mapping coordinate point; according to the actual height of the target obstacle and the pixel height of the target obstacle in the image coordinate system, the center coordinate point is converted to the vehicle coordinate system to obtain a second mapping coordinate point; based on the first mapping coordinate point and the second mapping coordinate point, the target position of the target obstacle at the target time is determined, thereby, by simultaneously considering the actual width and the actual height of the target obstacle, the center coordinate point of the detection frame obtained by performing target detection on the target image captured by the on-board camera is mapped to the vehicle coordinate system to obtain the first mapping coordinate point and the second mapping coordinate point, and the first mapping coordinate point and the second mapping coordinate point are combined to obtain more comprehensive position information of the target obstacle, thereby improving the accuracy of the position detection of the target obstacle.

[0040] In order to clearly illustrate how the above embodiment determines the target position of the target obstacle at the target time based on the first mapping coordinate point and the second mapping coordinate point, the embodiment of the present disclosure proposes another obstacle position detection method.

[0041] Figure 2 A flowchart of another obstacle location detection method proposed in an embodiment of the present disclosure.

[0042] like Figure 2 As shown, the obstacle position detection method may include the following steps:

[0043] Step 201 , obtaining a target image captured by a vehicle-mounted camera on a target vehicle at a target time, and performing target detection on the target image to obtain a detection frame containing a target obstacle.

[0044] Step 202 : based on the actual width of the target obstacle and the pixel width of the target obstacle in the image coordinate system of the target image, the center coordinate point of the detection frame is converted to the vehicle coordinate system of the target vehicle to obtain a first mapping coordinate point.

[0045] Step 203 : According to the actual height of the target obstacle and the pixel height of the target obstacle in the image coordinate system, the center coordinate point is converted to the vehicle coordinate system to obtain a second mapping coordinate point.

[0046] Step 204 , in response to the target image being the first frame image captured by the vehicle-mounted camera this time, a first state quantity of a first vehicle-mounted filter on the target vehicle is initialized using a first mapping coordinate point to obtain a first state quantity at a target moment.

[0047] It is important to understand that in the autonomous driving scenario, the vehicle-mounted filter is mainly used for data processing and filtering to improve the accuracy and robustness of the autonomous driving system. Among them, the vehicle-mounted filter may include but is not limited to the Kalman filter, the extended Kalman filter, the particle filter, etc.

[0048] As a possible implementation method, it can be determined whether the target image is the first frame image taken this time by the vehicle-mounted camera. For example, it can be determined whether the target image is the first frame image taken this time based on the shooting time of the target image and the shooting time of at least one image taken this time. When the target image is the first frame image taken this time by the vehicle-mounted camera and the target image is not the first frame image taken this time by the vehicle-mounted camera, the first vehicle-mounted filter and the second vehicle-mounted filter are processed differently.

[0049] As an example, when the target image is the first frame image taken by the vehicle-mounted camera this time, the first mapping coordinate point is used to initialize the first state quantity of the first vehicle-mounted filter on the target vehicle. For example, the first mapping coordinate point is used to determine the parameters of the first vehicle-mounted filter (such as the cutoff frequency of the vehicle-mounted filter, the order of the vehicle-mounted filter, the initial weight of the filter, etc.), and the parameters are applied to the first vehicle-mounted filter for initialization to obtain the first state quantity of the first vehicle-mounted filter at the target time.

[0050] As another example, when the target image is not the first frame image taken by the vehicle-mounted camera this time, the first state quantity of the first vehicle-mounted filter at the previous moment of the target moment can be updated based on the first mapping coordinate point. At the same time, the second state quantity of the second vehicle-mounted filter of the target vehicle at the previous moment of the target moment can be updated using the second mapping coordinate point.

[0051] Step 205: Initialize the second state quantity of the second vehicle-mounted filter on the target vehicle using the second mapping point to obtain the second state quantity at the target time.

[0052] As a possible implementation method, when the target image is the first frame image taken by the vehicle-mounted camera this time, the second state quantity of the second vehicle-mounted filter on the target vehicle is initialized using the second mapping point. For example, the parameters of the second vehicle-mounted filter (such as the cutoff frequency of the vehicle-mounted filter, the order of the vehicle-mounted filter, the initial weight of the filter, etc.) are determined using the second mapping coordinate point, and the parameters are applied to the second vehicle-mounted filter for initialization to obtain the second state quantity of the second vehicle-mounted filter at the target time.

[0053] Step 206, determining a target position of the target obstacle at the target time according to the first state quantity at the target time and the second state quantity at the target time.

