A method, apparatus, equipment and medium for detecting obstacles around a target object.

Abstract

This application discloses a method, apparatus, device, and medium for detecting obstacles around a target object, relating to the field of detection. The method involves acquiring multiple regions pre-established around the target object and their corresponding initial coordinate points, using the distance from each region to its corresponding preset point as the initial distance signal for each region. When an obstacle is detected in a region, the method acquires the current distance signal from the obstacle to its corresponding preset point, adjusting the region's distance signal from the initial distance signal to the current distance signal. The position of the obstacle within the corresponding region is determined based on the current distance signal and the initial coordinate points. In this method, the surface formed by the coordinate points of each region can depict the contour trend of the obstacle approaching the target object, and the positions of obstacles around the target object within their corresponding regions can be determined relatively accurately based on the distance signals and initial coordinate points of each region.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of detection, in particular to a method and device for detecting obstacles around a target object, equipment and medium. BACKGROUND

[0002] Based on the ultrasonic radar distributed on the vehicle, the detected obstacle distance within a certain range is taken as a data source, and then a whole rectangular or arc-shaped surface or cubic color block of different colors is displayed near the obstacle on the image to warn that there is an obstacle approaching.

[0003] The display method is too rough, the visual experience effect is poor, and the outline trend of the obstacle approaching the vehicle cannot be outlined and the accurate position of the obstacle cannot be quickly judged by the driver; for example, if the obstacle is only like a slender column or a pedestrian, etc., but a large color block is displayed near the obstacle, which means that the whole area is restricted for parking or driving, so even if the driver is informed that there is an obstacle, it is not convenient to assist in obstacle avoidance.

[0004] Therefore, how to accurately determine the position of the obstacle is a technical problem that needs to be solved by those skilled in the art. SUMMARY

[0005] The purpose of the present application is to provide a method and device for detecting obstacles around a target object, equipment and medium, which can accurately determine the position of the obstacle.

[0006] To solve the above technical problems, the present application provides a method for detecting obstacles around a target object, comprising:

[0007] Obtaining a plurality of regions established around the target object in advance and initial coordinate points corresponding to each region, and taking the distance from each region to the corresponding preset point as the initial distance signal of each region;

[0008] In the case where it is detected that the region has the obstacle, obtaining the current distance signal from the obstacle to the corresponding preset point, and adjusting the distance signal of the region from the initial distance signal to the current distance signal;

[0009] According to the current distance signal of the region and the initial coordinate point, the position of the obstacle in the corresponding region is determined.

[0010] Preferably, establishing a plurality of regions around the target object comprises:

[0011] A plurality of regions are established according to the detection range of a plurality of ranging sensors on the target object around the target object, wherein all the regions surround the target object once.

[0012] Preferably, the acquiring of the initial coordinate point corresponding to each of the regions comprises:

[0013] a plurality of first coordinate points with a distance of 0 to the target object are established in the direction along the contour of the target object, wherein the target position is the position of the region on the contour of the target object, and wherein the first coordinate points surround the target object;

[0014] the association of each of the regions with the first coordinate point corresponding to the region;

[0015] the movement of the first coordinate point corresponding to each of the regions in the direction perpendicular to the target position by a distance corresponding to the region;

[0016] the acquisition of the position of the moved first coordinate point, and the position of the moved first coordinate point is taken as the initial coordinate point corresponding to each of the regions.

[0017] Preferably, before the determining of the position of the obstacle in the corresponding region according to the current distance signal of the region and the initial coordinate point, the method further comprises:

[0018] the judgment of whether each of the initial coordinate points has a corresponding region;

[0019] if not, the expansion of each of the regions to obtain an expanded region corresponding to each of the regions, the segmentation of each of the expanded regions to obtain a segmented region, and the return to the step of judging whether each of the initial coordinate points has a corresponding region;

[0020] if yes, the entering of the step of determining the position of the obstacle in the corresponding region according to the current distance signal of the region and the initial coordinate point.

[0021] Preferably, the determining of the position of the obstacle in the corresponding region according to the current distance signal of the region and the initial coordinate point comprises:

[0022] the weighted average of the distance signal of the current region and the distance signal of the region adjacent to the current region by a Gaussian filtering algorithm to obtain a weighted average value;

[0023] the determination of the adjusted coordinate point corresponding to the current region according to the weighted average value;

[0024] the determination of the position of the obstacle in the current region according to the adjusted coordinate point.

