Vehicle reversing anti-collision early warning method, electronic equipment and vehicle

Abstract

The invention provides a reversing anti-collision early warning method of a vehicle, electronic equipment and the vehicle, which are applied to the technical field of reversing control of the vehicle, when gear information of the vehicle is determined to be a reversing gear and opening degree information of a rear tail door of the vehicle is greater than or equal to a preset opening degree, area image information acquired by image acquisition equipment is acquired; when it is determined that the area image information comprises an obstacle image, a safe distance is determined based on the area image information, and when the distance between the tail of the vehicle and a rear obstacle reaches the safe distance, an early warning is given out to ensure that the distance between the vehicle and the rear obstacle is controlled within the range larger than or equal to the safe distance; and therefore, the rear tail door of the vehicle or articles in a vehicle trunk below the rear tail door are ensured not to collide with a rear obstacle.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle reversing control, and in particular to a vehicle reversing anti-collision warning method, an electronic device and a vehicle. BACKGROUND

[0002] A vehicle reversing anti-collision warning system works in cooperation through various technical means to monitor obstacles behind the vehicle in real time and timely remind the driver. Existing reversing anti-collision warning systems include ultrasonic radar and panoramic image systems, etc. However, in some special scenarios, the existing reversing anti-collision warning system cannot normally give a warning, which affects the user experience. SUMMARY

[0003] In view of the above, the purpose of the present application is to provide a vehicle reversing anti-collision warning method, an electronic device and a vehicle.

[0004] To achieve the above purpose, the first aspect of the present application provides a vehicle reversing anti-collision warning method, a rear tail door of the vehicle is provided with an image acquisition device at an inner tail end, and the method comprises: In response to the gear information of the vehicle being a reverse gear and the opening degree information of the rear tail door of the vehicle being greater than or equal to a preset opening degree, acquiring regional image information collected by the image acquisition device, the regional image information at least including image information of a region behind the vehicle; In response to the regional image information including an obstacle image, determining a safety distance based on the regional image information; In response to the distance between the tail of the vehicle and the obstacle behind the vehicle reaching the safety distance, issuing a warning reminder.

[0005] Optionally, the safety distance is determined based on the regional image information, comprising: In response to the regional image information including an object image of a target object, determining a boundary pixel point of the object image based on the regional image information, the target object being an object protruding from the coverage area of the rear tail door of the vehicle; Determining an obstacle equidistant pixel point based on the boundary pixel point and the obstacle image; Determining the safety distance based on the boundary pixel point and the obstacle equidistant pixel point.

[0006] Optionally, the obstacle image includes a plurality of pixel points; The obstacle equidistant pixel point is determined based on the boundary pixel point and the obstacle image, comprising: Determining a first distance between the boundary pixel point and a first plane, the first plane being a plane where one end of the image acquisition device away from the rear tail door is located; determining a second distance between each of the pixel points in the obstacle image and the first plane; in response to an absolute value of a difference between the second distance and the first distance being less than or equal to a preset distance, determining the pixel point corresponding to the second distance as the obstacle equidistance pixel point.

[0007] Optionally, the determining the safety distance based on the boundary pixel point and the obstacle equidistance pixel point comprises: determining a pixel point distance between the boundary pixel point and the obstacle equidistance pixel point based on the region image information; determining an actual distance between an article boundary point corresponding to the boundary pixel point and an obstacle equidistance point corresponding to the obstacle equidistance pixel point based on the pixel point distance; determining the safety distance based on the actual distance.

[0008] Optionally, the determining the safety distance based on the actual distance comprises: determining a first included angle between a normal line of an optical axis of the image acquisition device and a vehicle height direction; determining the safety distance based on the actual distance and the first included angle.

[0009] Optionally, the determining the safety distance based on the region image information comprises: in response to an article image in the region image information not including a target article, determining an obstacle boundary point of the rear obstacle based on the region image information, the target article being an article protruding from a coverage region of a rear hatch of a vehicle; determining a third distance between the obstacle boundary point and a first plane, the first plane being a plane on which an end of the image acquisition device away from the rear hatch is located; determining the safety distance based on the third distance.

[0010] Optionally, the determining the safety distance based on the third distance comprises: determining a first included angle between a normal line of an optical axis of the image acquisition device and a vehicle height direction; determining a second included angle between the normal line of the optical axis of the image acquisition device and a field of view boundary line of the image acquisition device; determining the safety distance based on the third distance, the first included angle and the second included angle.

[0011] Optionally, the obtaining region image information collected by an image acquisition device comprises: determining a first included angle between a normal line of an optical axis of the image acquisition device and a vehicle height direction; determine a second included angle between a normal of an optical axis of the image acquisition device and a boundary line of a field of view of the image acquisition device; determine a target detection region based on the first included angle and the second included angle; obtain region image information of the target detection region collected by the image acquisition device.

[0012] Based on the same inventive concept, the second aspect of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor, and the processor implements the method of any one of the above first aspect when executing the computer program.

[0013] Based on the same inventive concept, the third aspect of the present application provides a vehicle including the electronic device of the above second aspect.

[0014] As can be seen from the above, the vehicle, the electronic device and the vehicle provided by the present application, when the gear information of the vehicle is determined to be the reverse gear and the opening degree information of the rear door of the vehicle is greater than or equal to the preset opening degree, the region image information collected by the image acquisition device is obtained, and the region image information at least includes the image information of the rear region of the vehicle. When it is determined that the region image information includes the obstacle image, it means that there is a rear obstacle affecting the reversing of the vehicle in the rear region of the vehicle. At this time, the safety distance is determined based on the region image information. Since the region image information includes the image information of the rear region of the vehicle, and the image acquisition device is located at the tail end of the inner side of the rear door, the determined safety distance is related to the opening degree of the rear door, the position of the rear obstacle of the vehicle and the condition of the articles in the trunk under the rear door. Then, when the distance between the tail of the vehicle and the rear obstacle reaches the safety distance, a warning is issued to remind the user that the distance between the vehicle and the rear obstacle is very close at this time, and the vehicle needs to be stopped. The distance between the vehicle and the rear obstacle is controlled in the range of greater than or equal to the safety distance, so as to ensure that the rear door of the vehicle or the articles in the trunk under the rear door do not collide with the rear obstacle. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the present application or related art, the following will briefly introduce the drawings needed to be used in the embodiments or related art description. Obviously, the drawings in the following description are only embodiments of the present application, and other drawings can be obtained by those skilled in the art without creating any inventive labor.

[0016] Figure 1 A schematic diagram of a use scenario in which the existing reversing collision avoidance system cannot accurately detect the distance; Figure 2A flowchart of a reverse collision warning method according to an embodiment of the present application; Figure 3 A schematic diagram of a first use scenario according to an embodiment of the present application; Figure 4 A pixel grayscale map determined based on regional image data according to an embodiment of the present application; Figure 5 A schematic diagram of a second use scenario according to an embodiment of the present application; Figure 6 A schematic diagram of a reverse collision warning device according to an embodiment of the present application; Figure 7 A schematic diagram of an electronic device according to an embodiment of the present application.

