Image determination method, and storage medium, electronic device, program product and vehicle

Abstract

An image determination method, comprising: acquiring environment information of a target region, wherein the target region is a detection region corresponding to at least one of four corners of the body of a vehicle; on the basis of the environment information, determining distribution information of obstacles in the target region, wherein the distribution information indicates the number of obstacles and the position of each obstacle; on the basis of the number of obstacles and the position of each obstacle, determining a stitching seam position in the target region; and on the basis of the stitching seam position, determining a target panoramic image corresponding to the vehicle.

Description

Image determination method, storage medium, electronic device, program product and vehicle

[0001] Cross-reference to Related Applications

[0002] The present disclosure claims priority to the Chinese patent application No. 202411084748.4, filed on August 8, 2024, and entitled “Image determination method, storage medium, electronic device, program product and vehicle”, the entire content of which is incorporated herein by reference. TECHNICAL FIELD

[0003] The present disclosure relates to the technical field of vehicles, and in particular to an image determination method, a storage medium, an electronic device, a program product and a vehicle. BACKGROUND

[0004] The panoramic view image of a vehicle is stitched from images captured by front, rear, left and right wide-angle cameras, wherein the regions of the four corners of the vehicle body are regions where the stitching seams are located. Since the four images overlap in the stitching region, objects may be lost at the stitching seams. SUMMARY

[0005] The purpose of the present disclosure is to provide an image determination method, a storage medium, an electronic device, a program product and a vehicle for improving the accuracy of generating a panoramic image of a vehicle.

[0006] According to a first aspect of an embodiment of the present disclosure, an image determination method is provided, the method comprising:

[0007] obtaining environment information of a target region, the target region being a detection region corresponding to at least one corner of a vehicle body of the vehicle;

[0008] determining distribution information of obstacles in the target region according to the environment information, the distribution information representing the number of obstacles and the position of each obstacle;

[0009] determining the position of a stitching seam of the target region according to the number of obstacles and the position of each obstacle;

[0010] determining a target panoramic image corresponding to the vehicle according to the position of the stitching seam.

[0011] Optionally, the method further comprises:

[0012] obtaining gear information of the vehicle;

[0013] determining the target region from a plurality of specified regions according to the gear information, the specified regions including detection regions corresponding to the four corners of the vehicle body.

[0014] Optionally, the method further comprises:

[0015] The preset position is taken as the splicing seam position of the other area, and the other area includes an area other than the target area in the plurality of designated areas.

[0016] Optionally, each of the target areas includes a plurality of sub-areas, and each of the sub-areas is covered by the detection area of at least two radar detection devices; and the determining of the splicing seam position of the target area according to the number of the obstacles and the position of each of the obstacles comprises:

[0017] In a case where the number of the obstacles is zero, a preset position is taken as the splicing seam position; or,

[0018] In a case where the number of the obstacles is greater than or equal to one, a target sub-area is determined from the plurality of sub-areas according to the position of the obstacle, and a designated position in the target sub-area is taken as the splicing seam position.

[0019] Optionally, the determining of the target sub-area from the plurality of sub-areas according to the position of the obstacle comprises:

[0020] In a case where the number of the obstacles is one, a movement direction of the obstacle is determined according to the position of the obstacle;

[0021] The target sub-area is determined from a sub-area located in an opposite direction of the movement direction, and the target sub-area is a sub-area farthest from the obstacle.

[0022] Optionally, the determining of the target sub-area from the plurality of sub-areas according to the position of the obstacle comprises:

[0023] In a case where the number of the obstacles is greater than one, a distribution state of the obstacles is determined according to the position of the obstacles, and the distribution state represents that the obstacles are distributed in a scattered manner or in a dense manner;

[0024] The target sub-area is determined according to the distribution state and the position of the obstacles.

[0025] Optionally, the determining of the target sub-area according to the distribution state and the position of the obstacles comprises:

[0026] In a case where the distribution state represents that the obstacles are distributed in a scattered manner, a target obstacle closest to the vehicle is determined;

[0027] A sub-area farthest from the target obstacle is taken as the target sub-area.

[0028] Optionally, the determining the target sub-region according to the distribution state and the position of the obstacle comprises:

[0029] In a case where the distribution state indicates that the obstacle is densely distributed, determining a target obstacle closest to the vehicle;

[0030] In a case where there are multiple target obstacles closest to the vehicle and the multiple target obstacles are located in different sub-regions, taking a sub-region with the least number of obstacles as the target sub-region.

[0031] Optionally, a side of the vehicle is provided with multiple first image acquisition devices for acquiring images of the environment around the vehicle, and at least one second image acquisition device is arranged at each corner of the vehicle body for acquiring an image of the environment corresponding to the corner of the vehicle body; the determining the target panoramic image corresponding to the vehicle according to the position of the splicing seam comprises:

[0032] acquiring multiple first environment images through the multiple first image acquisition devices;

[0033] acquiring multiple second environment images through the multiple second image acquisition devices;

[0034] determining the target panoramic image according to the position of the splicing seam, the first environment images and the second environment images.