[0025] Preferably, before the step of determining the adjusted coordinate point corresponding to the current region according to the weighted average value, the method further comprises:

[0026] determining whether the current coordinate point is a point at the center of the current region;

[0027] if not, determining the position of the adjusted current coordinate point according to the weighted average value;

[0028] if yes, keeping the position of the current coordinate point.

[0029] Preferably, after the step of determining the position of the obstacle in the current region according to the adjusted coordinate point, the method further comprises:

[0030] determining the warning color information corresponding to the distance signal of each region according to the correspondence between the distance signal of the region and the color used to represent the degree of the obstacle approaching the target object;

[0031] updating the information of the warning color corresponding to each region, the initial coordinate point or the adjusted coordinate point corresponding to each region to a shader for rendering;

[0032] obtaining a streamline curve / surface used to represent the distance between the obstacle and the target object after rendering; wherein the transparency of the streamline curve / surface is the same.

[0033] To solve the above technical problems, the present application also provides a device for detecting obstacles around a target object, comprising:

[0034] an acquisition module, configured to acquire a plurality of regions established in advance around the target object and initial coordinate points corresponding to each region, and take the distance from each region to a corresponding preset point as an initial distance signal of each region;

[0035] an acquisition and adjustment module, configured to, in the case where it is detected that the region has the obstacle, acquire a current distance signal from the obstacle to the corresponding preset point, and adjust the distance signal of the region from the initial distance signal to the current distance signal;

[0036] a determination module, configured to determine the position of the obstacle in the corresponding region according to the current distance signal of the region and the initial coordinate point.

[0037] To solve the above technical problems, the present application also provides a device for detecting obstacles around a target object, comprising:

[0038] a memory, configured to store a computer program;

[0039] A processor is configured to implement the steps of the obstacle detection method around the target object when executing the computer program.

[0040] To solve the above technical problems, the present application also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program is configured to implement the steps of the obstacle detection method around the target object when executed by a processor.

[0041] The obstacle detection method around the target object provided by the present application comprises the following steps: obtaining a plurality of regions established around the target object in advance and initial coordinate points corresponding to the regions, and taking distances from the regions to preset points as initial distance signals of the regions; in the case that an obstacle is detected in a region, obtaining a current distance signal from the obstacle to the preset point, and adjusting the distance signal of the region from the initial distance signal to the current distance signal; and determining a position of the obstacle in the corresponding region according to the current distance signal of the region and the initial coordinate point. Compared with the previous method of displaying the obstacle around the target object by a large piece of rectangular or arc-shaped surface or cubic color block with different colors, in the method of the present application, a curved surface formed by the coordinate points corresponding to the regions can depict the contour trend of the obstacle approaching the target object, and the position of the obstacle in the corresponding region can be determined according to the current distance signal of the region and the initial coordinate point, so that the position of the obstacle around the target object can be determined more accurately, and the user can identify the position of the obstacle around the target object, so as to better avoid the obstacle and improve the user experience.

[0042] In addition, the present application also provides an obstacle detection device around a target object, equipment and a computer readable storage medium, which have the same or corresponding technical features as the above-mentioned obstacle detection method around the target object, and the effects are the same as above. BRIEF DESCRIPTION OF DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present application, the drawings required in the embodiments will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0044] Figure 1 A flowchart of the obstacle detection method around the target object provided by the present application;

[0045] Figure 2 A schematic diagram of the obstacle detection curve / surface around the target object provided by the present application;

[0046] Figure 3A structural diagram of an obstacle detection device around a target object is provided for an embodiment of the present application.

[0047] Figure 4 A structural diagram of an obstacle detection device around a target object is provided for another embodiment of the present application.

[0048] Figure 5 A flowchart of a display method of a streamlined curve or surface for warning obstacles around a vehicle is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0049] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the present application.

[0050] The core of the present application is to provide an obstacle detection method, device, equipment and medium around a target object, which is used to determine the position of the obstacle more accurately.

[0051] In practice, when there is an obstacle around a target object, if the position of the obstacle cannot be obtained, the target object or the obstacle may be affected. For example, when the target object is a vehicle and the obstacle is a pedestrian, if the position of the pedestrian cannot be accurately understood, the vehicle may affect the safety of the pedestrian. When the obstacle is a column, if the position of the column cannot be accurately understood, the vehicle may hit the column. Therefore, it is necessary to accurately obtain the position of the obstacle around the target object.