[0054] In order to improve the accuracy of obstacle position detection, as a possible implementation manner, the target position of the target obstacle at the target moment is calculated based on the first state quantity at the target moment and the second state quantity at the target moment.

[0055] As an example, a first variance between the actual width and the pixel width is obtained, and a first mean between the actual width and the pixel width is obtained; a first weight is determined based on the ratio of the first variance to the first mean; a second variance between the actual height and the pixel height is obtained, and a second mean between the actual height and the pixel height is obtained; a second weight is determined based on the ratio of the second variance to the second mean; and the first weight and the second weight are used to perform weighted summation on the first state quantity at the target moment and the second state quantity at the target moment to obtain the target position of the target obstacle at the target moment.

[0056] For example, the first state quantity at the target time is Q w , the second state quantity at the target time is Q h , the first variance between the actual width and the pixel width is The first mean between the actual width and the pixel width is μ 1 , the first weight The second variance between the actual height and the pixel height is The second mean between the actual width and the pixel width is μ 2 , the second weight Target position = α*Q w +β*Q h .

[0057] It should be noted that the execution process of steps 201 to 203 can be implemented in any manner in the embodiments of the present disclosure, and the embodiments of the present disclosure do not limit this and will not be described in detail.

[0058] In summary, in response to the target image being the first frame image taken by the vehicle-mounted camera this time, the first state quantity of the first vehicle-mounted filter on the target vehicle is initialized using the first mapping coordinate point to obtain the first state quantity at the target moment; the second state quantity of the second vehicle-mounted filter on the target vehicle is initialized using the second mapping point to obtain the second state quantity at the target moment, and the target position of the target obstacle at the target moment is determined according to the first state quantity at the target moment and the second state quantity at the target moment. Thus, the state quantity of the vehicle-mounted filter is initialized based on the position coordinate, so that the vehicle-mounted filter can better adapt to the environment and state of the vehicle, and improve the filtering effect. Therefore, by initializing the state quantity of the vehicle-mounted filter, the position information of the target obstacle can be better processed, and the accuracy of the position detection of the target obstacle can be improved.

[0059] In order to clearly illustrate how the above embodiment determines the target position of the target obstacle at the target time based on the first mapping coordinate point and the second mapping coordinate point, the embodiment of the present disclosure proposes another obstacle position detection method.

[0060] Figure 3 A flowchart of another obstacle location detection method proposed in an embodiment of the present disclosure.

[0061] like Figure 3 As shown, the obstacle position detection method may include the following steps:

[0062] Step 301 , obtaining a target image captured by a vehicle-mounted camera on a target vehicle at a target time, and performing target detection on the target image to obtain a detection frame containing a target obstacle.

[0063] Step 302 : Based on the actual width of the target obstacle and the pixel width of the target obstacle in the image coordinate system of the target image, the center coordinate point of the detection frame is converted to the vehicle coordinate system of the target vehicle to obtain a first mapping coordinate point.

[0064] Step 303 : According to the actual height of the target obstacle and the pixel height of the target obstacle in the image coordinate system, the center coordinate point is converted to the vehicle coordinate system to obtain a second mapping coordinate point.

[0065] Step 304, in response to the target image being a non-first frame image captured by the vehicle-mounted camera this time, the first mapping coordinate point is used to update the first state quantity of the first vehicle-mounted filter of the target vehicle at the previous moment of the target moment to obtain the first state quantity at the target moment.

[0066] As a possible implementation method, when it is determined that the target image is not the first frame image taken by the vehicle-mounted camera this time, the first mapping coordinate point is used as observation data and input into the first vehicle-mounted filter. The first vehicle-mounted filter will update the first state quantity at the previous moment of the target moment based on these observation data and internal states to obtain the second state quantity at the target moment.

[0067] Step 305 : using the second mapping coordinate point, updating the second state quantity of the second vehicle-mounted filter of the target vehicle at the previous moment of the target moment, so as to obtain the second state quantity at the target moment.

[0068] Similarly, when the target image is not the first frame image taken by the vehicle-mounted camera, the second mapping coordinate point is used as observation data and input into the second vehicle-mounted filter. The second vehicle-mounted filter will update the second state quantity at the previous moment of the target moment based on these observation data and internal states to obtain the second state quantity at the target moment.

[0069] Step 306, determining a target position of the target obstacle at the target time according to the first state quantity at the target time and the second state quantity at the target time.