[0035] Optionally, the determining the target panoramic image according to the position of the splicing seam, the first environment images and the second environment images comprises:

[0036] splicing the multiple first environment images according to the position of the splicing seam to obtain a candidate panoramic image;

[0037] fusing the multiple second environment images and the candidate panoramic image according to the position of the splicing seam to obtain the target panoramic image.

[0038] According to a second aspect of the embodiments of the present disclosure, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by a processor to implement the steps of the method according to the first aspect of the embodiments of the present disclosure.

[0039] According to a third aspect of the embodiments of the present disclosure, an electronic device is provided, which comprises:

[0040] a memory, which stores a computer program;

[0041] a processor, which is configured to execute the computer program in the memory to implement the steps of the method according to the first aspect of the embodiments of the present disclosure.

[0042] According to a fourth aspect of the embodiments of the present disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the method according to the first aspect of the embodiments of the present disclosure.

[0043] According to a fifth aspect of the embodiments of the present disclosure, a vehicle is provided, which is configured to implement the steps of the method according to the first aspect of the embodiments of the present disclosure.

[0044] According to the above technical solution, the environment information of the target region is first acquired, and the distribution information of the obstacles in the target region is determined according to the environment information. The target region is a detection region corresponding to at least one corner of the vehicle body, and the distribution information represents the number of obstacles and the position of each obstacle. Then, the splicing seam position of the target region is determined according to the number of obstacles and the position of each obstacle, and the target panoramic image corresponding to the vehicle is determined according to the splicing seam position. According to the number of obstacles and the position of each obstacle in the target region corresponding to the four corners of the vehicle body, the splicing seam position is dynamically determined. In the case that there are multiple obstacles in the splicing region, the splicing seam position can also avoid the obstacles as much as possible, thereby avoiding the situation that objects are lost at the splicing seam, and the accuracy of the panoramic image obtained is higher.

[0045] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF DRAWINGS

[0046] The accompanying drawings are included to provide a further understanding of the present disclosure and constitute a part of the specification, and are used together with the following detailed description to explain the present disclosure, but do not constitute a limitation of the present disclosure.

[0047] FIG. 1 is a schematic diagram of the layout of a camera on the side of a vehicle body.

[0048] FIG. 2 is a flowchart illustrating a method for determining an image according to an example embodiment.

[0049] FIG. 3 is a schematic diagram of ultrasonic ranging according to the embodiment of FIG. 2.

[0050] FIG. 4 is a flowchart illustrating another method for determining an image according to an example embodiment.

[0051] FIG. 5 is a schematic diagram of a detection region of an ultrasonic radar according to the embodiment of FIG. 4.

[0052] FIG. 6 is a flowchart illustrating another method for generating an image according to an example embodiment.

[0053] FIG. 7 is a flowchart illustrating a method for generating a panoramic image of a vehicle according to an example embodiment.

[0054] FIG. 8 is a block diagram of an image determination apparatus according to an example embodiment.

[0055] FIG. 9 is a block diagram of another image determination apparatus according to an example embodiment.

[0056] FIG. 10 is a block diagram of an electronic device according to an example embodiment. DETAILED DESCRIPTION

[0057] The specific embodiments of the present disclosure are described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely intended to illustrate and explain the present disclosure, and are not intended to limit the present disclosure.

[0058] Before introducing the image determination method, storage medium, electronic device, program product and vehicle according to the embodiments of the present disclosure, the application scenario of the embodiments of the present disclosure is introduced first.

[0059] As shown in FIG. 1, a wide-angle camera is arranged at each of the front, rear, left and right sides of the vehicle body. For example, a front-view camera is arranged at A near the front bumper, a rear-view camera is arranged at C near the rear bumper, and left and right-view cameras are arranged at D and B on the side of the vehicle body. After the four wide-angle cameras collect images, the images are spliced into a panoramic view image. The four corners of the top view are usually the splicing zones (Zone 1, Zone 2, Zone 3 and Zone 4). When adjacent wide-angle images are spliced in the splicing zones, a splicing seam will appear. In the related art, obstacles (such as vehicles, pedestrians, etc.) located at the splicing seam cannot be displayed in the spliced panoramic image, resulting in low accuracy of the generated panoramic image.

[0060] The present disclosure dynamically determines the position of the splicing seam according to the number of obstacles in the target region corresponding to the four corners of the vehicle body and the position of each obstacle. For the case where multiple obstacles exist in the splicing zone, the position of the splicing seam can also be made to avoid the obstacles as much as possible, thereby avoiding the loss of objects at the splicing seam and obtaining a target panoramic image with higher accuracy.