[0017] In the figure: 100, image acquisition device; 200, rear door; 300, target object; 400, rear obstacle; 500, detection pixel discard region. DETAILED DESCRIPTION

[0018] To make the objectives, technical solutions and advantages of the present application clearer, further detailed description will be made to the present application with reference to the embodiments and the accompanying drawings.

[0019] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present application should be understood as the common meanings understood by those with ordinary skills in the art to which the present application belongs. The terms "first", "second", and similar terms used in the embodiments of the present application do not represent any order, number, or importance, but are only used to distinguish different components. The terms "include", "contain", and similar terms mean that the elements or objects before the terms encompass the elements or objects listed after the terms and their equivalents, without excluding other elements or objects. The terms "connect" or "connected" and similar terms do not mean physical or mechanical connections, but can include electrical connections, whether direct or indirect. The terms "up", "down", "left", "right", and the like only represent relative positional relationships, which can change accordingly when the absolute positions of the described objects change.

[0020] The vehicle reverse collision warning system works cooperatively through various technical means, monitors the rear obstacles of the vehicle in real time and timely reminds the driver. The following are common implementation methods: 1. Ultrasonic radar Multiple ultrasonic sensors (usually with a frequency of 40-80 kHz) are installed at the rear of the vehicle to measure the distance by emitting sound waves and calculating the reflection time. It has the advantages of low cost, mature technology, suitable for short distance detection (usually within 0.2-3 meters), not affected by light, and can detect low objects (such as steps, stone pillars, etc.).

[0021] 2. Panoramic image system (also known as 360° surround view system) The panoramic image system is an auxiliary driving system that provides the driver with a 360° real-time image of the vehicle surroundings through multi-camera and image processing technology. It is mainly used in low-speed scenarios (such as parking and narrow road passing), helping the driver to eliminate blind spots and improve safety.

[0022] It is usually composed of 4-6 wide-angle cameras, installed on the front grille (front view), under the left and right side mirrors (side view), and on the tailgate (rear view). Each camera has a viewing angle of about 180°~190°, covering the entire vehicle surroundings through splicing. When in use, multiple camera images are spliced into an "aerial view" in real time, simulating the view from the top of the vehicle. In addition, the vehicle movement path (such as the reversing trajectory line) can be predicted according to the steering wheel angle and displayed.

[0023] The panoramic image system is automatically triggered when the vehicle is in reverse gear (reversing image + panoramic image), or when the vehicle is moving at low speed (e.g. <20km / h), the panoramic image system can be activated manually or automatically. It can perform parking assistance functions, such as identifying parking lines and obstacle distance prompts; it can also perform narrow lane passing assistance functions to help users observe the gap between the two sides and obstacles (such as alleys and width-limited piers); it can also monitor blind spots and compensate for low objects (such as children and pets) that cannot be seen by the rearview mirror.

[0024] 3. Millimeter wave radar Millimeter wave (24GHZ / 77GHz) is used to detect the distance and relative speed of objects, with a detection distance of up to 30 meters. It is suitable for high-speed scenarios and has strong resistance to harsh weather (rain, snow, fog), but the cost is relatively high, and it has weak recognition ability for small objects (such as bicycles), so it is usually used in combination with ultrasonic waves.

[0025] 4. Camera (vision system) Through the reversing camera and image algorithm, obstacles such as pedestrians and vehicles can be identified, providing intuitive images such as reversing images and dynamic trajectory lines. It relies on light conditions and performance decreases at night or in strong light.

[0026] As can be seen from the above, the current vehicle reversing collision warning system has many functions. When the system needs to provide a warning, the vehicle multimedia display screen shows the user the surrounding environment and the distance to the rear obstacle, and also provides a collision warning sound.

[0027] However, these existing reversing collision warning systems have a major drawback, which is that when the user opens the rear door and there is cargo protruding outside the vehicle trunk, the system may not be able to accurately detect the distance to the rear obstacle, resulting in a false warning or a missed warning. Figure 1The various reverse collision warning systems described above cannot normally provide warning when the vehicle needs to be parked again during the process of moving the vehicle, such as when the moving vehicle needs to be parked again during the process of moving the vehicle halfway through the unloading work.

[0028] For example, in the case of a 360-degree surround view system, the rear surround view camera position moves with the rear door in this scenario due to the trunk being open, and the 360-degree surround view cannot display the environment behind the vehicle. Therefore, it is impossible to detect the distance between the vehicle and the rear obstacle (such as a rear wall or a stone pillar), and it is also impossible to provide a warning before the goods collide with the rear obstacle, which may cause the goods or the rear door of the vehicle to collide with the rear obstacle, affecting the user experience.

[0029] For example, in the case of an ultrasonic radar, the vehicle is different from the calibration state at the design stage due to the protrusion of the external object at this time. Therefore, the reverse radar alarm at this time is also unreliable, and the goods may collide with the rear obstacle without a prompt alarm. Even worse, the radar alarm is disabled on some vehicle models. At this time, the user can only rely on experience to reverse the vehicle, which may cause the goods or the rear door of the vehicle to collide with the rear obstacle, affecting the user experience.

[0030] In summary, the surround view camera and ultrasonic radar on the vehicle cannot support reverse collision detection when the rear door protrudes from the vehicle.

[0031] Therefore, how to accurately provide a reverse collision warning when the rear door of the vehicle is open to avoid a collision between the rear door of the vehicle and the rear obstacle is a problem that needs to be solved.

[0032] Based on this, referring to Figure 2 The present application provides a reverse collision warning method for a vehicle, wherein the inner side of the rear door of the vehicle is provided with an image acquisition device. The image acquisition device is a device that can acquire images. For example, the image acquisition device can be a camera, a scanner, a laser radar device, etc.

[0033] The method can be executed by a parking controller, and the method specifically comprises the following steps: Step S100, in response to the gear information of the vehicle being a reverse gear and the opening degree information of the rear door of the vehicle being greater than or equal to a preset opening degree, acquiring the area image information acquired by the image acquisition device, wherein the area image information at least includes image information of the rear area of the vehicle; Step S200, in response to the area image information including obstacle image, determining a safety distance based on the area image information; Step S300, in response to the distance between the rear part of the vehicle and the rear obstacle reaching the safety distance, issuing a warning reminder.

[0034] Specifically, first, gear information of the vehicle and opening degree information of the tailgate are acquired. The gear information is used to represent the gear in which the vehicle is currently located. The opening degree information is used to represent the degree to which the tailgate is currently opened. The greater the opening degree information, the greater the degree to which the tailgate is opened.