[0052] In order for those skilled in the art to better understand the present application, the present application will be further described in detail below with reference to the drawings and specific embodiments. Figure 1 A flowchart of an obstacle detection method around a target object is provided for an embodiment of the present application, as shown in Figure 1 , which comprises:

[0053] S10: Obtain a plurality of regions established in advance around the target object and initial coordinate points corresponding to each region, and take the distance from each region to the corresponding preset point as the initial distance signal of each region.

[0054] The target object and the obstacle are not limited in the embodiment, and are determined according to the actual scene. For example, the target object is a vehicle, and the obstacle is a pedestrian or a column. Generally, the obstacle does not affect the target object when the obstacle is within a safe distance, or the target object does not affect the obstacle. Therefore, the embodiment considers the case that the obstacle is within the safe distance. When the obstacle is within the safe distance, the obstacle and the target object may affect each other. When the obstacle is outside the safe distance, the obstacle and the target object can be ensured not to affect each other as much as possible. It should be noted that the safe distance is not only the distance between the obstacle in front of the target object and the front of the target object. There may be a safe distance around the target object, and the corresponding safe distance around the target object may be different. The value of the safe distance is not limited. For example, in the scene of a vehicle and an obstacle, the safe distance set in front of the vehicle is 1.3 m in front of the vehicle.

[0055] In order to perceive the position of the obstacle relative to the target object, a distance measuring sensor is generally arranged on the target object, and the distance measuring sensor is distributed at different positions on the target object. The number, position and type of the distance measuring sensor on the target object are not limited. For example, the target object is a vehicle, four radars can be arranged at the front and rear of the vehicle, and two laser radars can be arranged at the left and right sides of the vehicle. The four radars arranged at the front of the vehicle perceive the obstacle in front of the vehicle. The two radars arranged at the left side of the vehicle perceive the obstacle on the left side of the vehicle. A plurality of regions are established around the target object, including establishing a plurality of regions around the target object according to the detection range of the plurality of distance measuring sensors on the target object, wherein all the regions surround a circle of the target object. A plurality of virtual regions surrounding the target object are subdivided in combination with the plurality of distance measuring sensors arranged on the target object. For example, a plurality of radars are distributed around the vehicle to detect the obstacle. In order to obtain the accurate position of the obstacle in the transverse and longitudinal directions, a plurality of virtual regions surrounding the vehicle are subdivided after the combination of the plurality of radars. It should be noted that the region is established outside the target object and is perpendicular to the corresponding target object contour. Therefore, the region can be specifically described as a longitudinal region relative to the target object.

[0056] The initial coordinate points corresponding to the regions are obtained by: establishing a plurality of first coordinate points with a distance of 0 to the target object in the direction along the contour of the target object for each region; wherein the target position is the position of the region on the contour of the target object; wherein the first coordinate points surround the target object; associating each region with the first coordinate point corresponding to the region; moving the first coordinate point corresponding to each region in the direction perpendicular to the target position by a distance corresponding to the region; obtaining the position of the moved first coordinate point, and taking the position of the moved first coordinate point as the initial coordinate point corresponding to each region. Still taking the target object as an example of a vehicle, after obtaining the virtual region surrounding the vehicle body, a plurality of continuous first coordinate points with a distance of 0 to the vehicle body are established in the lateral range of each region, so that a curved coordinate system surrounding the vehicle body is obtained. After obtaining the first coordinate points, each first coordinate point needs to be associated with a region, i.e., each first coordinate point belongs to a region. For example, in the front of the vehicle head, there are three regions, first coordinate point 1, first coordinate point 2, and first coordinate point 3 belong to region 1, first coordinate point 4, first coordinate point 5, and first coordinate point 6 belong to region 2, and first coordinate point 7, first coordinate point 8, and first coordinate point 9 belong to region 3. Then, each coordinate point is moved in the direction perpendicular to the vehicle head by a distance corresponding to the region to a position away from the vehicle head. For example, if the current region in front of the vehicle head is a rectangle, the length of the side perpendicular to the vehicle head is selected as the region distance of the current region. If each region distance is 1.3 m, each first coordinate point is moved in the direction perpendicular to the vehicle head by 1.3 m to a position away from the vehicle head, and then the initial coordinate point corresponding to each region is obtained. The distance from each region to the corresponding preset point is taken as the initial distance signal of each region. It should be noted that the preset point here refers to the point on the contour of the target object corresponding to each region. For example, if the current region is in front of the vehicle head, the preset point refers to the point on the contour in front of the vehicle head corresponding to the region.