[0061] FIG. 2 is a flowchart of an image determination method according to an example embodiment. As shown in FIG. 2, the method can include the following steps.

[0062] In step S101, environmental information of a target region is obtained. The target region is a detection region corresponding to at least one corner of the four corners of the vehicle body of a vehicle.

[0063] For example, a plurality of detection devices can be arranged at the four corners of the vehicle body, wherein the detection devices can include radar detection devices and / or image detection devices. The radar detection devices can be ultrasonic radars, laser radars, etc. The image detection devices can be cameras, such as monocular cameras, binocular cameras, etc.

[0064] In some embodiments, a target region can be determined from the four detection regions corresponding to the four corners of the vehicle body. In one possible implementation, the target region can be determined according to the driving state and gear information of the vehicle. For example, when the vehicle is in D gear, the detection regions corresponding to the two corners on the front side of the vehicle body can be used as the target region. When the vehicle is in the driving state and in R gear, the detection regions corresponding to the two corners on the rear side of the vehicle body can be used as the target region.

[0065] In step S102, distribution information of the obstacles in the target region is determined according to the environmental information, wherein the distribution information represents the number of obstacles and the position of each obstacle.

[0066] For example, taking the ultrasonic radar as the radar detection device and the camera as the image detection device, when the ultrasonic radar and the cameras at the four corners of the vehicle body detect the obstacles in the stitching region, the camera can capture the obstacle image and extract the obstacle instance through the instance segmentation algorithm. The ultrasonic radar can determine the coordinates of the obstacle by using the detection distance information of a plurality of ultrasonic radars in different sub-regions through the triangular positioning method.

[0067] The ultrasonic radar ranging mainly includes phase detection method, transit time detection method, and sound wave amplitude detection method. In the transit time detection method, the time t0 is started when the ultrasonic sensor transmits the ultrasonic wave. The ultrasonic wave is reflected after hitting the obstacle, and the receiving time t1 is stopped when the reflected wave is received by the ultrasonic receiver. The distance between the obstacle and the ultrasonic radar is determined by the flight time Δt=t1-t0 between the received wave and the transmitted wave, and the ultrasonic wave propagation speed v.

[0068] As shown in (a) of FIG. 3, the related art cannot accurately describe the position of the obstacle using a single ultrasonic radar. When the same distance from the ultrasonic radar and different positions are detected, only the detection distance of the obstacle can be obtained, and the specific position cannot be confirmed. The information collected by the front-view and left-view wide-angle cameras in the edge area of the image is severely distorted, and after correction, the obstacle cannot be accurately identified. The embodiment of the present disclosure adopts the positioning method shown in (b) of FIG. 3 to determine the coordinates of the obstacle. The detection distance information of the same obstacle by two ultrasonic radars is used to confirm the position of the obstacle by the triangulation method. The pixel area corresponding to the different partitions in the image in the splicing area can be confirmed by calibration, and the transformation relationship between the ultrasonic radar and the camera is confirmed. The coordinates of the obstacle are converted from the camera coordinate system to the radar coordinate system, so as to associate the obstacle instance determined by the camera with the position of the obstacle determined by the ultrasonic radar.

[0069] In step S103, the splicing seam position of the target area is determined according to the number of obstacles and the position of each obstacle.

[0070] For example, if there is no obstacle in the target area, the preset position can be used as the splicing seam position. The preset position can be the position of the center axis of the target area, or the position of the center axis deviated to the left by a specified angle, for example, the position of the center axis deviated to the left by 5 degrees or the position of the center axis deviated to the right by 10 degrees, which is not limited in the present disclosure. If there is an obstacle in the target area, the splicing seam position of the target area can be further determined according to the number of obstacles and the position of each obstacle.

[0071] In some embodiments, the detection area corresponding to the four corners of the vehicle body can be divided into multiple sub-areas in advance, as shown in FIG. 3. For example, Zone 1 can be divided into three sub-areas L1, L2 and L3. First, the target sub-area can be determined from the multiple sub-areas according to the number of obstacles and the position of each obstacle. If there is one obstacle in the target area and the obstacle is in a moving state, the sub-area farthest from the obstacle in the opposite direction of the obstacle movement can be used as the target sub-area. If there is one obstacle in the target area and the obstacle is in a stationary state, the sub-area farthest from the obstacle can be used as the target sub-area. If there are multiple obstacles, the target obstacle closest to the vehicle can be determined, and the sub-area farthest from the target obstacle can be used as the target sub-area. If there are multiple obstacles, the sub-area with the smallest obstacle density can also be used as the target sub-area.

[0072] In other embodiments, the preset position in the target sub-area can be used as the splicing seam position, or the splicing seam position in the target sub-area can be dynamically determined according to the position of the obstacle, so that the splicing seam position can avoid the obstacle as much as possible.