[0035] After the gear information of the vehicle and the opening degree information of the tailgate are acquired, the gear information and the opening degree information are judged to determine whether the gear information is a reverse gear and whether the opening degree information is greater than or equal to a preset opening degree.

[0036] When the gear information is a parking gear, it indicates that the user has a reverse intention at this time.

[0037] The preset opening degree is a preset minimum opening degree value that needs to enable the image acquisition device to participate in the anti-collision warning. When the opening degree information is greater than or equal to the preset opening degree, it indicates that the degree to which the tailgate is opened is greater, and the part of the tailgate protruding from the vehicle is more, so the image acquisition device needs to be enabled to participate in the anti-collision warning at this time. When the opening degree information is less than the preset opening degree, it indicates that the degree to which the tailgate is opened is smaller, and the part of the tailgate protruding from the vehicle is less, so the image acquisition device does not need to be enabled to participate in the anti-collision warning at this time.

[0038] When it is determined that the gear information of the vehicle is a reverse gear and the opening degree information of the tailgate of the vehicle is greater than or equal to a preset opening degree, it indicates that the user has a reverse intention and the opening degree information of the tailgate is greater at this time, so the image acquisition device needs to be enabled to participate in the anti-collision warning, at this time, the region image information acquired by the image acquisition device is acquired, and the region image information at least includes image information of a region behind the vehicle.

[0039] Then, based on the region image information, it is determined whether the region image information includes an obstacle image. The obstacle image is a preset image of a rear obstacle that may appear behind the vehicle and affect the reverse of the vehicle. Exemplarily, the obstacle image can be a wall image, a stone pier image, a vehicle image, a human image, a bicycle image, an electric vehicle image, etc.

[0040] When it is determined that the region image information includes an obstacle image, it indicates that there is a rear obstacle that affects the reverse of the vehicle in the region behind the vehicle, so a safety distance needs to be determined based on the region image information. The safety distance is the minimum distance between the vehicle and the rear obstacle without collision.

[0041] In the present application, the safety distance determined based on the area image information is determined depending on more accurate area image information containing the area behind the vehicle, since the area image information contains image information of the area behind the vehicle, and the image collection device is located at the tail end inside the tailgate, the safety distance determined based on the area image information is related to the opening degree of the tailgate, the position of the obstacle behind the vehicle, and the condition of the items in the trunk behind the tailgate.

[0042] Compared with the existing radar monitoring distance, the safety distance determined based on the area image information is more accurate and more consistent with the scenario of opening the tailgate (i.e., the tailgate protruding from the vehicle), ensuring that the situation of the radar monitoring not yet reminding but the tailgate already colliding with the obstacle behind will not occur.

[0043] When the distance between the vehicle and the obstacle behind is greater than the safety distance, the tailgate of the vehicle or the items protruding from the trunk will not collide with the obstacle behind; when the distance between the vehicle and the obstacle behind is less than the safety distance, the tailgate of the vehicle or the items protruding from the trunk are most likely to collide with the obstacle behind.

[0044] During the reversing of the vehicle, the distance between the tail of the vehicle and the obstacle behind is monitored in real time, and when the distance between the tail of the vehicle and the obstacle behind reaches the safety distance, a warning reminder is issued.

[0045] Exemplarily, the warning reminder can be issued in the form of a sound alarm, a visual prompt, and / or a tactile feedback, etc. The sound alarm is to issue a warning reminder through a buzzing sound, and the frequency of the buzzing sound is accelerated with the shortening of the distance. The visual prompt is to display a distance bar or a virtual radar map on the center control screen. The tactile feedback is to issue a reminder through the vibration of the steering wheel.

[0046] Exemplarily, the distance between the tail of the vehicle and the obstacle behind can be monitored in real time by a radar. The radar is arranged at the tail of the vehicle for monitoring the distance between the tail of the vehicle and the obstacle behind, at this time, the radar only monitors the distance between the tail of the vehicle and the obstacle behind, and is irrelevant to the opened tailgate and the items protruding from the trunk.

[0047] In this application, when the vehicle's gear is determined to be in reverse and the tailgate opening is greater than or equal to a preset opening, it indicates that the user intends to reverse and the tailgate opening is relatively large. At this point, an image acquisition device is needed to participate in the reversing collision avoidance warning. Therefore, the image acquisition device acquires regional image information, which includes at least the image information of the area behind the vehicle. When it is determined that the regional image information includes an obstacle image, it indicates that there is a rear obstacle in the area behind the vehicle that could affect its reversing. A safe distance is then determined based on the regional image information, since the regional image information includes the area behind the vehicle. The image information is collected by the image acquisition device located at the inner end of the tailgate. Therefore, the determined safe distance is related to the opening of the tailgate, the position of the obstacle behind the vehicle, and the contents of the vehicle's trunk below the tailgate. When the distance between the rear of the vehicle and the obstacle behind it reaches the safe distance, a warning is issued to remind the user that the distance between the vehicle and the obstacle behind it is too close and that the vehicle needs to stop reversing. This ensures that the distance between the vehicle and the obstacle behind it is controlled within the range of greater than or equal to the safe distance, thereby ensuring that the tailgate or the contents of the vehicle's trunk below the tailgate will not collide with the obstacle behind it.

[0048] In some embodiments, see Figure 3 and Figure 4 As shown, determining the safe distance based on the region image information includes: In response to the area image information including an image of the target item 300, the boundary pixels of the item image are determined based on the area image information, wherein the target item 300 is an item that protrudes from the area covered by the rear tailgate 200 of the vehicle. Based on the boundary pixels and the obstacle image, determine the equidistant pixels of the obstacle; The safe distance is determined based on the boundary pixels and the equidistant pixels of the obstacles.

[0049] Specifically, in determining the safe distance based on the area image information, it is first necessary to determine whether the area image information includes the image of the target item 300. The target item 300 is an item that protrudes from the area covered by the rear tailgate 200 of the vehicle. That is, the distance between the target item 300 and the rear obstacle 400 is less than the distance between the tailgate end and the rear obstacle 400.

[0050] In this scenario, when a collision is possible, the point where the target item 300 first collides with the rear obstacle 400 is the point on the target item 300 that is closest to the rear obstacle 400, i.e., the outermost exposed boundary point on the target item 300 (for example, such as...). Figure 3 (Point P1 in the middle).

[0051] Therefore, the boundary pixels of the item image are first determined based on the region image information (for example, such as...). Figure 4 Point P10 in the diagram), the boundary pixel is the outermost exposed boundary point on the target item 300 (for example, such as...). Figure 3 The pixel corresponding to point P1 in the region image information. For example, the region image information can be input into a pre-trained image recognition model, and then the boundary features of the object image in the image information can be extracted based on the image recognition model to finally determine the boundary pixel of the object image.

