Method, apparatus, electronic device and storage medium for determining target motion information

Abstract

An embodiment of the present application provides a method, apparatus, electronic device, and computer-readable storage medium for determining target motion information, which relates to the technical field of traffic monitoring. The method includes: obtaining a first image collected by an image acquisition device and a second image captured by a target physical capture device for the same area at the same moment; determining a first reference target in the first image, and respectively determining first relative position information between at least one first target in the first image and the first reference target; determining a second reference target in the second image, and respectively determining second relative position information between at least one second target in the second image and the second reference target; and determining the fused motion information of the target at the current moment in the area according to the first relative position information and the second relative position information. The embodiment of the present application can efficiently and comprehensively determine the fused motion information of the target based on the relative position information.

Description

Technical Field

[0001] This application relates to the technical field of traffic monitoring and processing. Specifically, this application relates to a method, apparatus, electronic device, and computer-readable storage medium for determining target motion information. Background Art

[0002] In the traffic industry, radar is less affected by environmental factors and can accurately detect moving targets. Therefore, moving targets can be tracked and analyzed by radar. However, it is not intuitive enough to determine the information of moving targets only by radar. Therefore, the target motion information determined by radar is not comprehensive enough, and the recognition effect is poor. Summary of the Invention

[0003] This application provides a method, apparatus, electronic device, and computer-readable storage medium for determining target motion information, which can solve the problem of incomplete acquisition of target motion information. The technical solutions are as follows:

[0004] Obtain a first image collected by an image acquisition device and a second image captured by a target physical capture device for the same area at the same moment;

[0005] Determine a first reference target in the first image, and respectively determine first relative position information between at least one first target in the first image and the first reference target;

[0006] Determine a second reference target in the second image, and respectively determine second relative position information between at least one second target in the second image and the second reference target;

[0007] Determine the fused motion information of the target at the current moment in the area according to the first relative position information and the second relative position information.

[0008] In a possible implementation, determining the first relative position information between at least one first target in the first image and the first reference target includes:

[0009] Obtain a first distance between the first reference target and the image acquisition device;

[0010] Obtain a second distance between at least one first target and the image acquisition device;

[0011] Determine the first relative position information according to the ratio of the second distance to the first distance.

[0012] In a possible implementation, the first image includes an image containing a lane; obtaining the first distance between the first reference target and the image acquisition device includes:

[0013] Obtain the focal length of the image acquisition device, the actual width of the lane in the first image, and the lane pixel width for each target in the first image;

[0014] Determine the first distance between the first reference target and the image acquisition device based on the focal length of the image acquisition device, the actual width of the lane in the first image, and the lane pixel width of the first reference target in the first image;

[0015] Obtain the second distances between at least one first target and the image acquisition device, including:

[0016] Determine the second distances between at least one first target and the image acquisition device based on the focal length of the image acquisition device, the actual width of the lane in the first image, and the lane pixel width of at least one first target in the first image.

[0017] In another possible implementation, the target physical capture device includes a radar device; determining the second relative position information between the second target and the second reference target in the second image includes:

[0018] Obtain the third distance between the second reference target and the radar device;

[0019] Obtain the fourth distances between at least one second target and the radar device;

[0020] Determine the second relative position information according to the ratio of the fourth distance to the second distance.

[0021] In one possible implementation, determining the fusion motion information of the target at the current moment in this area according to the first relative position information and the second relative position information includes:

[0022] Determine the second targets respectively matching at least one first target according to the first relative position information and the second relative position information;

[0023] Fuse the first motion information of the first target and the second motion information of the matching second target to obtain the fusion motion information of the target at the current moment in this area.

[0024] In another possible implementation, determining the fusion motion information of the target at the current moment in this area according to the first relative position information and the second relative position information includes:

[0025] Determine the information error between the first relative position information and the second relative position information;

[0026] If the error is less than the preset error value, determine the fusion motion information of the target at the current moment in this area according to the first relative position information and the second relative position information.