[0073] Step S104, determining the target panoramic image corresponding to the vehicle according to the splicing seam position.

[0074] For example, the wide-angle images collected by the cameras on the sides of the vehicle body can be spliced according to the splicing seam position, so as to obtain the panoramic image of the vehicle. Since the splicing seam position is dynamically determined according to the number of obstacles and the position of each obstacle in the target region corresponding to the four corners of the vehicle body, even if there are multiple obstacles in the image splicing area, whether the obstacles are distributed sparsely or densely, the splicing seam position can be ensured to avoid the obstacles as much as possible, so as to avoid the situation that objects are lost at the splicing seam, and the accuracy of the target panoramic image is higher.

[0075] In summary, the present disclosure first acquires the environmental information of the target region, and determines the distribution information of the obstacles in the target region according to the environmental information. The target region is a detection region corresponding to at least one corner of the vehicle body, and the distribution information represents the number of obstacles and the position of each obstacle. Then, the splicing seam position of the target region is determined according to the number of obstacles and the position of each obstacle, and the target panoramic image corresponding to the vehicle is determined according to the splicing seam position. According to the number of obstacles and the position of each obstacle in the target region corresponding to the four corners of the vehicle body, the splicing seam position is dynamically determined. For the case that there are multiple obstacles in the splicing area, the splicing seam position can be made to avoid the obstacles as much as possible, so as to avoid the situation that objects are lost at the splicing seam, and the accuracy of the panoramic image obtained is higher.

[0076] FIG. 4 is a flowchart of another method for determining an image according to an example embodiment. As shown in FIG. 4, the method further includes the following steps.

[0077] Step S105, acquiring the gear information of the vehicle.

[0078] Step S106, determining the target region from the plurality of specified regions according to the gear information.

[0079] Step S107, taking the preset position as the splicing seam position of the other regions, and the other regions include regions other than the target region in the plurality of specified regions.

[0080] For example, different gears of the vehicle can correspond to different target regions. The target region whose splicing seam needs to be dynamically adjusted can be selected from the plurality of specified regions according to the gear information of the vehicle, and the splicing seam position of the target region is determined according to the number of obstacles and the position of each obstacle. And the preset position can be taken as the splicing seam position of the other regions in the plurality of specified regions except the target region. The specified regions can include four detection regions corresponding to the four corners of the vehicle body.

[0081] When the vehicle is in a driving state and in the D gear, the two corners of the front side of the vehicle body can be used as the target region, and the joint position of the two corners of the rear side of the vehicle body can be a preset position. When the vehicle is in a driving state and in the R gear, the two corners of the rear side of the vehicle body can be used as the target region, and the joint position of the two corners of the front side of the vehicle body can be a preset position. When the vehicle is in the P gear or the N gear, the four corners of the vehicle body can be used as the target region. In this way, the target region for which the joint position needs to be dynamically adjusted is determined according to the gear information, and the preset position is used as the joint position of other regions, so that the joint position of each image joint area does not need to be dynamically adjusted, and the amount of data processing is reduced.

[0082] In some embodiments, each target region includes a plurality of sub-regions, and each sub-region is covered by the detection region of at least two radar detection devices.

[0083] In a possible implementation, ultrasonic radars can be arranged at the four corners of the vehicle body to detect obstacles and the density thereof. For example, 16 ultrasonic radars can be arranged at the four corners of the vehicle body, and four ultrasonic radars can be arranged near each corner of the vehicle body. For example, ultrasonic radars a, b, c, and d can be arranged at the left front corner, and the detection ranges of the four ultrasonic radars can completely cover the left front image joint area.

[0084] As shown in FIG. 5, the ultrasonic radars a and d are located at the outermost sides, and the detection boundaries need to exceed the joint area boundary line. The ultrasonic radars b and c are located at the inner sides, wherein the ultrasonic radar b is close to the ultrasonic radar a, and the detection direction is biased toward the front of the vehicle (the central axis of the detection region is biased toward l1), and the ultrasonic radar c is close to the ultrasonic radar d, and the detection direction is biased toward the left side of the vehicle (the central axis of the detection region is biased toward l2). The detection overlap area of the four ultrasonic radars at each corner of the vehicle body needs to completely cover the wide-angle image joint area. As shown in FIG. 5, the image joint area Zone 1 can be divided into three regions L1, L2, and L3 according to the detection overlap of the ultrasonic radars a, b, c, and d, wherein the region L1 is the detection overlap area of the ultrasonic radars a and c, the region L2 is the detection overlap area of the ultrasonic radars b and d, and the region L3 is the detection overlap area of the ultrasonic radars b and c.

[0085] In actual application, the number of radars can not necessarily be four, but can be determined according to the actual detection range of the ultrasonic radar to be used, so that each sub-region of the image joint area can be simultaneously detected by at least two ultrasonic radars.