[0052] Then, based on the boundary pixels and the obstacle image, equidistant pixels of the obstacle are determined (for example, such as...). Figure 4 Point P30 in the image), the equidistant pixel points of the obstacle are the pixel points on the rear obstacle 400 that are equidistant from the outermost boundary point in the obstacle image. Here, "equidistant" means that the distance between the two points and the first plane is the same. The first plane is the plane where the end of the image acquisition device 100 away from the rear tailgate 200 (i.e., the end closer to the ground) is located (for example, such as...). Figure 3 (The plane containing MN in the diagram).

[0053] Finally, the safe distance is determined based on the boundary pixels and the equidistant pixels of the obstacles. Thus, the determined safe distance is based on the outermost exposed boundary point on the target item 300 (e.g., ...). Figure 3 The safe distance is determined by the pixel corresponding to point P1 in the region image information (i.e., the boundary pixel) and the pixel corresponding to the position point on the rear obstacle 400 that is equidistant from the outermost boundary point in the obstacle image (i.e., the obstacle equidistant pixel). This way, the determined safe distance can be accurate to the distance between the outermost exposed boundary point on the target object 300 and the rear obstacle 400. This greatly improves the accuracy of the determined safe distance, so that when the user is reversing, a warning will be issued when the distance between the rear of the vehicle and the rear obstacle 400 reaches the safe distance, reminding the user to stop reversing. This ensures that even the outermost exposed boundary point on the target object 300 will not collide with the rear obstacle 400, thereby ensuring the safety of reversing the vehicle.

[0054] In some embodiments, the obstacle image includes a plurality of pixels; determining the equidistant pixels of the obstacle based on the boundary pixels and the obstacle image includes: Determine a first distance between the boundary pixel and a first plane, wherein the first plane is the plane where the end of the image acquisition device 100 away from the rear tailgate 200 is located; Determine a second distance between each pixel in the obstacle image and the first plane; In response to the absolute value of the difference between the second distance and the first distance being less than or equal to a preset distance, the pixel point corresponding to the second distance is determined as the equidistant pixel point of the obstacle.

[0055] Specifically, in the process of determining equidistant obstacle pixels based on the boundary pixels and the obstacle image, the first distance between the boundary pixels and the first plane is first determined (for example, such as...). Figure 3 (As shown in D1).

[0056] Then, a second distance is determined between each pixel in the obstacle image and the first plane.

[0057] When a certain second distance (exemplarily, such as...) Figure 3 (as shown in D2) and the first distance (exemplarily, as shown in D2) Figure 3 If the absolute value of the difference between the first distance and the second distance (as shown in D1) is less than or equal to a preset distance, it indicates that the first distance and the second distance are almost the same. In this case, the pixel corresponding to the second distance is determined as the equidistant pixel of the obstacle (for example, as shown in D1). Figure 3 (as shown in P3).

[0058] Furthermore, the image acquisition device 100 is a binocular camera, and the two cameras of the binocular camera are arranged along the width direction of the vehicle (i.e., Figure 3 direction shown in Y).

[0059] A binocular camera is an imaging system that mimics human binocular vision. It simultaneously captures images using two cameras (or dual lenses) placed side-by-side, and calculates depth information using the principle of parallax to achieve 3D environmental perception. The two cameras / lenses in a binocular camera are two independent optical systems, typically arranged horizontally (with a fixed baseline distance). The baseline refers to the straight-line distance between the optical centers of the two cameras, directly affecting the depth measurement range (a longer baseline results in a greater distance measured, but a smaller overlap of the field of view).

[0060] When determining the first distance between a boundary pixel and the first plane, or the second distance between each pixel in the obstacle image and the first plane, the first distance and the second distance are determined based on the parallax ranging principle of the binocular camera.

[0061] The principle of parallax ranging is as follows: the difference in pixel position (i.e., parallax) of the same object in two images acquired by the binocular camera is inversely proportional to the distance. The depth of an object can be calculated according to the following formula, which is the distance between the object and the plane where the binocular camera is located at the end closest to the object.

[0062] The formula is: wherein z is the distance between the object and the plane where the end of the binocular camera close to the object is located, f is the focal length of the binocular camera, B is the baseline length of the binocular camera, and d is the pixel displacement (i.e. the parallax) of the object in the two images obtained by the binocular camera.

[0063] Therefore, based on the above formula, the first distance between the boundary pixel point and the first plane can be determined, and the second distance between each pixel point in the obstacle image and the first plane can be determined.

[0064] In this application, the first distance and each second distance are accurately determined based on the parallax principle of the binocular camera, and then the obstacle equidistant pixel point is accurately determined based on the determined multiple second distances, which improves the accuracy of the entire distance determination and the determination of the obstacle equidistant pixel point, and further improves the accuracy of the subsequent safety distance determination.

[0065] In some embodiments, referring to Figure 4 and Figure 4 , the safety distance is determined based on the boundary pixel point and the obstacle equidistant pixel point, comprising: determining the pixel point distance between the boundary pixel point and the obstacle equidistant pixel point based on the region image information; determining the actual distance between the article boundary point corresponding to the boundary pixel point and the obstacle equidistant point corresponding to the obstacle equidistant pixel point based on the pixel point distance; determining the safety distance based on the actual distance.

[0066] Specifically, first, the pixel point distance between the boundary pixel point (i.e. the P10 point in Figure 3 which corresponds to the position of the P1 point in Figure 4 ) and the obstacle equidistant pixel point (i.e. the P30 point in Figure 3 which corresponds to the position of the P3 point in Figure 4 ) is determined based on the region image information (i.e. D0 in Figure 4 ), and the determination process of the pixel point distance is the conventional distance measurement method for determining the distance between any two pixel points on the image based on the image, which is not described here.

[0067] Then, the article boundary point (i.e. the P1 point in Figure 3 ) corresponding to the boundary pixel point (i.e. the P10 point in Figure 4 ) and the obstacle equidistant point (i.e. the P30 point in Figure 3 ) corresponding to the obstacle equidistant pixel point (i.e. the P30 point in Figure 3The actual distance between point P1 in the diagram (i.e.) Figure 3 shown as D3 in ).

[0068] Finally, based on the actual distance (i.e. Figure 3 As shown in D3 in the figure, the safe distance (i.e.) is determined. Figure 3 As shown in D4), the final determined safe distance is based on the actual distance between the object boundary point corresponding to the boundary pixel and the obstacle equidistant point corresponding to the obstacle equidistant pixel. The actual distance is determined based on the pixel distance in the regional image information. Therefore, the entire distance determination process is based on very accurate image data, which improves the accuracy of the determined pixel distance, actual distance and safe distance.

[0069] In some embodiments, see continue to see Figure 4 and Figure 3 As shown, determining the safe distance based on the actual distance includes: Determine the first angle between the optical axis normal of the image acquisition device 100 and the vehicle height direction; The safe distance is determined based on the actual distance and the first included angle.