[0027] In yet another possible implementation, the method for determining target motion information further includes:

[0028] Determine the comprehensive information error between the first relative position information of the first images of multiple such regions at different times and the second relative position information of the second images at multiple different times;

[0029] If the comprehensive error is less than a preset error value, determine second targets respectively matching at least one first target according to the first relative position information of each moment of this region and the second relative position information of each moment of this region;

[0030] Fuse the first motion information of the first targets of each moment of this region with the second motion information of the matching second targets to obtain the fused motion information of the targets at different times of this region.

[0031] In another possible implementation, determining the fused motion information of the targets at the current moment in this region according to the first relative position information and the second relative position information includes:

[0032] Determine second targets respectively matching at least one first target according to the first relative position information and the second relative position information;

[0033] Fuse the first motion information of the first targets with the second motion information of the matching second targets to obtain the fused motion information of the targets at the current moment in this region.

[0034] According to another aspect of the present application, there is provided a target motion information determination device, and this device includes:

[0035] An acquisition module, configured to acquire a first image collected by an image acquisition device and a second image captured by a target physical capture device for the same region at the same moment;

[0036] A first determination module, configured to determine a first reference target in the first image, and respectively determine the first relative position information between at least one first target in the first image and the first reference target;

[0037] A second determination module, configured to determine a second reference target in the second image, and respectively determine the second relative position information between at least one second target in the second image and the second reference target;

[0038] A third determination module, configured to determine the fused motion information of the targets at the current moment in this region according to the first relative position information and the second relative position information.

[0039] In a possible implementation, the third determination module includes:

[0040] A matching sub-module, configured to determine second targets respectively matching at least one first target according to the first relative position information and the second relative position information;

[0041] A fusion sub-module, configured to fuse the first motion information of a first target with the second motion information of a second target that matches it, to obtain the fused motion information of the target at the current moment in this area.

[0042] According to another aspect of the present application, there is provided an electronic device, which includes:

[0043] One or more processors;

[0044] A memory;

[0045] One or more applications, where one or more applications are stored in the memory and are configured to be executed by one or more processors, and one or more programs are configured to perform operations corresponding to the method for determining target motion information as shown in the first aspect of the present application.

[0046] According to still another aspect of the present application, there is provided a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the method for determining target motion information as shown in the first aspect of the present application.

[0047] The beneficial effects brought by the technical solution provided by the present application are as follows: By obtaining the first image collected by the first acquisition device and the second image collected by the second acquisition device for the same area at the same moment, it can provide reference materials for determining the motion information of the target in the current area at the current moment; by determining the relative position information between each target and the reference target, the position information of each target in each image can be determined; according to the first relative position information and the second relative position information, the first target in the first image and the second target in the second image can be automatically matched, improving the matching efficiency. The motion information collected in the first image and the second image can be respectively extracted for the matched targets, and finally the fused motion information of the target at the current moment in this area is obtained, making the determined fused motion information more comprehensive. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments of the present application.

[0049] Figure 1 It is a schematic flowchart of a method for determining target motion information provided by an embodiment of the present application;

[0050] Figure 2 It is a schematic diagram of a first image provided by an embodiment of the present application;

[0051] Figure 3 It is a coordinate system conversion diagram of a camera imaging coordinate system and an actual physical coordinate system provided by an embodiment of the present application;

[0052] Figure 4 Schematic diagram of a second image provided by an embodiment of the present application;

[0053] Figure 5 Flow schematic diagram of another method for determining target motion information provided by an embodiment of the present application;

[0054] Figure 6 Structural schematic diagram of a device for determining target motion information provided by an embodiment of the present application;

[0055] Figure 7 Structural schematic diagram of an electronic device for determining target motion information provided by an embodiment of the present application. Detailed implementation manners

[0056] The embodiments of the present application will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described by referring to the accompanying drawings are exemplary and are only used to explain the present application and cannot be construed as a limitation to the present application.