[0086] In some embodiments, when the number of obstacles is zero, that is, there is no obstacle in the target region, the preset position can be used as the joint position.

[0087] In some embodiments, if the number of obstacles is greater than or equal to one, i.e., there is an obstacle in the target region, then the target sub-region can be determined from the plurality of sub-regions according to the position of the obstacle, and the specified position in the target sub-region is taken as the seam position.

[0088] For example, if there is one obstacle in the target region, then the moving direction of the obstacle can be determined according to the position of the obstacle, and the sub-region farthest from the obstacle and opposite to the moving direction of the obstacle is taken as the target sub-region. As shown in FIG. 5, if the obstacle is located in region L3 and the moving direction is toward region L1, then region L2 can be taken as the target sub-region. The specified position can be the center axis of the target sub-region, or a position deviated left or right by a specified angle from the center axis, which is not limited in the present disclosure.

[0089] If the number of obstacles is greater than one, i.e., there are multiple obstacles, then the distribution state of the obstacles can be determined according to the positions of the obstacles, and the target sub-region is determined according to the distribution state and the positions of the obstacles. The distribution state represents whether the obstacles are scattered or dense.

[0090] If the distribution state represents that the obstacles are scattered, then the target obstacle closest to the vehicle can be determined, and the sub-region farthest from the target obstacle is taken as the target sub-region. As shown in FIG. 5, if obstacles A, B and C are distributed in region L1, region L2 and region L3 respectively, and the distance between obstacle A and the vehicle is 1 m, the distance between obstacle B and the vehicle is 0.5 m, and the distance between obstacle C and the vehicle is 1.2 m, then obstacle B can be taken as the target obstacle, and region L1 farthest from obstacle B is taken as the target sub-region.

[0091] If the distribution state represents that the obstacles are dense, then the target obstacle closest to the vehicle can be determined. If there are multiple target obstacles closest to the vehicle, and the multiple target obstacles are located in different sub-regions, then the sub-region with the least number of obstacles is taken as the target sub-region. As shown in FIG. 5, if the obstacles are densely distributed, there are 6 obstacles in region L1, 4 obstacles in region L2, and 5 obstacles in region L3, and there are target obstacles closest to the vehicle in region L1, region L2 and region L3, then region L2 with the least number of obstacles is taken as the target sub-region.

[0092] In this way, the seam position is dynamically determined according to the number of obstacles in the target region corresponding to the four corners of the vehicle body and the position of each obstacle, so that even if there are multiple obstacles in the image stitching area, the seam position can be ensured to avoid the obstacles as much as possible, regardless of whether the obstacles are scattered or dense, thereby avoiding the situation that objects are lost at the seam, and the accuracy of the target panoramic image is higher.

[0093] FIG. 6 is a flowchart of another method for generating an image according to an exemplary embodiment. As shown in FIG. 6, step S104 can be implemented by the following steps.

[0094] Step S1041, obtaining a plurality of first environment images through a plurality of first image acquisition devices.

[0095] Step S1042, obtaining a plurality of second environment images through a plurality of second image acquisition devices.

[0096] Step S1043, determining a target panoramic image according to the position of the stitching seam, the first environment images and the second environment images.

[0097] For example, at least one first image acquisition device for collecting environment images around the vehicle can be arranged on each side of the vehicle, and at least one second image acquisition device for collecting environment images corresponding to the corners of the vehicle body can be arranged on each corner of the vehicle body. Referring to FIG. 1, the environment images corresponding to the corners of the vehicle body can be the environment images of the stitching zones Zone 1, Zone 2, Zone 3 and Zone 4, respectively. A plurality of first environment images corresponding to the four sides of the vehicle can be collected through the first image acquisition devices, and a plurality of second environment images corresponding to the corners of the vehicle body can be collected through the second image acquisition devices. The plurality of second environment images can be stitched according to the position of the stitching seam in combination with the plurality of first environment images to obtain a target panoramic image. Since the position of the stitching seam is dynamically adjusted according to the distribution information of the obstacles, the occurrence of object loss at the stitching seam can be avoided as much as possible, and the accuracy of the target panoramic image is higher.

[0098] In some embodiments, the plurality of second environment images can be stitched according to the position of the stitching seam to obtain a candidate panoramic image, and then it can be determined whether there are obstacles at the four positions of the stitching seam according to the first environment images. If there are obstacles at a certain position of the stitching seam, the candidate panoramic image and the first environment image corresponding to the stitching seam can be fused to obtain a more accurate target panoramic image. In this way, even if the obstacles are distributed densely, causing obstacles at the dynamically adjusted position of the stitching seam, the occurrence of object loss at the stitching seam can be avoided, and the accuracy of the target panoramic image is higher.

[0099] A specific embodiment is provided below. Referring to FIG. 7, the process of generating a panoramic image of a vehicle is as follows.