[0057] S11: In the case where it is detected that the region has an obstacle, the current distance signal of the obstacle to the corresponding preset point is obtained, and the distance signal of the region is adjusted from the initial distance signal to the current distance signal.

[0058] The presence of obstacles in each area is determined by signals from distance sensors. When an obstacle enters the warning range of a certain area (such as within the aforementioned safe distance), a distance signal for that area is obtained. Assuming the safe distance in front of the vehicle is 1.3m, if an obstacle is detected in an area in front of the vehicle and is 0.5m away, the current distance signal becomes 0.5m, and the distance signal for that area is also adjusted from 1.3m to 0.5m. If no obstacle is detected in an area in front of the vehicle, the distance signal for that area remains the initial distance signal of 1.3m. In other words, the distance signal for areas with obstacles is updated, while the distance signal for areas without detected obstacles retains its initial default value.

[0059] S12: Determine the location of the obstacle in the corresponding area based on the current distance signal and the initial coordinate point of the area.

[0060] After obtaining the distance signals for each region, the corresponding coordinate points of each region can be updated based on the distance signals. For example, the first coordinate points 1, 2, and 3 belong to region 1; the first coordinate points 4, 5, and 6 belong to region 2; and the first coordinate points 7, 8, and 9 belong to region 3. Assuming no obstacles are detected in regions 1 and 3, but an obstacle is detected in region 2, the distance signals for regions 1 and 3 remain the initial distance signal of 1.3m. In region 2, if an obstacle is detected 0.5m in front of the vehicle, the distance signal for region 2 is updated to 0.5m. Correspondingly, the three first coordinate points in region 1 and the three first coordinate points in region 3 retain their initial coordinate points; that is, the adjusted coordinate points for regions 1 and 3 are still the initial coordinate points (where the coordinates in the direction perpendicular to the vehicle's front are 1.3). However, the three first coordinate points in region 2 need to be adjusted to obtain adjusted coordinate points (where the coordinates in the direction perpendicular to the vehicle's front are adjusted from 1.3 to 0.5).

[0061] After updating the coordinate points of each region based on the distance signals of each region, the concave position of the coordinate points indicates the location of the obstacle. Connecting the coordinate points of each region forms a curve or surface that can depict the contour trend of the obstacle approaching the target object. Figure 2 This is a schematic diagram of a parking obstacle detection curve / surface provided for an embodiment of this application. (See attached diagram.) Figure 2 As shown, the vehicle is surrounded by a detection surface. This detection surface is not closed and is surrounded by multiple curves or surfaces with the same streamlined effect. The recessed positions in the surface represent the positions of obstacles.

[0062] This application provides a method for detecting obstacles around a target object, comprising: acquiring multiple regions pre-established around the target object and initial coordinate points corresponding to each region, and using the distance from each region to its corresponding preset point as the initial distance signal of each region; when an obstacle is detected in a region, acquiring the current distance signal from the obstacle to its corresponding preset point, and adjusting the distance signal of the region from the initial distance signal to the current distance signal; and determining the position of the obstacle in the corresponding region based on the current distance signal and the initial coordinate point. Compared to previous methods that displayed obstacles around a target object using large rectangular, arc-shaped, or cubic color blocks of different colors, the method in this application uses a curved surface formed by the coordinate points of each region to depict the contour trend of the obstacle approaching the target object. Furthermore, by determining the position of the obstacle in the corresponding region based on the current distance signal and the initial coordinate point, the method can more accurately determine the position of obstacles around the target object, thereby facilitating user identification of the obstacle's location for better obstacle avoidance and improved user experience.

[0063] In implementation, the number of regions may differ from the number of coordinate points, causing coordinate points to not find corresponding regions, thus making it impossible to determine whether the coordinate point's position needs adjustment. Therefore, it is necessary to ensure that the number of regions and coordinate points are consistent. In a preferred embodiment, before determining the obstacle's position within the corresponding region based on the region's current distance signal and initial coordinate points, the obstacle detection method around the target object further includes:

[0064] Determine whether each initial coordinate point has a corresponding region;

[0065] If not, expand each region to obtain the corresponding expanded region, divide each expanded region and obtain the segmented region; return to the step of determining whether each initial coordinate point has a corresponding region;

[0066] If so, proceed to the step of determining the location of the obstacle in the corresponding area based on the current distance signal and the initial coordinate point of the area.