[0057] Those skilled in the art of the present technology can understand that unless specifically stated otherwise, the singular forms "a", "an", "the", and "said" used herein may also include the plural forms. It should be further understood that the term "including" used in the specification of the present application means the presence of the described features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It should be understood that when we say an element is "connected" or "coupled" to another element, it can be directly connected or coupled to other elements, or there may also be intermediate elements. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The phrase "and / or" used herein includes all or any unit of one or more related listed items and all combinations.

[0058] To make the objectives, technical solutions, and advantages of the present application clearer, the embodiments of the present application will be further described in detail below in conjunction with the accompanying drawings.

[0059] The technical solutions of the present application and how the technical solutions of the present application solve the above technical problems will be described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0060] An embodiment of the present application provides a method for determining target motion information. As Figure 1 shown, the method includes:

[0061] Step S101: Obtain a first image captured by an image acquisition device and a second image captured by a target physical capture device for the same area at the same moment.

[0062] Among them, the motion information of the target includes information such as the distance, angle, geographical location, and speed of the moving target. It can be understood that often only through the image acquisition device or only through the target physical capture device, it is not possible to accurately determine the comprehensive motion information of the moving target in this area. Therefore, the motion information of the moving target captured by the image acquisition device and the target physical capture device can be combined to obtain more comprehensive motion information.

[0063] Among them, both the image acquisition device and the target physical capture device can capture the target, and the target in the area is the first target in the first image and the second target in the second image.

[0064] In the actual device installation process, the image acquisition device and the target physical capture device can be integrally installed, that is, the actual distance of the moving target relative to the image acquisition device is the same as the actual distance of the moving target relative to the target physical capture device, and the distance deviation between the two can be ignored. And for the convenience of calculation, both the image acquisition device and the target physical capture device are installed upright, that is, the image acquisition device and the target physical capture device are installed perpendicular to the horizontal plane.

[0065] Step S102: Determine a first reference target in the first image, and respectively determine the first relative position information between at least one first target in the first image and the first reference target.

[0066] Among them, for the convenience of calculation, the first target at a specific position in the first image can be determined as the first reference target. For example, the first target at the bottom edge of the first image is used as the first reference target. The first relative position information between the first target and the first reference target can be information such as the azimuth and distance of the first target relative to the first reference target. By obtaining the first relative position information between the first target and the first reference target, the azimuth or distance information of each first target can be roughly locked.

[0067] In an embodiment of the present application, a possible implementation manner is provided to determine the first relative position information between at least one first target in the first image and the first reference target, including:

[0068] (1) Obtain the first distance between the first reference target and the image acquisition device.

[0069] (2) Obtain the second distance between at least one first target and the image acquisition device.

[0070] (3) Determine the first relative position information according to the ratio of the second distance to the first distance.

[0071] In one embodiment of the present application, the image acquisition device may be a terminal device with an image acquisition function such as a camera, a video camera, and a mobile phone. The camera can capture a moving target with an intelligent algorithm to obtain the position of the moving target in the pixels of the picture.

[0072] When determining the first relative position information between the first target in the first image and the first reference target, it can be determined based on the first distance between the first reference target and the camera device and the second distance between the first target and the camera device.

[0073] If the camera captures multiple targets at a certain moment, the target closest to the lower edge of the camera, such as target A, is taken as the first reference target, and the remaining targets A1, A2, A3... An are taken as the first targets. Then, the actual distances LA, LA1, LA2... LAn of each target relative to the camera are determined, and then the ratios of LA1, LA2... LAn to LA are calculated. Thus, the first relative position information of the first target relative to the first reference target can be determined.

[0074] A possible implementation manner is provided in the embodiment of the present application. The first image includes an image containing a lane. Obtaining the first distance between the first reference target and the image acquisition device, and obtaining the second distance between at least one first target and the image acquisition device includes:

[0075] (1) Obtain the focal length of the image acquisition device, the actual width of the lane in the first image, and the lane pixel width for each target in the first image.

[0076] (2) Determine the first distance between the first reference target and the image acquisition device based on the focal length of the image acquisition device, the actual width of the lane in the first image, and the lane pixel width for the first reference target in the first image.

[0077] (3) Determine the second distance between at least one first target and the image acquisition device based on the focal length of the image acquisition device, the actual width of the lane in the first image, and the lane pixel width for at least one first target in the first image.