[0100] Step S01: power on the entire vehicle, start the front view, rear view, left view and right view wide-angle cameras, collect the four-direction views around the vehicle, and start the four-corner ultrasonic radar and four-corner cameras to obtain the environment information of the four-corner panoramic stitching zones of the vehicle body.

[0101] Step S02: input initial four-corner splicing seam default value, i.e. preset position.

[0102] Step S03: judge gear information, and the splicing area corresponding to non-gear direction adopts the default value input in step S02.

[0103] Step S04: based on the gear information in step S03, identify whether there is an obstacle in the detection area for the splicing area on the same side as the driving direction of the vehicle corresponding to the gear.

[0104] Step S05: if the splicing area identified in step S04 does not exist an obstacle, the splicing seam default value input in step S02 is still adopted.

[0105] Step S06: judge whether the splicing area obstacle identified in step S04 is unique.

[0106] Step S07: if the splicing area obstacle identified in step S06 is unique, the splicing seam is dynamically adjusted to the sub-area without obstacle or the sub-area farthest from the obstacle.

[0107] Step S08: if the splicing area obstacle identified in step S06 is not unique, judge the distribution state of the obstacle.

[0108] Step S09: if the obstacle identified in step S08 is scattered distribution, combine the ultrasonic radar ranging information to determine the target obstacle closest to the vehicle, and dynamically adjust the splicing seam to the sub-area farthest from the target obstacle.

[0109] Step S10: if the obstacle identified in step S08 is dense distribution, combine the four-corner camera recognition information and ultrasonic radar ranging information to dynamically adjust the splicing seam to the sub-area with the smallest obstacle density.

[0110] Step S11: based on the splicing seam position obtained in step S05, step S07, step S09 and step S10, determine the four-corner splicing seam position of the vehicle body.

[0111] Step S12: combine the first environment image obtained by the four-way wide-angle camera and the second environment image obtained by the four-corner camera to obtain a panoramic surround view image, i.e. target panoramic image.

[0112] In summary, the present disclosure first acquires environmental information of a target region, and determines distribution information of obstacles in the target region according to the environmental information. The target region is a detection region corresponding to at least one corner of a vehicle body, and the distribution information represents the number of obstacles and the position of each obstacle. Then, the splicing seam position of the target region is determined according to the number of obstacles and the position of each obstacle, and the target panoramic image corresponding to the vehicle is determined according to the splicing seam position. According to the number of obstacles and the position of each obstacle in the target region corresponding to the four corners of the vehicle body, the present disclosure dynamically determines the splicing seam position. In the case that there are multiple obstacles in the splicing region, the splicing seam position can also avoid the obstacles as much as possible, thereby avoiding the situation that objects are lost at the splicing seam, and the accuracy of the obtained panoramic image is higher.

[0113] FIG. 8 is a block diagram of an image determination apparatus according to an exemplary embodiment. As shown in FIG. 8, the apparatus 200 includes the following modules.

[0114] The first acquisition module 201 is configured to acquire environmental information of a target region. The target region is a detection region corresponding to at least one corner of a vehicle body.

[0115] The first determination module 202 is configured to determine distribution information of obstacles in the target region according to the environmental information. The distribution information represents the number of obstacles and the position of each obstacle.

[0116] The second determination module 203 is configured to determine the splicing seam position of the target region according to the number of obstacles and the position of each obstacle.

[0117] The third determination module 204 is configured to determine the target panoramic image corresponding to the vehicle according to the splicing seam position.

[0118] FIG. 9 is a block diagram of another image determination apparatus according to an exemplary embodiment. As shown in FIG. 9, the apparatus 200 further includes the following modules.

[0119] The second acquisition module 205 is configured to acquire gear information of the vehicle.

[0120] The fourth determination module 206 is configured to determine the target region from a plurality of specified regions according to the gear information. The specified regions include detection regions corresponding to the four corners of the vehicle body.

[0121] In some embodiments, the second determination module 203 is further configured to take a preset position as the splicing seam position of other regions. The other regions include regions other than the target region in the plurality of specified regions.

[0122] In some embodiments, each target region comprises a plurality of sub-regions, each sub-region is covered by the detection region of at least two radar detection devices, and the second determining module 203 is configured to: in the case that the number of obstacles is zero, take the preset position as the splicing seam position. Alternatively, in the case that the number of obstacles is greater than or equal to one, determine a target sub-region from the plurality of sub-regions according to the positions of the obstacles, and take a specified position in the target sub-region as the splicing seam position.

[0123] In some embodiments, the second determining module 203 is configured to: in the case that the number of obstacles is one, determine the moving direction of the obstacle according to the position of the obstacle. In the sub-region that is opposite to the moving direction and farthest from the obstacle, determine a target sub-region, which is the sub-region farthest from the obstacle.