[0070] Specifically, the optical axis normal, also known as the optical axis direction normal, refers to the perpendicular line of the optical axis normal plane. The optical axis normal plane is a plane perpendicular to the optical axis direction, and the optical axis direction normal is the perpendicular line of this optical axis normal plane. Ideally, the optical axis normal is the optical axis itself. For example, as... Figure 3 As shown, the optical axis normal is the direction indicated by L1.

[0071] The optical axis is the center line of symmetry of the optical system, and its direction is along the ideal optical propagation path of the lens (from the center of the lens to the center of the image plane; it is a virtual straight line that passes through the geometric center of all optical elements in the optical system). Ideally, light rays propagating along the optical axis do not deflect. In this embodiment, the optical system is the image acquisition device 100.

[0072] The height direction of the vehicle is Figure 3 The direction indicated by z is parallel to the normal of the image acquisition device 100 in the X direction boundary. Therefore, the determined first included angle is the optical axis normal of the image acquisition device 100 (i.e., Figure 3 As shown in L1, the boundary normal of the image acquisition device 100 in the X direction (i.e., Figure 3 The first included angle between (as shown in L4) and (i.e.) Figure 3 (as shown by θ in the diagram).

[0073] The first included angle is dependent on the installation angle of the image acquisition device 100, so the normal of the optical axis of the image acquisition device 100 can be determined based on the actual installation angle of the image acquisition device 100, and then the first included angle between the normal of the optical axis of the image acquisition device 100 and the vehicle height direction can be determined.

[0074] Then, based on the actual distance and the first included angle, the safety distance is determined (i.e. Figure 5 D4 shown in FIG. 4).

[0075] Specifically, the actual distance and the sine value of the first included angle can be determined as the safety distance, i.e. , so as to obtain the safety distance, i.e. the distance between the outermost boundary point of the exposed target object 300 and the rear obstacle 400.

[0076] In this application, when determining the safety distance, the first included angle between the normal of the optical axis of the image acquisition device 100 and the vehicle height direction is first determined, and then the safety distance is determined based on the actual distance and the first included angle. The safety distance thus determined is related to the first included angle, i.e. related to the arrangement angle of the image acquisition device 100 and the opening degree of the tailgate 200, so that the determined safety distance is more suitable for the current angle of the image acquisition device 100 and the current opening degree of the tailgate 200, and thus the determined safety distance is more in line with the actual opening of the tailgate 200.

[0077] In some embodiments, referring to FIG. 4, Figure 5 , the determination of the safety distance based on the area image information includes: In response to the fact that the target object 300 is not included in the object image in the area image information, the obstacle boundary point of the rear obstacle 400 is determined based on the area image information, and the target object 300 is an object protruding from the coverage area of the vehicle tailgate 200; A third distance between the obstacle boundary point and a first plane is determined, and the first plane is a plane where one end of the image acquisition device 100 away from the tailgate 200 is located; The safety distance is determined based on the third distance.

[0078] Specifically, when the target object 300 is not included in the object image in the area image information, it means that there is no object protruding from the coverage area of the vehicle tailgate 200, and then the position closest to the rear obstacle 400 on the vehicle is the position of the tail end of the tailgate 200.

[0079] Since the image acquisition device 100 is arranged at the tail end of the inside of the tail door 200, the specific position of the rear obstacle 400 closest to the tail end of the tail door 200 can be determined based on the field of view boundary region that the image acquisition device 100 can capture.

[0080] Therefore, the obstacle boundary point of the rear obstacle 400 is determined based on the region image information, that is, the most outer boundary point of the obstacle that the image acquisition device 100 can capture. Figure 5 The obstacle boundary point in P2 is shown in the figure. The obstacle boundary pixel point in the obstacle image can be determined based on the region image information, that is, the most outer pixel point in the obstacle image, and then the obstacle boundary pixel point determines the corresponding obstacle boundary point on the rear obstacle 400, that is, the most outer boundary point of the obstacle that the image acquisition device 100 can capture. Figure 5 The obstacle boundary point in P2 is shown in the figure. The obstacle boundary pixel point in the obstacle image can be determined based on the region image information, that is, the most outer pixel point in the obstacle image, and then the obstacle boundary pixel point determines the corresponding obstacle boundary point on the rear obstacle 400, that is, the most outer boundary point of the obstacle that the image acquisition device 100 can capture.

[0081] Then, a third distance between the obstacle boundary point and a first plane is determined, that is, D5 in the figure. The first plane is a plane where one end of the image acquisition device 100 is away from the tail door 200. The third distance can be determined according to the aforementioned parallax distance measurement principle. Figure 5

[0082] Finally, the safety distance is determined based on the third distance. In this way, the determined safety distance is related to the third distance between the obstacle boundary point and the first plane, and the third distance is related to the arrangement angle of the image acquisition device 100 and the opening degree of the tail door 200. In this way, the determined safety distance is more suitable for the current angle of the image acquisition device 100 and the current opening degree of the tail door 200, and thus the determined safety distance is more in line with the actual opening of the tail door 200.

[0083] In some embodiments, the safety distance is determined based on the third distance, including: determining a first included angle between the optical axis normal of the image acquisition device 100 and the height direction of the vehicle; determining a second included angle between the optical axis normal of the image acquisition device 100 and the field of view boundary line of the image acquisition device 100; determining the safety distance based on the third distance, the first included angle, and the second included angle.

[0084] Specifically, the field of view boundary line (i.e. Figure 5 ​The second included angle between the normal line of the optical axis of the image acquisition device 100 (i.e., L1 shown in FIG. 1) and the boundary line of the field of view of the image acquisition device 100 (i.e., L2 and L3 shown in FIG. 1) is denoted as a in FIG. 1.

[0085] The second included angle between the normal line of the optical axis of the image acquisition device 100 (i.e., L1 shown in FIG. 1) and the boundary line of the field of view of the image acquisition device 100 (i.e., L2 and L3 shown in FIG. 1) is denoted as a in FIG. 1. Figure 5 The second included angle between the normal line of the optical axis of the image acquisition device 100 (i.e., L1 shown in FIG. 1) and the boundary line of the field of view of the image acquisition device 100 (i.e., L2 and L3 shown in FIG. 1) is denoted as a in FIG. 1. Figure 5 The second included angle between the normal line of the optical axis of the image acquisition device 100 (i.e., L1 shown in FIG. 1) and the boundary line of the field of view of the image acquisition device 100 (i.e., L2 and L3 shown in FIG. 1) is denoted as a in FIG. 1. Figure 5 The second included angle between the normal line of the optical axis of the image acquisition device 100 (i.e., L1 shown in FIG. 1) and the boundary line of the field of view of the image acquisition device 100 (i.e., L2 and L3 shown in FIG. 1) is denoted as a in FIG. 1.