[0070] In order to improve the stability of target obstacle position detection and avoid sudden changes in target obstacle position estimation caused by observation mutations (such as lane change, overtaking, etc.), position prediction can be performed based on the actual width and actual height of the target obstacle. As an example, a first variance between the actual width and the pixel width is obtained, and a first mean between the actual width and the pixel width is obtained; a first weight is determined according to the ratio of the first variance to the first mean; a second variance between the actual height and the pixel height is obtained, and a second mean between the actual height and the pixel height is obtained; a second weight is determined according to the ratio of the second variance to the second mean; and the first state quantity at the target moment and the second state quantity at the target moment are weightedly summed using the first weight and the second weight to obtain the target position of the target obstacle at the target moment.

[0071] It should be noted that the execution process of steps 301 to 303 can be implemented in any manner in the embodiments of the present disclosure, and the embodiments of the present disclosure do not limit this and will not be described in detail.

[0072] In summary, in response to the target image being a non-first frame image taken by a vehicle-mounted camera, a first mapping coordinate point is used to update a first state quantity of a first vehicle-mounted filter of the target vehicle at a previous moment of the target moment to obtain the first state quantity at the target moment; a second mapping coordinate point is used to update a second state quantity of a second vehicle-mounted filter of the target vehicle at a previous moment of the target moment to obtain the second state quantity at the target moment; according to the first state quantity at the target moment and the second state quantity at the target moment, the target position of the target obstacle at the target moment is determined, thereby, by updating the state of the vehicle-mounted filter in real time, the vehicle can respond quickly to changes in the environment, avoid sudden changes in the position estimation of the target obstacle caused by sudden changes in observations, and improve the detection accuracy and stability of the target position of the target obstacle at the target moment.

[0073] In order to clearly illustrate how in the above embodiment, the center coordinate point of the detection frame is converted to the vehicle coordinate system of the target vehicle based on the actual width of the target obstacle and the pixel width of the target obstacle in the image coordinate system of the target image to obtain the first mapping coordinate point, the present disclosure proposes another obstacle position detection method.

[0074] Figure 4 A flowchart of another obstacle location detection method proposed in an embodiment of the present disclosure.

[0075] like Figure 4 As shown, the obstacle position detection method may include the following steps:

[0076] Step 401 , obtaining a target image captured by a vehicle-mounted camera on a target vehicle at a target time, and performing target detection on the target image to obtain a detection frame containing a target obstacle.

[0077] Step 402 : determining a third mapping coordinate point of the center coordinate point in the camera coordinate system where the target image is located based on the actual width of the target obstacle and the pixel width of the target obstacle in the image coordinate system of the target image.

[0078] As a possible implementation method, a first number of pixels occupied by the focal length of the vehicle-mounted camera in the horizontal direction of the image coordinate system is obtained; a first ratio of the actual width to the pixel width is determined, and a first distance between the target obstacle and the camera plane of the vehicle-mounted camera is determined based on the product of the first ratio and the first number of pixels; based on the first distance and the optical center coordinates of the image coordinate system, the center coordinate point is converted to the camera coordinate system to obtain a third mapping coordinate point.

[0079] For example, the number of pixels (the first number of pixels) occupied by the focal length of the vehicle-mounted camera in the horizontal direction of the image coordinate system is f u , actual width W carThe first ratio to the pixel width w is W car / w, first distance dist 1 =W car *f u / w; the third mapping coordinate point in the camera coordinate system can be expressed as P c (P cx ,P cy ,P cz ), where P cx =(P x -c u ) / f u *dist 1 , P cy =(P y -c u ) / f v *dist 1 , P cz =dist 1 , (c u ,c v ) is the coordinate of the optical center in the image coordinate system.

[0080] Step 403 : According to the mapping relationship between the camera coordinate system and the vehicle coordinate system where the target vehicle is located, the third mapping coordinate point is converted to the vehicle coordinate system to obtain the first mapping coordinate point.

[0081] Further, based on the mapping relationship between the camera coordinate system and the vehicle coordinate system where the target vehicle is located, the third mapping coordinate point P c (P cx ,P cy ,P cz ) is converted to the vehicle coordinate system to obtain the first mapping coordinate point. For example, the first mapping coordinate point P w =[RT] c→w *P c , [RT] c→w It is the inverse matrix of the camera extrinsic matrix, that is, the mapping relationship between the camera coordinate system and the vehicle coordinate system where the target vehicle is located.