[0078] It can be understood that the first image includes an image containing a lane, and the moving targets in the first image include vehicles moving in the lane. Exemplarily, the first image can be as Figure 2 shown. Figure 2 The first image is captured by the camera acquisition device. The first image includes a lane and multiple first targets 201. The first targets can be vehicles, and each lane is marked with a lane number.

[0079] Since the camera device cannot directly measure the actual distance between the first target and the camera device, parameters in the actual physical world can be used, such as the actual width of the lane and parameters of the camera device itself, such as the focal length of the camera device and the pixel width occupied by the lane in the camera image, to determine the actual distance between the first target and the camera device.

[0080] It should be noted that objects in the real world correspond one-to-one with the objects on the camera sensor plane, as Figure 3 shown. Figure 3 As shown in the conversion diagram of the camera imaging coordinate system and the actual physical coordinate system, the camera imaging is similar to the principle of pinhole imaging. The coordinates of any point relative to the camera imaging plane are (Xc, Yc, Zc), and the coordinates of the image on the camera sensor plane are (x, y). Then, we can get: x = f * Xc / Zc, y = f * Yc / Zc.

[0081] After obtaining the above coordinate conversion relationship, for the Figure 2 first target, that is, the vehicle, the distance between the first target and the camera device can be determined using the parameters in the actual physical world and the parameters of the camera device.

[0082] Specifically, Figure 2 the actual distance between point 1 and point 2 is the lane width W. Let the coordinates of point 1 be (Xc1, Yc1, Zc1), and the coordinates of point 2 be (Xc2, Yc2, Zc2). The mapped coordinates on the camera imaging plane are (x1, y1) and (x2, y2) respectively. Since the camera device is installed perpendicular to the horizontal plane on the road, that is, the imaging X-axis is perpendicular to the lane line, the Y coordinates and Z coordinates of point 1 and point 2 are the same. W = |Xc1 - Xc2|, and the distance w mapped to the camera imaging plane is w = |x2 - x1| = f * |Xc2 - Xc1| / Zc, that is, Zc = f * W / w. If the width size of a single pixel of the camera imaging sensor is a, and the pixel width occupied by the above lane width in the camera image is Wp, then the distance w mapped by the lane width to the camera imaging plane is w = Wp * a, that is, Zc = f * W / (Wp * a). It can be understood that in the traffic camera installation scenario, generally a larger focal length is used, so the angle between the Z-axis and the road target is generally very small (<8°). Therefore, the Z-axis distance L of the target ≈ the actual distance between the camera and the target, which is also regarded as L, that is, L = f * W / (Wp * a).

[0083] When the camera captures the target, the actual width of the lane is known as W. Assuming that the width size of a single pixel of the camera sensor is c, and the focal length after the camera is debugged is f. After the same scene is debugged, W, a, and f are all fixed values. Therefore, only by obtaining the pixel width Wp of the lane line can the distance between the target and the camera be determined.

[0084] Through the above formula \(L = f\times W / (W_p\times a)\), the first distance between the first reference target and the image acquisition device, and the second distance between the first target and the image acquisition device can be obtained.

[0085] Exemplarily, if the camera captures multiple targets at a certain moment, the target closest to the lower edge of the camera, such as target A, is taken as the first reference target, and the remaining targets A1, A2, A3... An are taken as the first targets. According to the positions of the targets, the pixel widths of the lane lines at each target are obtained, that is, the pixel widths of the lane lines at different distances are different. Then, according to the above formula \(L = f\times W / (W_p\times a)\), the actual distances \(L_A\), \(L_{A1}\), \(L_{A2}\)... \(L_{An}\) of each target relative to the camera can be calculated, and then the ratios of \(L_{A1}\), \(L_{A2}\)... \(L_{An}\) to \(L_A\) are calculated. Since \(W\), \(a\), and \(f\) are fixed values, the obtained series of ratios are actual values. Thus, the relative position relationship between the first target and the first reference target can be analyzed based on the image captured by the camera.