[0086] Then, based on the third distance (i.e., D5 shown in FIG. 1), the first included angle (i.e., θ shown in FIG. 1), and the second included angle (i.e., a shown in FIG. 1), the safety distance is determined. For example, the safety distance can be determined according to the following formula: Figure 5 Figure 5 Figure 5

[0087] In the present application, when determining the safety distance, first, the first included angle between the normal line of the optical axis of the image acquisition device 100 and the height direction of the vehicle is determined, then the second included angle between the normal line of the optical axis of the image acquisition device 100 and the boundary line of the field of view of the image acquisition device 100 is determined, and finally, based on the third distance, the first included angle, and the second included angle, the safety distance is determined. The safety distance thus determined is related to the first included angle and the second included angle, i.e., related to the arrangement angle of the image acquisition device 100 and the opening degree of the tailgate 200, so that the safety distance determined is more suitable for the current angle of the image acquisition device 100 and the current opening degree of the tailgate 200, and thus the safety distance determined is more in line with the actual opening of the tailgate 200.

[0088] In some embodiments, continuing to refer to FIG. 1, the image acquisition device 100 is arranged on the tailgate 200 of the vehicle 1000, and the image acquisition device 100 is arranged to be capable of capturing the region image information of the region 300. Figure 3 Figure 5 The method comprises the following steps. Determining the first included angle between the normal line of the optical axis of the image acquisition device 100 and the height direction of the vehicle. Determining the second included angle between the normal line of the optical axis of the image acquisition device 100 and the boundary line of the field of view of the image acquisition device 100. Determining the target detection region based on the first included angle and the second included angle. Acquiring the region image information of the target detection region captured by the image acquisition device 100.

[0089] ​​​​​Specifically, first, the first included angle (i.e. the angle of θ in Figure 5 ) and the second included angle (i.e. the angle of a in Figure 5 ) are determined, and the determination manner of the first included angle and the second included angle is as shown above, which will not be repeated here.

[0090] Then, as shown in Figure 5 , since the target object 300 in the L4 line does not protrude the coverage area of the tail gate 200, the existence of the target object 300 will not affect the determination of the safety distance at this time, so when the image acquisition device 100 performs image acquisition, the pixel rejection for the field of view angle a-(90°-θ) part (e.g. the oblique line filled part in Figure 5 ) is abandoned, and no detection is performed, and the field of view angle a-(90°-θ) area away from the rear obstacle 400 is determined as the detection pixel rejection area 500 (e.g. the area shown by the oblique line filled part in Figure 5 ), and then the entire detectable area of the image acquisition device 100 (i.e. the area between L2 and L3 in Figure 5 ) is removed from other areas outside the detection pixel rejection area 500 to determine the target detection area.

[0091] Finally, the area image information of the target detection area collected by the image acquisition device 100 is obtained, at this time, the area image information only includes the obstacle image of the rear obstacle 400 and the object image of the target object 300 protruding from the coverage area of the tail gate 200, and does not include the image of the object covered by the coverage area of the tail gate 200.

[0092] In this application, the area image information of the target detection area obtained can include the obstacle image of the rear obstacle 400 and the object image of the target object 300 protruding from the coverage area of the tail gate 200, and does not include the image of the object covered by the coverage area of the tail gate 200, which not only improves the accuracy of the safety distance determination, but also avoids collecting unnecessary image data, reduces the amount of data collected, and speeds up the execution of the data collection step.

[0093] In some embodiments, continuing to refer to Figure 2 , Figure 3 , Figure 4 and Figure 5 , in the vehicle reversing anti-collision warning method provided by the present application, the vehicle coordinate system adopts the coordinate system as shown in Figure 3 and Figure 5 , the ranging capability is enhanced, the image acquisition device 100 adopts a binocular camera, the binocular camera is arranged at the tail end of the back door inner side, the arrangement direction of the binocular camera is along the Y axis direction, and the rear obstacle 400 of the vehicle is a wall.

[0094] In the diagram, L1 is the normal to the camera's optical axis, L2 and L3 are the camera's field of view boundaries, L4 is the normal to the camera's X-direction boundary, θ is the angle between the optical axis normal and the camera's X-direction boundary normal, α is half the camera's field of view angle, point O is the camera's focal point, P1 is the outermost exposed boundary point of the cargo, P2 is the highest detection point on the wall, P3 is a detection point on the wall equidistant from P1, D1 is the distance from P1 to the camera, D2 is the distance from P3 to the camera, D3 is the pixel distance between P1 and P3, and D4 is the distance from cargo point P1 to the wall.

[0095] The specific execution process of the method is as follows: ①The cargo within line L4 is not exposed, so pixels in the field of view α - (90° - θ) portion are discarded and not detected (e.g.) Figure 3 (As shown in the shaded area).

[0096] ②The camera is a black and white camera that collects image information within the field of view, including goods and obstacle walls. The image is captured as a grayscale pixel image, which is the area image information.

[0097] ③ The area image information captured by the camera is transmitted to the parking controller. The parking controller has a built-in AI image recognition model. The AI ​​model is trained to recognize common goods (furniture, bicycles, etc.). By using the trained AI model, the boundary features of the goods are extracted from the area image information.

[0098] ④ Find the farthest point, i.e., the exposed boundary P1 of the cargo, in the grayscale image of the cargo boundary after feature extraction. Utilize the parallax distance measurement principle of the binocular camera to measure the distance between point P1 and the plane where the end of the binocular camera near the ground is located (i.e., the first distance).

[0099] ⑤ Simultaneously, in the grayscale pixel image of the wall (i.e. the obstacle image), using the same steps as in step ④, traverse and calculate the distance between each pixel and the plane where the end of the binocular camera near the ground is located (i.e., determine the second distance of each pixel), find the grayscale pixel with the same distance as P1, i.e., the point P3 with the same distance as P1. When searching for P3, a tolerance value △ (i.e. the preset distance) can be added to the calculated distance.

[0100] ⑥ Based on the region image information, calculate the pixel distance from pixel P3 to pixel P1, and obtain the actual distance D3 from P3 to P1 using the conversion rules between pixel coordinates and real-world coordinates. This means obtaining the distance between the cargo and the wall obstacle, which is the safe distance when the cargo protrudes beyond the coverage area of ​​the rear tailgate 200.

[0101] Other special scenarios: ① Scenario where the cargo does not exceed the boundary of the L4 normal (i.e., the cargo does not protrude beyond the coverage area of ​​the rear tailgate 200): If the camera does not recognize the features of the goods, i.e., the image of the goods is not included in the region image information, the above method is still used, the topmost pixel P2 point of the wall image is determined first, then the distance D5 between the topmost pixel P2 of the wall image and the binocular camera is determined, and the distance D5 is based on the formula The distance from the wall obstacle to the tail end of the tail door 200, i.e., the safety distance in the case where the goods do not protrude from the coverage area of the tail door 200, can be obtained.