[0082] Step 404 : According to the actual height of the target obstacle and the pixel height of the target obstacle in the image coordinate system, the center coordinate point is converted to the vehicle coordinate system to obtain a second mapping coordinate point.

[0083] As an example, based on the actual height of the target obstacle and the pixel height of the target obstacle in the image coordinate system of the target image, determine the fourth mapping coordinate point of the center coordinate point in the camera coordinate system where the target image is located; according to the mapping relationship between the camera coordinate system and the vehicle coordinate system where the target vehicle is located, convert the fourth mapping coordinate point to the vehicle coordinate system to obtain the second mapping coordinate point.

[0084] Among them, the steps for determining the fourth mapping coordinate point are as follows: obtain the second number of pixels occupied by the focal length of the vehicle-mounted camera in the longitudinal direction of the image coordinate system; determine the second ratio of the actual height and the pixel height, and determine the second distance between the target obstacle and the camera plane of the vehicle-mounted camera based on the product of the second ratio and the second number of pixels; according to the second distance and the optical center coordinates of the image coordinate system, convert the center coordinate point to the camera coordinate system to obtain the fourth mapping coordinate point.

[0085] For example, the number of pixels (the second number of pixels) occupied by the focal length of the vehicle-mounted camera in the vertical direction of the image coordinate system is f v , the second ratio of the actual height H and the pixel height h is H / h, and the second distance dist 2 =H*f v / h. The fourth mapping coordinate point in the camera coordinate system can be expressed as P d (P dx ,P dy ,P dz ), where P dx =(P x -c u ) / f u *dist 2 , P dy =(P y -c u ) / f v *dist 2 , P dz =dist 2 , (c u ,c v ) is the coordinate of the optical center in the image coordinate system.

[0086] Further, based on the mapping relationship between the camera coordinate system and the vehicle coordinate system where the target vehicle is located, the fourth mapping coordinate point P d (P dx ,P dy ,P dz ), and converted to the vehicle coordinate system to obtain the second mapping coordinate point. For example, the second mapping coordinate point P k =[RT] c→w *P d , [RT] c→w It is the inverse matrix of the camera extrinsic matrix, that is, the mapping relationship between the camera coordinate system and the vehicle coordinate system where the target vehicle is located.

[0087] Step 405: Determine a target position of the target obstacle at a target time based on the first mapped coordinate point and the second mapped coordinate point.

[0088] It should be noted that the execution process of step 401 and step 405 can be implemented in any way in the embodiments of the present disclosure, and the embodiments of the present disclosure do not limit this and will not be described in detail.

[0089] In summary, the third mapping coordinate point of the center coordinate point in the camera coordinate system where the target image is located is determined based on the actual width of the target obstacle and the pixel width of the target obstacle in the image coordinate system of the target image; according to the mapping relationship between the camera coordinate system and the vehicle coordinate system where the target vehicle is located, the third mapping coordinate point is converted to the vehicle coordinate system to obtain the first mapping coordinate point; according to the actual height of the target obstacle and the pixel height of the target obstacle in the image coordinate system, the center coordinate point is converted to the vehicle coordinate system to obtain the second mapping coordinate point, and the target position of the target obstacle at the target time is determined based on the first mapping coordinate point and the second mapping coordinate point. Therefore, by simultaneously considering the actual width and the actual height of the target obstacle, the center point of the detection frame obtained by target detection on the target image captured by the on-board camera is mapped to the vehicle coordinate system to obtain the first mapping coordinate point and the second mapping coordinate point. By combining the first mapping coordinate point and the second mapping coordinate point, more comprehensive position information of the target obstacle can be obtained, and the position estimation mutation caused by the observation mutation is avoided, thereby improving the accuracy and stability of the position detection of the target obstacle.

[0090] Based on any embodiment of the present disclosure, the implementation principle of the present disclosure mainly includes the following steps:

[0091] Step 1: Use a sensor, such as a camera, to observe the target in the current frame and obtain an image containing the target;

[0092] Step 2: Calculate the coordinates P of the center point of the observation frame in the image coordinate system; where P x =(x 1 +x 2 ) / 2,P y =(y 1 +y 2 ) / 2;

[0093] Step 3: Using pinhole imaging and similar triangle principles, the width of the target obstacle (e.g., vehicle) (actual width W car =A meters, the vehicle height is fixed at H = B meters), and the image coordinates P(P x ,P y ) is transformed to the camera coordinate system P c (P cx ,P cy );

[0094] (1) Figure 5As shown, first solve the distance dist between the target obstacle and the camera plane, dist = W car *f u / w, where w is the width of the target obstacle in the image coordinate system;