[0067] If the area in front of the vehicle is divided into three regions, and there are nine coordinate points, it's clear that the number of regions is different from the number of coordinate points. For coordinate points that cannot find a corresponding region, it's impossible to determine whether movement is necessary based on the distance signal to that region. Therefore, in this embodiment, the three regions are further subdivided. Let's assume they are ultimately divided into small regions 1, 2, 3, 4, 5, 6, 7, 8, and 9. Small regions 1, 2, and 3 belong to region 1; small regions 4, 5, and 6 belong to region 2; and small regions 7, 8, and 9 belong to region 3. At this point, the number of regions is the same as the number of coordinate points, meaning each coordinate point can find a corresponding region.

[0068] In the method provided in this embodiment, the region is further subdivided in advance, with the number of subdivisions matching the number of coordinate points. This ensures that each coordinate point can be matched with the region signal to calculate its changing position, thereby enabling a more accurate determination of the obstacle's location.

[0069] In the above embodiments, the distance signal of the region where an obstacle is detected is updated, while the distance signal of the region where no obstacle is detected remains at its initial default value. Therefore, the region may exhibit large jumps (resulting in the loss of contour details as the obstacle approaches). To represent the contour trend of the approaching obstacle and achieve better visual effects, a preferred embodiment involves determining the position of the obstacle in the corresponding region based on the current distance signal and initial coordinates, including:

[0070] The distance signal of the current region and the distance signals of the regions adjacent to the current region are weighted and averaged using a Gaussian filtering algorithm to obtain the weighted average value.

[0071] Determine the adjusted coordinate points corresponding to the current region based on the weighted average value;

[0072] The location of the obstacle in the current area is determined based on the adjusted coordinates.

[0073] To better represent the approaching contours of obstacles and achieve a better visual effect, a Gaussian filtering algorithm is used to perform a weighted average on the regions. Specifically, each region is obtained by weighting itself and the other regions in its neighborhood. The specific operation method is as follows: a template scans each region, and the weighted average of the neighboring regions determined by the template replaces the values ​​of regions with changed distances. For example, in the above embodiment, the three first coordinate points in region 1 and the three first coordinate points in region 3 retain their initial coordinate points; that is, the adjusted coordinate points corresponding to regions 1 and 3 are still the initial coordinate points (where the coordinate in the direction perpendicular to the vehicle's front is 1.3). However, the three first coordinate points in region 2 need to be adjusted to obtain adjusted coordinate points (where the coordinate in the direction perpendicular to the vehicle's front is adjusted from 1.3 to 0.5). When connecting the coordinate points adjacent to regions 1 and 2, and the coordinate points adjacent to regions 2 and 3, there will be significant jumps. Therefore, a Gaussian filtering algorithm is used to linearly smooth the region signals. For example, the coordinates of the three first coordinate points in region 2 after processing, perpendicular to the direction of the vehicle's head, might be 0.8, 0.6, and 0.8, respectively. Compared to the previous jump from 1.3 to 0.5 for the coordinate points adjacent to region 1 and region 2, after Gaussian filtering, the coordinate points jump from 1.3 to 0.8, reducing the degree of jump. The same applies to the changes in coordinate points adjacent to region 2 and region 3.

[0074] This embodiment provides a Gaussian filtering algorithm to linearly smooth the regional signal. Through smooth streamlined curves or surfaces, it can better represent the contour trend of the approaching obstacle and achieve better visual effects.

[0075] While linear smoothing is achieved based on the above embodiments, the distance to the region center is distorted during filtering. Therefore, in a preferred embodiment, before determining the adjusted coordinate point corresponding to the current region based on the weighted average, the obstacle detection method around the target object further includes:

[0076] Determine if the current coordinate point is located at the center of the current region;

[0077] If not, the adjusted position of the current coordinate point is determined based on the weighted average.

[0078] If so, then maintain the current coordinates.

[0079] After the Gaussian filtering algorithm, the coordinates of all regions whose distance from the signal has changed will be adjusted. However, in actual smoothing, the coordinates of the intermediate points do not need to be adjusted. Therefore, it is necessary to retrieve the original value of the center point of the region. In the above embodiment, the coordinates of the three first coordinate points of region 2 after processing in the direction perpendicular to the front of the vehicle may be 0.8, 0.6, and 0.8, respectively. The original coordinate of the center point of the region is 0.5. Replacing 0.6 with the original coordinate 0.5, the final coordinates of the three first coordinate points in region 2 in the direction perpendicular to the front of the vehicle may be 0.8, 0.5, and 0.8, respectively.