[0102] In a specific implementation, when the user engages the reverse gear, the parking controller judges the opening of the tail door 200, and starts to work when the opening of the tail door reaches the calibrated position, and sends an alarm prompt signal to the in-vehicle host instrument and other systems when the distance between the vehicle and the wall obstacle reaches the safety distance (i.e., D4 in the formula Figure 3 or D6 in the formula Figure 5 The parking controller sends an alarm prompt sound to the in-vehicle host instrument and other systems, and the frequency of the alarm sound increases as the distance decreases.

[0103] The application adds an image acquisition device 100 in the trunk, and uses the image acquisition device 100 to intelligently identify the distance from the edge of the protruding goods features to the obstacle when the tail door is opened, and accurately gives a warning prompt to the user when reversing.

[0104] It should be noted that the method of the embodiments of the application can be executed by a single device, such as a computer or a server. The method of the embodiments can also be applied to a distributed scenario, and be completed by multiple devices cooperating with each other. In this distributed scenario, one of the multiple devices can only execute one or more steps in the method of the embodiments of the application, and the multiple devices can interact with each other to complete the method.

[0105] It should be noted that some embodiments of the application have been described above. In some cases, the actions or steps recorded in the above embodiments can be executed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are possible or can be advantageous.

[0106] Based on the same inventive concept, the application also provides a vehicle reversing anti-collision warning device corresponding to any of the above-mentioned method embodiments, wherein the tail end of the inner side of the tail door of the vehicle is provided with an image acquisition device.

[0107] With reference to Figure 6 , the vehicle reversing anti-collision warning device comprises: The acquisition module 100 is configured to acquire regional image information collected by an image collection device in response to the gear information of the vehicle being a reverse gear and the opening information of the rear door of the vehicle being greater than or equal to a preset opening. The determination module 200 is configured to determine a safety distance based on the regional image information in response to the regional image information including an obstacle image. The early warning module 300 is configured to issue a pre-warning in response to the distance between the rear of the vehicle and the rear obstacle reaching the safety distance.

[0108] In some embodiments, the determination module 200 is further configured to: determine a boundary pixel point of the article image based on the regional image information in response to the regional image information including an article image of a target article, the target article being an article protruding from the coverage area of the rear door of the vehicle; determine an obstacle equidistant pixel point based on the boundary pixel point and the obstacle image; determine the safety distance based on the boundary pixel point and the obstacle equidistant pixel point.

[0109] In some embodiments, the obstacle image includes a plurality of pixel points.

[0110] In some embodiments, the determination module 200 is further configured to: determine a first distance between the boundary pixel point and a first plane, the first plane being a plane in which an end of the image collection device away from the rear door is located; determine a second distance between each of the pixel points in the obstacle image and the first plane; determine the pixel point corresponding to the second distance as the obstacle equidistant pixel point in response to the absolute value of the difference between the second distance and the first distance being less than or equal to a preset distance.

[0111] In some embodiments, the determination module 200 is further configured to: determine a pixel point distance between the boundary pixel point and the obstacle equidistant pixel point based on the regional image information; determine an actual distance between an article boundary point corresponding to the boundary pixel point and an obstacle equidistant point corresponding to the obstacle equidistant pixel point based on the pixel point distance; determine the safety distance based on the actual distance.

[0112] In some embodiments, the determination module 200 is further configured to: determine a first included angle between a normal line of an optical axis of the image acquisition device and a vehicle height direction; determine the safety distance based on the actual distance and the first included angle.

[0113] In some embodiments, the determining module 200 is further configured to: determine a boundary point of the rear obstacle based on the region image information, in response to the region image information not including an object image of a target object, the target object being an object protruding from a cover region of a rear hatch of the vehicle; determine a third distance between the boundary point of the obstacle and a first plane, the first plane being a plane where an end of the image acquisition device away from the rear hatch is located; determine the safety distance based on the third distance.

[0114] In some embodiments, the determining module 200 is further configured to: determine a first included angle between a normal line of an optical axis of the image acquisition device and a vehicle height direction; determine a second included angle between the normal line of the optical axis of the image acquisition device and a boundary line of a field of view of the image acquisition device; determine the safety distance based on the third distance, the first included angle and the second included angle.

[0115] In some embodiments, the obtaining module 100 is further configured to: determine a first included angle between a normal line of an optical axis of the image acquisition device and a vehicle height direction; determine a second included angle between the normal line of the optical axis of the image acquisition device and a boundary line of a field of view of the image acquisition device; determine a target detection region based on the first included angle and the second included angle; obtain region image information of the target detection region acquired by the image acquisition device.

[0116] Based on the same inventive concept, the present application further provides an electronic device corresponding to the method of any of the above embodiments, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for warning against collision during reversing of the vehicle according to any of the above embodiments.

[0117] Figure 7A more specific electronic device hardware structure schematic diagram provided by the embodiment is shown. The device can include a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are connected to each other through the bus 1050 for internal communication.

[0118] The processor 1010 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits, and is configured to execute related programs to implement the technical solutions provided by the embodiments of the present specification.

[0119] The memory 1020 can be implemented by a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, etc. The memory 1020 can store an operating system and other application programs. When the technical solutions provided by the embodiments of the present specification are implemented by software or firmware, the related program codes are stored in the memory 1020 and are called and executed by the processor 1010.

[0120] The input / output interface 1030 is configured to connect an input / output module to realize information input and output. The input / output module can be configured as a component in the device (not shown in the figure) or can be externally connected to the device to provide corresponding functions. The input device can include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device can include a display, a speaker, a vibrator, an indicator light, etc.

[0121] The communication interface 1040 is configured to connect a communication module (not shown in the figure) to realize the communication interaction between the device and other devices. The communication module can realize communication through a wired manner (such as USB, network cable, etc.) or through a wireless manner (such as mobile network, WIFI, Bluetooth, etc.).

[0122] The bus 1050 includes a channel to transmit information between various components (such as the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040) of the device.

[0123] It should be noted that although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040 and the bus 1050, but in the specific implementation process, the device can also include other components necessary for normal operation. In addition, those skilled in the art can understand that the above device can also only contain the components necessary to implement the embodiments of the present application, and does not necessarily contain all the components shown in the figure.

[0124] The electronic device of the above embodiment is used to implement the reversing anti-collision warning method of the vehicle in any of the preceding embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0125] Based on the same inventive concept, corresponding to the method of any of the above embodiments, the present application also provides a non-transitory computer readable storage medium storing computer instructions for causing the computer to execute the reversing anti-collision warning method of the vehicle as described in any of the above embodiments.

[0126] The computer readable medium of the present embodiment includes permanent and non-permanent, removable and non-removable media, which can be implemented by any method or technology to store information. The information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible by a computing device.