[0095] (2) Image coordinates P(P x ,P y ) is converted to the camera coordinate system P c (P cx ,P cy ):

[0096] P cx =(P x -c u ) / f u *dist;

[0097] P cy =(P y -c u ) / f v *dist;

[0098] P cz = dist;

[0099] Among them, f u is the number of pixels that the focal length occupies in the x direction in the image coordinate system, (c u ,c v ) is the coordinate of the optical center in the image coordinate system,

[0100] Step 4: Use the camera external parameters (i.e., the mapping relationship between the camera coordinate system and the vehicle coordinate system) to transform P c (P cx ,P cy ) is converted to the vehicle body coordinate system to obtain the target position information (first mapping coordinate point) P based on width estimation w (P wx ,P wy );

[0101] Step 5: Similarly, using the height information H of the target obstacle and the height information (pixel height) h of the target obstacle in the image coordinate system based on the observation, execute steps 3-4 to obtain the target position information P in the vehicle coordinate system based on the height estimation. h (P hx ,P hy );

[0102] Step 6: Use the position information P w (P wx ,P wy ) and P h (P hx ,Phy ) Initialize the state quantities Q of the two Kalman filters w ,Q h ;

[0103] Step 7: Update the state quantities of the two Kalman filters;

[0104] For the second frame and subsequent frames, repeat steps 2-5 and update the Kalman filter Q w ,Q h ;

[0105] Step 8: Output the position information of the Kalman filter Q based on the vehicle body coordinate system to the downstream;

[0106] The stability of the width and height attributes of the target vehicle obtained by observation is calculated respectively, for example, using the coefficient of variation (CV, variance divided by the mean), and assigning Q according to the stability. w and Q h Different weights, get the final position information pose = α * Q w +β*Q h .

[0107] In order to implement the above embodiment, the embodiment of the present disclosure further proposes a device for detecting the position of an obstacle.

[0108] Figure 6 A schematic diagram of the structure of an obstacle position detection device provided in an embodiment of the present disclosure.

[0109] like Figure 6 As shown, the obstacle position detection device 600 may include: an acquisition module 610 , a first conversion module 620 , a second conversion module 630 and a determination module 640 .

[0110] Among them, the acquisition module 610 is used to acquire the target image captured by the on-board camera of the target vehicle at the target time, and perform target detection on the target image to obtain a detection frame containing the target obstacle; the first conversion module 620 is used to convert the center coordinate point of the detection frame to the vehicle coordinate system of the target vehicle based on the actual width of the target obstacle and the pixel width of the target obstacle in the image coordinate system of the target image to obtain a first mapping coordinate point; the second conversion module 630 is used to convert the center coordinate point to the vehicle coordinate system according to the actual height of the target obstacle and the pixel height of the target obstacle in the image coordinate system to obtain a second mapping coordinate point; the determination module 640 is used to determine the target position of the target obstacle at the target time based on the first mapping coordinate point and the second mapping coordinate point.

[0111] As a possible implementation method, the determination module 640 is used to initialize the first state quantity of the first vehicle-mounted filter on the target vehicle using the first mapping coordinate point in response to the target image being the first frame image taken by the vehicle-mounted camera this time, so as to obtain the first state quantity at the target moment; initialize the second state quantity of the second vehicle-mounted filter on the target vehicle using the second mapping point to obtain the second state quantity at the target moment; and determine the target position of the target obstacle at the target moment based on the first state quantity at the target moment and the second state quantity at the target moment.

[0112] As a possible implementation method, the determination module 640 is used to obtain a first variance between the actual width and the pixel width, and obtain a first mean between the actual width and the pixel width; determine a first weight according to the ratio of the first variance to the first mean; obtain a second variance between the actual height and the pixel height, and obtain a second mean between the actual height and the pixel height; determine a second weight according to the ratio of the second variance to the second mean; and use the first weight and the second weight to perform weighted summation on the first state quantity at the target moment and the second state quantity at the target moment to obtain the target position of the target obstacle at the target moment.

[0113] As a possible implementation method, the determination module 640 is used to respond to the target image being a non-first frame image taken by the vehicle-mounted camera this time, use the first mapping coordinate point to update the first state quantity of the first vehicle-mounted filter of the target vehicle at the previous moment of the target moment to obtain the first state quantity at the target moment; use the second mapping coordinate point to update the second state quantity of the second vehicle-mounted filter of the target vehicle at the previous moment of the target moment to obtain the second state quantity at the target moment; determine the target position of the target obstacle at the target moment according to the first state quantity at the target moment and the second state quantity at the target moment.