[0080] In this embodiment, the coordinates of the center point corresponding to the area where the distance signal has changed are replaced with the original coordinates as a precision compensation, so that the position of the obstacle can be described more accurately, while other areas remain unchanged, preserving the smoothness characteristics.

[0081] In practice, to facilitate users' intuitive understanding of the approaching obstacle's contour trend, a preferred implementation method, after determining the obstacle's position in the current area based on the adjusted coordinate points, further includes the following obstacle detection method around the target object:

[0082] The warning color information corresponding to the distance signal of each area is determined based on the correspondence between the distance signal of the pre-set area and the color used to represent the degree of proximity of the obstacle to the target object;

[0083] Update the warning color information for each area, as well as the initial or adjusted coordinates for each area, to the shader for rendering.

[0084] Obtain the rendered streamlined curves / surfaces representing the distance between the obstacle and the target object; wherein the streamlined curves / surfaces have the same transparency.

[0085] There are no restrictions on the correspondence between the distance signal of a pre-defined area and the color used to represent the degree of proximity of an obstacle to the target object. Based on the area distance signal, the warning color information (with additional transparency information) corresponding to the current distance is obtained from a custom color range. For example, an area where an obstacle is extremely close will be displayed as a red warning; otherwise, it will be blue-green.

[0086] After updating the obtained surface coordinates and color information to the shader, the shader automatically renders the changed streamlined surface, which can then realize the display function of parking obstacle detection curve / surface (PDC) on the screen.

[0087] It should be noted that in this embodiment, the entire PDC is displayed even when there are no obstacles; when an obstacle enters the detection alarm range and slowly approaches, the complete PDC is still displayed; the transparency of the entire PDC remains unchanged as the obstacle moves from far to near; the PDC effect is the same in both 2D and 3D views.

[0088] The PDC display function provided in this embodiment enables users to clearly understand the trend of obstacles approaching the target object, and to determine the degree of obstacle approaching the target object based on color information, greatly improving the user experience.

[0089] In the above embodiments, the method for detecting obstacles around a target object has been described in detail. This application also provides embodiments of an obstacle detection device or equipment around a target object. It should be noted that this application describes the embodiments of the device part from two perspectives: one is based on the functional module, and the other is based on the hardware.

[0090] Figure 3 This is a structural diagram of an obstacle detection device around a target object provided in one embodiment of this application. This embodiment, based on functional modules, includes:

[0091] The acquisition module 10 is used to acquire multiple regions that are pre-established around the target object and the initial coordinate points corresponding to each region, and to use the distance from each region to the corresponding preset point as the initial distance signal of each region.

[0092] The acquisition and adjustment module 11 is used to acquire the current distance signal from the obstacle to the corresponding preset point when an obstacle is detected in the area, and adjust the distance signal of the area from the initial distance signal to the current distance signal.

[0093] The determination module 12 is used to determine the position of the obstacle in the corresponding area based on the current distance signal of the area and the initial coordinate point.

[0094] Since the embodiments of the device section correspond to the embodiments of the method section, the embodiments of the device section are described in the method section and will not be repeated here. Furthermore, it has the same beneficial effects as the obstacle detection method around the target object mentioned above.

[0095] Figure 4 This is a structural diagram of an obstacle detection device around a target object provided in another embodiment of this application. This embodiment is based on a hardware perspective, such as... Figure 4 As shown, the obstacle detection device around the target object includes:

[0096] Memory 20 is used to store computer programs;

[0097] The processor 21 is used to execute a computer program to implement the steps of the obstacle detection method around the target object as described in the above embodiments.

[0098] The processor 21 may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor 21 may be implemented using at least one of the following hardware forms: Digital Signal Processor (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 21 may also include a main processor and a coprocessor. The main processor, also known as the Central Processing Unit (CPU), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor 21 may integrate a Graphics Processing Unit (GPU), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, the processor 21 may also include an Artificial Intelligence (AI) processor, which is used to handle computational operations related to machine learning.

[0099] The memory 20 may include one or more computer-readable storage media, which may be non-transitory. The memory 20 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In this embodiment, the memory 20 is used to store at least the following computer program 201, which, after being loaded and executed by the processor 21, is capable of implementing the relevant steps of the obstacle detection method around the target object disclosed in any of the foregoing embodiments. In addition, the resources stored in the memory 20 may also include an operating system 202 and data 203, and the storage method may be temporary or permanent storage. The operating system 202 may include Windows, Unix, Linux, etc. The data 203 may include, but is not limited to, the data involved in the obstacle detection method around the target object mentioned above.