[0124] In some embodiments, the second determining module 203 is configured to: in the case that the number of obstacles is greater than one, determine the distribution state of the obstacles according to the positions of the obstacles, the distribution state representing whether the obstacles are dispersed or dense. Determine a target sub-region according to the distribution state and the positions of the obstacles.

[0125] In some embodiments, the second determining module 203 is configured to: in the case that the distribution state represents that the obstacles are dispersed, determine a target obstacle closest to the vehicle. Take the sub-region farthest from the target obstacle as the target sub-region.

[0126] In some embodiments, the second determining module 203 is configured to: in the case that the distribution state represents that the obstacles are dense, determine a target obstacle closest to the vehicle. In the case that there are multiple target obstacles closest to the vehicle and the multiple target obstacles are located in different sub-regions, take the sub-region with the least number of obstacles as the target sub-region.

[0127] In some embodiments, the side of the vehicle is provided with a plurality of first image acquisition devices for acquiring images of the environment around the vehicle, and at least one second image acquisition device is arranged at each corner of the vehicle body for acquiring images of the environment corresponding to the corner of the vehicle body. The third determining module 204 is configured to: acquire a plurality of first environment images through the plurality of first image acquisition devices. Acquire a plurality of second environment images through the plurality of second image acquisition devices. Determine a target panoramic image according to the splicing seam position, the first environment images, and the second environment images.

[0128] In some embodiments, the third determining module 204 is configured to: splice the plurality of first environment images according to the splicing seam position to obtain a candidate panoramic image. Fuse the plurality of second environment images and the candidate panoramic image according to the splicing seam position to obtain the target panoramic image.

[0129] With regard to the apparatus in the above-described embodiments, in which the specific manner in which each module performs operations has been described in detail in the embodiments related to the method, no detailed elaboration will be made here.

[0130] To sum up, the present disclosure first acquires the environmental information of the target region, and determines the distribution information of the obstacles in the target region according to the environmental information. The target region is a detection region corresponding to at least one corner of the vehicle body, and the distribution information represents the number of obstacles and the position of each obstacle. Then, the position of the splicing seam of the target region is determined according to the number of obstacles and the position of each obstacle, and the target panoramic image corresponding to the vehicle is determined according to the position of the splicing seam. According to the number of obstacles and the position of each obstacle in the target region corresponding to the four corners of the vehicle body, the present disclosure dynamically determines the position of the splicing seam. For the case where there are multiple obstacles in the splicing area, the position of the splicing seam can also avoid the obstacles as much as possible, thereby avoiding the situation that objects are lost at the splicing seam, and the accuracy of the obtained panoramic image is higher.

[0131] FIG. 10 is a block diagram of an electronic device, according to an exemplary embodiment. As shown in FIG. 10, the electronic device 300 can include a processor 301, a memory 302. The electronic device 300 can further include one or more of a multimedia component 303, an input / output (I / O) interface 304, and a communication component 305.

[0132] The processor 301 is configured to control overall operations of the electronic device 300 to complete all or part of the steps in the above-described image determination method. The memory 302 is configured to store various types of data to support operations of the electronic device 300, which can include, for example, instructions for any application or method operating on the electronic device 300, and application-related data, such as contact data, sent and received messages, pictures, audio, video, and the like. The memory 302 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic storage, a flash memory, a magnetic disk, or an optical disk. The multimedia component 303 can include a screen and an audio component. The screen can be, for example, a touch screen, and the audio component is configured to output and / or input audio signals. For example, the audio component can include a microphone configured to receive external audio signals. The received audio signals can be further stored in the memory 302 or transmitted through the communication component 305. The audio component also includes at least one speaker configured to output audio signals. The I / O interface 304 provides an interface between the processor 301 and other interface modules, which can be a keyboard, a mouse, a button, and the like. The buttons can be virtual buttons or physical buttons. The communication component 305 is configured to perform wired or wireless communication between the electronic device 300 and other devices. The wireless communication, such as Wi-Fi, Bluetooth, near field communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, and the like, or a combination of one or more of them, is not limited herein. Therefore, the communication component 305 can include, for example, a Wi-Fi module, a Bluetooth module, an NFC module, and the like.

[0133] In an exemplary embodiment, the electronic device 300 can be implemented by one or more Application Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), controller, microcontroller, microprocessor or other electronic elements for performing the above-described image determination method.

[0134] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the above-described image determination method. For example, the computer-readable storage medium can be the above-described memory 302 including program instructions, which can be executed by the processor 301 of the electronic device 300 to complete the above-described image determination method.

[0135] In another exemplary embodiment, a computer program product including a computer program is also provided, which, when executed by a processor, implement the steps of the above-described image determination method.

[0136] In another exemplary embodiment, a vehicle for performing the steps of the above-described image determination method is also provided.