[0114] As a possible implementation method, the first conversion module 620 is used to determine the third mapping coordinate point of the center coordinate point in the camera coordinate system where the target image is located based on the actual width of the target obstacle and the pixel width of the target obstacle in the image coordinate system of the target image; according to the mapping relationship between the camera coordinate system and the vehicle coordinate system where the target vehicle is located, the third mapping coordinate point is converted to the vehicle coordinate system to obtain the first mapping coordinate point.

[0115] As a possible implementation method, the first conversion module 620 is used to obtain a first number of pixels occupied by the focal length of the vehicle-mounted camera in the horizontal direction of the image coordinate system; determine a first ratio of the actual width to the pixel width, and determine a first distance between the target obstacle and the camera plane of the vehicle-mounted camera based on the product of the first ratio and the first number of pixels; and convert the center coordinate point to the camera coordinate system based on the first distance and the optical center coordinates of the image coordinate system to obtain a third mapping coordinate point.

[0116] As a possible implementation method, the second conversion module 630 is used to determine the fourth mapping coordinate point of the center coordinate point in the camera coordinate system where the target image is located based on the actual height of the target obstacle and the pixel height of the target obstacle in the image coordinate system of the target image; according to the mapping relationship between the camera coordinate system and the vehicle coordinate system where the target vehicle is located, the fourth mapping coordinate point is converted to the vehicle coordinate system to obtain the second mapping coordinate point.

[0117] As a possible implementation method, the second conversion module 630 is used to obtain the second number of pixels occupied by the focal length of the vehicle-mounted camera in the longitudinal direction of the image coordinate system; determine the second ratio of the actual height and the pixel height, and determine the second distance between the target obstacle and the camera plane of the vehicle-mounted camera based on the product of the second ratio and the second number of pixels; based on the second distance and the optical center coordinates of the image coordinate system, convert the center coordinate point to the camera coordinate system to obtain a fourth mapping coordinate point.

[0118] The obstacle position detection device of the embodiment of the present disclosure obtains a target image captured by a vehicle-mounted camera on a target vehicle at a target time, and performs target detection on the target image to obtain a detection frame containing the target obstacle; based on the actual width of the target obstacle and the pixel width of the target obstacle in the image coordinate system of the target image, the center coordinate point of the detection frame is converted to the vehicle coordinate system of the target vehicle to obtain a first mapping coordinate point; according to the actual height of the target obstacle and the pixel height of the target obstacle in the image coordinate system, the center coordinate point is converted to the vehicle coordinate system to obtain a second mapping coordinate point; based on the first mapping coordinate point and the second mapping coordinate point, the target position of the target obstacle at the target time is determined, thereby, by simultaneously considering the actual width and the actual height of the target obstacle, the center point of the detection frame obtained by performing target detection on the target image captured by the vehicle-mounted camera is mapped to the vehicle coordinate system to obtain the first mapping coordinate point and the second mapping coordinate point, and the first mapping coordinate point and the second mapping coordinate point are combined to obtain more comprehensive target obstacle position information, thereby improving the accuracy of target obstacle position detection.

[0119] In order to implement the above embodiments, the present disclosure also proposes an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the obstacle position detection method as described in the above method embodiments is implemented.

[0120] In order to implement the above embodiments, the present disclosure further proposes a non-temporary computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the obstacle position detection method as described in the above method embodiments is implemented.

[0121] In order to implement the above embodiments, the present disclosure further proposes a computer program product, on which a computer program is stored. When the computer program is executed by a processor, the obstacle position detection method as described in the above method embodiments is implemented.

[0122] Figure 7 The electronic device 700 is a block diagram of an electronic device provided by an embodiment of the present disclosure. For example, the electronic device 700 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0123] Reference Figure 7 , the electronic device 700 may include one or more of the following components: a processing component 702 , a memory 704 , a power component 706 , a multimedia component 708 , an audio component 710 , an input / output (I / O) interface 712 , a sensor component 714 , and a communication component 716 .

[0124] The processing component 702 generally controls the overall operation of the electronic device 700, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 702 may include one or more processors 720 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 702 may include one or more modules to facilitate the interaction between the processing component 702 and other components. For example, the processing component 702 may include a multimedia module to facilitate the interaction between the multimedia component 708 and the processing component 702.