[0100] In some embodiments, the obstacle detection device around the target object may further include a display screen 22, an input / output interface 23, a communication interface 24, a power supply 25, and a communication bus 26.

[0101] Those skilled in the art will understand that Figure 4The structure shown does not constitute a limitation on the obstacle detection device around the target object and may include more or fewer components than shown.

[0102] The obstacle detection device around a target object provided in this application includes a memory and a processor. When the processor executes the program stored in the memory, it can implement the following method: obstacle detection method around a target object, with the same effect as above.

[0103] This application also provides an embodiment corresponding to a computer-readable storage medium. The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps described in the above method embodiments.

[0104] It is understood that if the methods in the above embodiments are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and executes all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0105] The computer-readable storage medium provided in this application includes the obstacle detection method around the target object mentioned above, and has the same effect.

[0106] To enable those skilled in the art to better understand the present application, the following description, in conjunction with the appendix, is provided. Figure 5 The present application will be further described in detail with reference to specific embodiments. Figure 5 A flowchart illustrating a method for displaying streamlined curves or surfaces that warn of obstacles around a vehicle, as provided in this application embodiment, is shown below. Figure 5 As shown, the method includes:

[0107] S13: Acquire obstacle distance signals in different longitudinal zones around the vehicle;

[0108] S14: Establish the initial surface coordinate system;

[0109] S15: Mapping between the longitudinal region and the surface coordinate system;

[0110] S16: Perform linear smoothing on the longitudinal signal;

[0111] S17: Accuracy compensation for the central longitudinal zone;

[0112] S18: Update the position of the surface coordinate system;

[0113] S19: Obtain the corresponding warning color information based on the longitudinal zone signal;

[0114] S20: Render PDC.

[0115] The streamlined curves or surfaces for displaying obstacles around a vehicle provided in this embodiment can roughly outline the trend of an obstacle approaching the vehicle and display the accurate position of the obstacle through smooth streamlined curves or surfaces. This helps the driver to identify obstacles around the vehicle more quickly and effectively, so as to better avoid obstacles during parking or in complex road conditions. The smooth streamlined curves or surfaces also greatly enhance the visual effect of technology. The position of the obstacle is displayed accurately enough, at least in the plane dimension of the ground, without ambiguity - accurately representing the accurate and unique position of the obstacle in both the horizontal and vertical directions.

[0116] The foregoing has provided a detailed description of a method, apparatus, device, and medium for detecting obstacles around a target object, as provided in this application. The various embodiments in the specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section. It should be noted that those skilled in the art can make several improvements and modifications to this application without departing from the principles of this application, and these improvements and modifications also fall within the protection scope of the claims of this application.

[0117] It should also be noted that, in this specification, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

Claims

1. An obstacle detection method around a target object, characterized by, The method comprises: acquiring a plurality of regions established in advance around the target object and initial coordinate points corresponding to each of the regions, and taking the distance from each of the regions to a corresponding preset point as an initial distance signal of each of the regions; wherein the regions are established outside the target object and are perpendicular to the corresponding contour of the target object; in the case where the regions are detected to have the obstacle, acquiring a current distance signal from the obstacle to the corresponding preset point, and adjusting the distance signal of each of the regions from the initial distance signal to the current distance signal; whether each of the regions has the obstacle is determined by the signal of the distance measuring sensor, and when the obstacle reaches the alarm range of the region, the distance signal of the region will be obtained; determining the position of the obstacle in the corresponding region according to the current distance signal of the region and the initial coordinate point; wherein, after the coordinate points corresponding to each of the regions are updated according to the distance signal of each of the regions, the position of the coordinate point inwards is determined as the position of the obstacle; connecting the coordinate points corresponding to each of the regions to form a curve or a surface, which represents the contour trend of the obstacle approaching the target object; establishing a plurality of the regions around the target object comprises: establishing a plurality of the regions according to the detection range of a plurality of distance measuring sensors on the target object around the target object, wherein all the regions surround the target object once; acquiring the initial coordinate points corresponding to each of the regions comprises: establishing a plurality of first coordinate points with a target position of 0 from the target object in the direction along the contour of the target object; wherein the target position is the position corresponding to the region on the contour of the target object; wherein the first coordinate points surround the target object once; associating each of the regions with the first coordinate point corresponding to the region; moving the first coordinate point corresponding to each of the regions in the direction perpendicular to each of the target positions by the distance of the corresponding region; acquiring the position of each of the first coordinate points after the movement, and taking the position of each of the first coordinate points after the movement as the initial coordinate point corresponding to each of the regions.