[0086] It should be noted that in order to distinguish the targets in the same horizontal direction, the lanes where the targets are located can be locked for distinction. It can be understood that when there are at least two first targets on the same horizontal line and the first relative position information of each first target with respect to the first reference target is the same, in order to distinguish these two first targets, the lanes where each first target is located can be determined for distinction, that is, the first relative position information also includes the lane numbers of the lanes where the first targets are located.

[0087] Step S103: Determine the second reference target in the second image, and respectively determine the second relative position information between at least one second target and the second reference target in the second image.

[0088] Based on the same principle as the first reference target in the first image, the second target at a specific position in the second image can also be determined as the second reference target. For example, the first second target in the lower left corner of the second image is also taken as the second reference target. The second relative position information between the second target and the second reference target is the information such as the orientation or distance of the second target relative to the second reference target in the second image.

[0089] In an embodiment of the present application, a possible implementation manner is provided. The target physical capture device includes a radar device; determining the second relative position information between the second target and the second reference target in the second image includes:

[0090] (1) Obtain the third distance between the second reference target and the radar device;

[0091] (2) Obtain the fourth distance between at least one second target and the radar device;

[0092] (3) Determine the second relative position information according to the ratio of the fourth distance to the third distance.

[0093] It can be understood that the radar device has the advantages of being less affected by environmental factors and being able to accurately detect moving targets. Therefore, it is widely used in the field of traffic monitoring.

[0094] In an embodiment of the present application, as Figure 4 shown, Figure 4 is the second image collected by the radar device. The second image is an image of the same area captured by a different image acquisition device at the same moment as the first image. Therefore, the second image also includes lanes and multiple second targets 401. Figure 4 The lines in

[0095] represent lanes, and the boxes represent second targets 401. Each lane is marked with a lane number. Since the radar device can directly measure the target slant range between the radar and the target, that is, the actual distance of the second target collected by the radar relative to the radar can be directly obtained. Specifically, the actual distance of the second target relative to the radar can be obtained according to the formula R = ct / 2, where R is the actual distance from the second target to the radar, c is the speed of light, and t is the time for the radio wave to travel back and forth between the second target and the radar device once.

[0096] For the actual distances of the second reference target and the second targets other than the second reference target in the second image to the radar device, that is, the third distance and the fourth distance, they can all be obtained according to the above formula.

[0097] Assume that the second targets captured by the radar from near to far are B, B1, B2, B3... Bm, where B is the second reference target. Select the distance of the second reference target B as the denominator, and then perform proportional calculations with the second targets above in turn, then the second relative position information between the second targets and the second reference target can be obtained.

[0098] It should be noted that since the second targets can be distributed on the left and right sides of the second reference target, if the relative position information between a certain second target and the second reference target is the same, the relative position information between each second target and the second reference target can be locked according to the lane information where the second target is located.

[0099] Step S104: Determine the fusion motion information of the target at the current moment in this area according to the first relative position information and the second relative position information.

[0100] Among them, the fusion motion information of the target includes information such as the position, speed, and type of the target at the current moment. If the image acquisition device includes a camera device and the target physical capture device includes a radar device, the type information of the target can be obtained from the first image, and the position and speed of the target can be obtained from the second image. Therefore, comprehensive motion information of the target can be obtained.

[0101] In an embodiment of the present application, a possible implementation manner is provided. Determining the fusion motion information of the target at the current moment in the area according to the first relative position information and the second relative position information includes:

[0102] Determine second targets respectively matching at least one first target according to the first relative position information and the second relative position information.

[0103] Fuse the first motion information of the first target and the second motion information of the matching second target to obtain the fusion motion information of the target at the current moment in the area.

[0104] It can be understood that when obtaining the comprehensive motion information of the target, it is necessary to match the first target in the first image with the second target in the second image, and then fuse the first motion information of the first target and the second motion information of the second target to obtain the fused motion information.

[0105] In the process of matching the first target with the second target, automatic matching can be performed based on the first relative position information of the first target and the first reference target and the second relative position information of the second target and the second reference target.