[0125] The memory 704 is configured to store various types of data to support operations on the electronic device 700. Examples of such data include instructions for any application or method operating on the electronic device 700, contact data, phone book data, messages, pictures, videos, etc. The memory 704 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0126] The power component 706 provides power to the various components of the electronic device 700. The power component 706 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the electronic device 700.

[0127] The multimedia component 708 includes a screen that provides an output interface between the electronic device 700 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 708 includes a front camera and / or a rear camera. When the electronic device 700 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0128] The audio component 710 is configured to output and / or input audio signals. For example, the audio component 710 includes a microphone (MIC), and when the electronic device 700 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 704 or sent via the communication component 716. In some embodiments, the audio component 710 also includes a speaker for outputting audio signals.

[0129] I / O interface 712 provides an interface between processing component 702 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: home button, volume button, start button, and lock button.

[0130] The sensor assembly 714 includes one or more sensors for providing various aspects of status assessment for the electronic device 700. For example, the sensor assembly 714 can detect the open / closed state of the electronic device 700, the relative positioning of components, such as the display and keypad of the electronic device 700, and the sensor assembly 714 can also detect the position change of the electronic device 700 or a component of the electronic device 700, the presence or absence of user contact with the electronic device 700, the orientation or acceleration / deceleration of the electronic device 700, and the temperature change of the electronic device 700. The sensor assembly 714 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 714 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 714 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0131] The communication component 716 is configured to facilitate wired or wireless communication between the electronic device 700 and other devices. The electronic device 700 can access a wireless network based on a communication standard, such as WiFi, 4G or 5G, or a combination thereof. In an exemplary embodiment, the communication component 716 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 716 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0132] In an exemplary embodiment, the electronic device 700 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above methods.

[0133] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 704 including instructions, and the instructions can be executed by a processor 720 of an electronic device 700 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0134] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0135] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of the present disclosure, "plurality" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0136] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present disclosure includes additional implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present disclosure belong.

[0137] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute the instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0138] It should be understood that the various parts of the present disclosure can be implemented in hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0139] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0140] In addition, each functional unit in each embodiment of the present disclosure may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0141] The storage medium mentioned above may be a read-only memory, a disk or an optical disk, etc. Although the embodiments of the present disclosure have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations of the present disclosure. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present disclosure.

Claims

1. A method for detecting the position of an obstacle, characterized in that: include: Obtaining a target image captured by a vehicle-mounted camera on a target vehicle at a target time, and performing target detection on the target image to obtain a detection frame containing a target obstacle; Based on the actual width of the target obstacle and the pixel width of the target obstacle in the image coordinate system of the target image, converting the center coordinate point of the detection frame to the vehicle coordinate system of the target vehicle to obtain a first mapping coordinate point; According to the actual height of the target obstacle and the pixel height of the target obstacle in the image coordinate system, converting the central coordinate point to the vehicle coordinate system to obtain a second mapping coordinate point; Determining a target position of the target obstacle at the target time based on the first mapped coordinate point and the second mapped coordinate point; Wherein, determining the target position of the target obstacle at the target time based on the first mapping coordinate point and the second mapping coordinate point includes: In response to the target image being the first frame image captured by the vehicle-mounted camera this time, the first state quantity of the first vehicle-mounted filter on the target vehicle is initialized using the first mapping coordinate point to obtain the first state quantity at the target moment; Initializing a second state quantity of a second vehicle-mounted filter on the target vehicle using the second mapping point to obtain a second state quantity at the target moment; A target position of the target obstacle at the target moment is determined according to the first state quantity at the target moment and the second state quantity at the target moment.

2. The method according to claim 1, characterized in that The determining the target position of the target obstacle at the target moment according to the first state quantity at the target moment and the second state quantity at the target moment comprises: Obtaining a first variance between the actual width and the pixel width, and obtaining a first mean value between the actual width and the pixel width; determining a first weight according to a ratio of the first variance to the first mean; Obtain a second variance between the actual height and the pixel height, and obtain a second mean between the actual height and the pixel height; determining a second weight according to a ratio of the second variance to the second mean; The first weight and the second weight are used to perform weighted summation on the first state quantity at the target moment and the second state quantity at the target moment to obtain the target position of the target obstacle at the target moment.