2. The method of obstacle detection around a target object according to claim 1, wherein, Before the step of determining the position of the obstacle in the corresponding region according to the current distance signal of the region and the initial coordinate point, the method further comprises: determining whether each of the initial coordinate points has the corresponding region; if not, expanding each of the regions to obtain an expanded region corresponding to each of the regions, segmenting each of the expanded regions and acquiring a segmented region; returning to the step of determining whether each of the initial coordinate points has the corresponding region; if yes, entering the step of determining the position of the obstacle in the corresponding region according to the current distance signal of the region and the initial coordinate point.

3. The method of obstacle detection around a target object according to claim 2, wherein, The step of determining the position of the obstacle in the corresponding region according to the current distance signal of the region and the initial coordinate point comprises: performing weighted average on the distance signal of the current region and the distance signal of the region adjacent to the current region by a Gaussian filtering algorithm and acquiring a weighted average value; determining an adjusted coordinate point corresponding to the current region according to the weighted average value; determining the position of the obstacle in the current region according to the adjusted coordinate point.

4. The method of obstacle detection around a target object according to claim 3, wherein, Before the step of determining the adjusted coordinate point corresponding to the current region according to the weighted average value, the method further comprises: determining whether the current coordinate point is a point at the center of the current region; if not, determining the position of the adjusted current coordinate point according to the weighted average value; if yes, keeping the position of the current coordinate point.

5. The method of obstacle detection around a target object according to claim 3 or 4, characterized in that, After the step of determining the position of the obstacle in the current region according to the adjusted coordinate point, the method further comprises: determining the warning color information corresponding to the distance signal of each region according to the correspondence between the distance signal of each region and the color used to represent the degree of the obstacle approaching the target object; updating the information of the warning color corresponding to each region, the initial coordinate point or the adjusted coordinate point of each region to a shader for rendering; obtaining a streamline curve / surface after rendering, which is used to represent the distance between the obstacle and the target object; wherein the transparency of the streamline curve / surface is the same.

6. An obstacle detection device around a target object, characterized by, comprises: an obtaining module, configured to obtain a plurality of regions and initial coordinate points corresponding to each region, which are established around the target object in advance, and take the distance from each region to a corresponding preset point as the initial distance signal of each region; wherein the regions are established outside the target object and are perpendicular to the corresponding contour of the target object; an obtaining and adjusting module, configured to, in the case that the obstacle is detected in the region, obtain the current distance signal from the obstacle to the corresponding preset point, and adjust the distance signal of the region from the initial distance signal to the current distance signal; whether the obstacle exists in each region is determined by the signal of a ranging sensor; when the obstacle reaches the alarm range of the region, the distance signal of the region will be obtained; a determining module, configured to determine the position of the obstacle in the corresponding region according to the current distance signal of the region and the initial coordinate point; wherein, after the coordinate points corresponding to each region are updated according to the distance signal of each region, the position of the concave coordinate point is determined as the position of the obstacle; the curve or surface formed by connecting the coordinate points corresponding to each region represents the contour trend of the obstacle approaching the target object; establishing a plurality of regions around the target object comprises: establishing a plurality of regions according to the detection range of a plurality of ranging sensors on the target object around the target object, wherein all the regions surround the target object once; obtaining the initial coordinate points corresponding to each region comprises: establishing a plurality of first coordinate points with a target position of 0 from the target object in the direction along the contour of the target object; wherein the target position is the position of the region on the contour of the target object; wherein the first coordinate points surround the target object once; associating each region with the first coordinate point corresponding to the region; move the first coordinate point corresponding to each of the regions along a direction perpendicular to each of the target positions by a region distance corresponding to the region; obtain the position of each of the moved first coordinate points, and take the position of each of the moved first coordinate points as the initial coordinate point corresponding to the region.

7. An obstacle detection apparatus around a target object, characterized by, The method comprises the following steps: a memory for storing a computer program; a processor for executing the computer program to implement the steps of the obstacle detection method around the target object according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is executed by the processor to implement the steps of the obstacle detection method around the target object according to any one of claims 1 to 5.

Images