[0137] The preferred embodiments of the present disclosure are described in detail above with reference to the accompanying drawings, but the present disclosure is not limited to the specific details in the above-described embodiments. Within the technical concept of the present disclosure, various simple modifications can be made to the technical solutions of the present disclosure, and these simple modifications all belong to the protection scope of the present disclosure.

[0138] In addition, it should be noted that each specific technical feature described in the above-described specific embodiments can be combined in any appropriate manner without contradiction, and in order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0139] Furthermore, any combination of the various different embodiments of the present disclosure can also be made, as long as it does not deviate from the idea of the present disclosure, and it should also be considered as disclosed by the present disclosure.

Claims

1. A method of determining an image, characterized by, The method comprises: acquiring environmental information of a target region, the target region being a detection region corresponding to at least one corner of a vehicle body of the vehicle; determining distribution information of obstacles in the target region according to the environmental information, the distribution information representing a number of the obstacles and a position of each of the obstacles; determining a position of a splicing seam of the target region according to the number of the obstacles and the position of each of the obstacles; and determining a target panoramic image corresponding to the vehicle according to the position of the splicing seam.

2. The method of claim 1, wherein, The method further comprises: acquiring gear information of the vehicle; and determining the target region from a plurality of specified regions according to the gear information, the specified regions including detection regions corresponding to corners of the vehicle body of the vehicle.

3. The method of claim 2, wherein, The method further comprises: taking a preset position as a splicing seam position of other regions, the other regions including regions other than the target region among the plurality of specified regions.

4. The method according to any one of claims 1 to 3, characterized in that, Each of the target regions includes a plurality of sub-regions, each of the sub-regions being covered by detection regions of at least two radar detection devices; and the determination of the position of the splicing seam of the target region according to the number of the obstacles and the position of each of the obstacles comprises: in a case where the number of the obstacles is zero, taking a preset position as the position of the splicing seam; or in a case where the number of the obstacles is greater than or equal to one, determining a target sub-region from the plurality of sub-regions according to the positions of the obstacles, and taking a specified position in the target sub-region as the position of the splicing seam.

5. The method of claim 4, wherein, The determination of the target sub-region from the plurality of sub-regions according to the positions of the obstacles comprises: in a case where the number of the obstacles is one, determining a moving direction of the obstacle according to the position of the obstacle; determining the target sub-region from sub-regions located in a direction opposite to the moving direction, the target sub-region being a sub-region farthest from the obstacle.

6. The method of claim 4, wherein, The determination of the target sub-region from the plurality of sub-regions according to the positions of the obstacles comprises: in a case where the number of the obstacles is greater than one, determining a distribution state of the obstacles according to the positions of the obstacles, the distribution state representing whether the obstacles are distributed in a scattered manner or in a dense manner; and determining the target sub-region according to the distribution state and the positions of the obstacles.

7. The method of claim 6, wherein, The determination of the target sub-region according to the distribution state and the positions of the obstacles comprises: in a case where the distribution state represents that the obstacles are distributed in a scattered manner, determining a target obstacle closest to the vehicle; and taking a sub-region farthest from the target obstacle as the target sub-region.

8. The method of claim 6, wherein, The determination of the target sub-region according to the distribution state and the positions of the obstacles comprises: in a case where the distribution state represents that the obstacles are distributed in a dense manner, determining a target obstacle closest to the vehicle; and in a case where there are a plurality of target obstacles closest to the vehicle and the plurality of target obstacles are located in different sub-regions, taking a sub-region with the least number of obstacles as the target sub-region.

9. The method according to any one of claims 1-8, characterized in that, The side of the vehicle is provided with a plurality of first image acquisition devices for acquiring images of the environment around the vehicle, and at least one second image acquisition device is arranged at each corner of the vehicle body for acquiring images of the environment corresponding to the corner of the vehicle body; The method comprises the following steps: acquiring a plurality of first environment images through the plurality of first image acquisition devices; acquiring a plurality of second environment images through the plurality of second image acquisition devices; determining the target panoramic image according to the position of the splicing seam, the first environment images and the second environment images.

10. The method of claim 9, wherein, The method comprises the following steps: splicing the plurality of first environment images according to the position of the splicing seam to obtain a candidate panoramic image; fusing the plurality of second environment images and the candidate panoramic image according to the position of the splicing seam to obtain the target panoramic image.

11. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by a processor to implement the steps of the method of any one of claims 1-10.

12. An electronic device, comprising: The computer program is executed by a processor to implement the steps of the method of any one of claims 1-10. The computer program is executed by a processor to implement the steps of the method of any one of claims 1-10. The vehicle is used to implement the steps of the method of any one of claims 1-10.

13. A computer program product, characterised in that, The vehicle is used to implement the steps of the method of any one of claims 1-10.

14. A vehicle characterized by comprising: ​

Images