3. The method according to claim 1, characterized in that The determining, based on the first mapping coordinate point and the second mapping coordinate point, a target position of the target obstacle at the target time, further includes: In response to the target image being a non-first frame image captured by the vehicle-mounted camera this time, using the first mapping coordinate point, updating the first state quantity of the first vehicle-mounted filter of the target vehicle at the previous moment of the target moment to obtain the first state quantity at the target moment; Using the second mapping coordinate point, updating the second state quantity of the second vehicle-mounted filter of the target vehicle at a previous moment of the target moment, so as to obtain the second state quantity at the target moment; A target position of the target obstacle at the target moment is determined according to the first state quantity at the target moment and the second state quantity at the target moment.

4. The method according to claim 1, characterized in that The converting the center coordinate point of the detection frame to the vehicle coordinate system of the target vehicle based on the actual width of the target obstacle and the pixel width of the target obstacle in the image coordinate system of the target image to obtain a first mapping coordinate point includes: Determine, based on the actual width of the target obstacle and the pixel width of the target obstacle in the image coordinate system of the target image, a third mapping coordinate point of the center coordinate point in the camera coordinate system where the target image is located; According to the mapping relationship between the camera coordinate system and the vehicle coordinate system in which the target vehicle is located, the third mapping coordinate point is converted to the vehicle coordinate system to obtain the first mapping coordinate point.

5. The method according to claim 4, characterized in that The determining, based on the actual width of the target obstacle and the pixel width of the target obstacle in the image coordinate system of the target image, a third mapping coordinate point of the center coordinate point in the camera coordinate system where the target image is located comprises: Obtaining a first number of pixels occupied by the focal length of the vehicle-mounted camera in the horizontal axis direction of the image coordinate system; Determine a first ratio of the actual width to the pixel width, and determine a first distance between the target obstacle and a camera plane of the vehicle-mounted camera according to a product of the first ratio and the first number of pixels; According to the first distance and the optical center coordinates of the image coordinate system, the center coordinate point is converted to the camera coordinate system to obtain the third mapping coordinate point.

6. The method according to claim 1, characterized in that The converting the center coordinate point to the vehicle coordinate system according to the actual height of the target obstacle and the pixel height of the target obstacle in the image coordinate system to obtain a second mapping coordinate point includes: Determine, based on the actual height of the target obstacle and the pixel height of the target obstacle in the image coordinate system of the target image, a fourth mapping coordinate point of the center coordinate point in the camera coordinate system where the target image is located; According to the mapping relationship between the camera coordinate system and the vehicle coordinate system in which the target vehicle is located, the fourth mapping coordinate point is converted to the vehicle coordinate system to obtain a second mapping coordinate point.

7. The method according to claim 6, characterized in that The determining, based on the actual height of the target obstacle and the pixel height of the target obstacle in the image coordinate system of the target image, a fourth mapping coordinate point of the center coordinate point in the camera coordinate system where the target image is located, comprises: Obtaining the second number of pixels occupied by the focal length of the vehicle-mounted camera in the longitudinal direction of the image coordinate system; Determine a second ratio of the actual height to the pixel height, and determine a second distance between the target obstacle and a camera plane of the vehicle-mounted camera according to a product of the second ratio and the second number of pixels; According to the second distance and the optical center coordinates of the image coordinate system, the center coordinate point is converted to the camera coordinate system to obtain the fourth mapping coordinate point.

8. An obstacle position detection device, characterized in that: include: An acquisition module is used to acquire a target image captured by a vehicle-mounted camera on a target vehicle at a target time, and perform target detection on the target image to obtain a detection frame containing a target obstacle; a first conversion module, configured to convert the center coordinate point of the detection frame to the vehicle coordinate system of the target vehicle based on the actual width of the target obstacle and the pixel width of the target obstacle in the image coordinate system of the target image, so as to obtain a first mapping coordinate point; a second conversion module, configured to convert the central coordinate point to the vehicle coordinate system according to the actual height of the target obstacle and the pixel height of the target obstacle in the image coordinate system, so as to obtain a second mapping coordinate point; A determination module, configured to determine a target position of the target obstacle at the target time based on the first mapping coordinate point and the second mapping coordinate point; Wherein, the determination module is specifically used for: In response to the target image being the first frame image captured by the vehicle-mounted camera this time, the first state quantity of the first vehicle-mounted filter on the target vehicle is initialized using the first mapping coordinate point to obtain the first state quantity at the target moment; Initializing a second state quantity of a second vehicle-mounted filter on the target vehicle using the second mapping point to obtain a second state quantity at the target moment; A target position of the target obstacle at the target moment is determined according to the first state quantity at the target moment and the second state quantity at the target moment.

9. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and allowed to run on the processor, wherein when the processor executes the program, the method according to any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images