[0127] The computer instructions stored in the storage medium of the above embodiment are used to cause the computer to execute the reversing anti-collision warning method of the vehicle as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0128] Based on the same inventive concept, corresponding to the method of any of the above embodiments, the present application also provides a computer program product comprising computer program instructions, which, when executed on a computer, cause the computer to execute the reversing anti-collision warning method of the vehicle as described in any of the above embodiments, have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0129] Based on the same inventive concept, the application also provides a vehicle corresponding to the method of any of the above embodiments, the vehicle comprising the reversing anti-collision warning device, the electronic device, the computer readable storage medium or the computer program product of any of the above embodiments.

[0130] The vehicle has the beneficial effects of any of the above embodiments, which will not be repeated here.

[0131] It can be understood that, before using the technical solutions of various embodiments in the present disclosure, the type, use range, use scenario, etc. of the personal information involved will be informed to the user in an appropriate manner, and the authorization of the user will be obtained.

[0132] For example, in response to receiving the active request of the user, prompt information is sent to the user to explicitly prompt the user that the operation requested to be performed will require the acquisition and use of personal information of the user. Thus, the user can choose whether to provide personal information to the software or hardware such as electronic device, application program, server or storage medium that performs the operation of the technical solutions of the present disclosure according to the prompt information.

[0133] As an optional but not limited implementation manner, in response to accepting the active request of the user, the manner of sending prompt information to the user may, for example, be a pop-up window manner, and the prompt information may be presented in the form of text in the pop-up window. In addition, the pop-up window may also carry selection controls for the user to select "agree" or "disagree" to provide personal information to the electronic device.

[0134] It can be understood that the above notification and user authorization process is only illustrative, and does not limit the implementation manner of the present disclosure, and other manners meeting the relevant laws and regulations can also be applied to the implementation manner of the present disclosure.

[0135] Those skilled in the art should understand that the above discussion of any of the embodiments is only exemplary and is not intended to imply that the scope of the present application is limited to these examples; under the idea of the present application, the above embodiments or technical features in different embodiments can also be combined, the steps can be implemented in any order, and there are many other changes of different aspects of the embodiments of the present application as described above. In order to be brief, they are not provided in details.

[0136] Additionally, to simplify the description and discussion, and so as not to obscure the embodiments of the application being presented, the well-known functions or constructions of integrated circuit (IC) chips and other components can or can not be shown in the figures and will be omitted as not to unnecessarily obscure the embodiments of the application being presented. Moreover, the devices can be shown in block diagram form in order to avoid obscuring the embodiments of the application, and this also acknowledges the fact that the details in regards to the implementation of such block devices are highly dependent on the platform within which the embodiments of the application are to be implemented (i.e., these details should be well within the purview of one of ordinary skill in the art to determine given the

[0137] While the application has been described in connection with specific embodiments thereof, it will be understood that many modifications, substitutions and variations are possible therefrom. For example, other memory architectures (e.g., dynamic RAM (DRAM)) can use the embodiments discussed.

[0138] It is therefore intended that the application be covered by all such substitutions, modifications and variations that fall within the scope of the application. It is intended that the description presented herein be considered as illustrative only and that the scope of the application be determined not with reference to the description herein, but rather with reference to the appended claims, which are hereby incorporated by reference in their entirety.

Claims

1. A method of reverse collision warning for a vehicle, characterized by, The rear end of the rear door of the vehicle is provided with an image acquisition device, and the method comprises: In response to the gear information of the vehicle being a reverse gear and the opening information of the rear door of the vehicle being greater than or equal to a preset opening, acquiring region image information collected by the image acquisition device, the region image information at least comprising image information of a region behind the vehicle; In response to the region image information comprising an obstacle image, determining a safety distance based on the region image information; In response to the distance between the rear of the vehicle and the rear obstacle reaching the safety distance, issuing a warning reminder.

2. The method of claim 1, wherein, The determination of the safety distance based on the region image information comprises: In response to the region image information comprising an object image of a target object, determining a boundary pixel point of the object image based on the region image information, the target object being an object protruding from the coverage area of the rear door of the vehicle; Determining an obstacle equidistant pixel point based on the boundary pixel point and the obstacle image; Determining the safety distance based on the boundary pixel point and the obstacle equidistant pixel point.

3. The method of claim 2, wherein, The obstacle image comprises a plurality of pixel points; The determination of the obstacle equidistant pixel point based on the boundary pixel point and the obstacle image comprises: Determining a first distance between the boundary pixel point and a first plane, the first plane being a plane at which an end of the image acquisition device away from the rear door is located; Determining a second distance between each of the pixel points in the obstacle image and the first plane; In response to the absolute value of the difference between a second distance and the first distance being less than or equal to a preset distance, determining the pixel point corresponding to the second distance as the obstacle equidistant pixel point.

4. The method of claim 2, wherein, The determination of the safety distance based on the boundary pixel point and the obstacle equidistant pixel point comprises: Determining a pixel point distance between the boundary pixel point and the obstacle equidistant pixel point based on the region image information; Determining an actual distance between an object boundary point corresponding to the boundary pixel point and an obstacle equidistant point corresponding to the obstacle equidistant pixel point based on the pixel point distance; Determining the safety distance based on the actual distance.

5. The method of claim 4, wherein, The determination of the safety distance based on the actual distance comprises: Determining a first included angle between the optical axis normal of the image acquisition device and the height direction of the vehicle; Determining the safety distance based on the actual distance and the first included angle.

6. The method of claim 1, wherein, The determination of the safety distance based on the region image information comprises: In response to the region image information not comprising an object image of a target object, determining an obstacle boundary point of the rear obstacle based on the region image information, the target object being an object protruding from the coverage area of the rear door of the vehicle; Determining a third distance between the obstacle boundary point and a first plane, the first plane being a plane at which an end of the image acquisition device away from the rear door is located; Determining the safety distance based on the third distance.

7. The method of claim 6, wherein, The determination of the safety distance based on the third distance comprises: Determining a first included angle between the optical axis normal of the image acquisition device and the height direction of the vehicle; determining a second included angle between the optical axis normal of the image acquisition device and a boundary line of a field of view of the image acquisition device; determining the safety distance based on the third distance, the first included angle and the second included angle.

8. The method of claim 1, wherein, the region image information acquired by the image acquisition device includes: determining a first included angle between the optical axis normal of the image acquisition device and a height direction of the vehicle; determining a second included angle between the optical axis normal of the image acquisition device and a boundary line of a field of view of the image acquisition device; determining a target detection region based on the first included angle and the second included angle; acquiring region image information of the target detection region acquired by the image acquisition device.

9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and running on the processor, characterized in that, the processor implements the method of any one of claims 1 to 8 when executing the computer program.

10. A vehicle characterized by comprising: the electronic device of claim 9. the electronic device of claim 9.

Images