[0106] Specifically, a possible implementation manner is provided in an embodiment of the present application:

[0107] Determine the information error between the first relative position information and the second relative position information.

[0108] If the error is less than the preset error value, determine second targets respectively matching at least one first target.

[0109] Taking the image acquisition device including a camera device and the target physical capture device including a radar device as an example, the first target relative position information and the second relative position information can be compared. Assuming that the camera has n + 1 first targets, n ratios, that is, n first relative position information, can be obtained. If the information error between each first relative position information and the second relative position information is less than the preset error, that is, the first relative position information corresponds to the second relative position information, such as the lane numbers are the same and the difference in the distance ratios is less than 3%, then the target coordinates are successfully matched, that is, the first target in the first image and the second target in the second image are the same target, and the target matching is successful.

[0110] It should be noted that the target capture rate of the radar is relatively higher than that of the camera, especially in the case of long-distance capture. Therefore, in practical applications, it is default that the targets captured by the camera are all captured by the radar. Therefore, when the information error between the relative position information of the first target and the second relative position information does not meet the preset error, the second relative position information can be recalculated. For example, the second target B1 can be used as the second reference target, and then the second relative position information between each other second target and the newly established second reference target can be calculated in turn, so as to re-match the targets according to the first relative position information and the second relative position information.

[0111] The beneficial effects brought by the technical solution provided by this application are as follows:

[0112] By acquiring the first image collected by the first acquisition device and the second image collected by the second acquisition device for the same area at the same moment, this application can provide reference materials for determining the motion information of the targets in the current area at the current moment; by determining the relative position information between each target and the reference target, the position information of each target on each image can be determined; according to the first relative position information and the second relative position information, the first target in the first image and the second target in the second image can be automatically matched, improving the matching efficiency. The motion information collected in the first image and the second image can be respectively extracted for the matched targets, and finally the fused motion information of the target in this area at the current moment can be obtained, making the determined fused motion information more comprehensive.

[0113] A possible implementation manner is provided in the embodiments of this application, as Figure 5 shown. The method for determining the target motion information further includes:

[0114] Step S501: Determine the comprehensive information error between the first relative position information of multiple first images at different moments in this area and the second relative position information of multiple second images at different moments.

[0115] It can be understood that the relative position information corresponding to the same target according to the image collected by the image acquisition device and the second image captured by the target physical capture device may be slightly different. In order not to miss the matching of the same target, it is necessary to reduce the error between different relative position information. Therefore, the first relative position information of multiple first images at different moments in this area and the second relative position information of multiple second images at different moments in this area can be first determined, and then the comprehensive information error can be calculated according to the multiple first relative position information and the multiple second relative position information.

[0116] Specifically, in an embodiment of this application, the least squares method can be used to fit the first relative position information and the second relative position information at multiple different moments to obtain the comprehensive information error.

[0117] It can be understood that when calculating the comprehensive information error based on multiple first relative position information and multiple second relative position information, using the least squares method to fit the first relative position information and the second relative position information at multiple different times can reduce the error between the first relative position information and the second relative position information, making the matching of the target more accurate and covering a wider range.

[0118] Step S502: If the comprehensive error is less than the preset error value, determine second targets respectively matching at least one first target according to the first relative position information at each moment in this area and the second relative position information at each moment in this area.

[0119] Step S503: Fuse the first motion information of the first target at each moment in this area with the second motion information of the matching second target to obtain the fused motion information of the target at different times in this area.

[0120] It can be understood that if the comprehensive error is less than the preset error value, for the first image and the second image at each moment in this area, the first relative position information and the second relative position information correspond to each other. For example, when the lane numbers are the same and the difference in the distance ratio is less than 3%, the first target in the first image and the second target in the second image at each moment in this area can be matched as the same target.

[0121] When the first target in the first image and the second target in the second image at each moment in this area are successfully matched, fuse the first motion information of the first target and the second motion information of the second target at each moment in this area to obtain the fused target motion information.

[0122] Specifically, still taking the image acquisition device including a camera device and the target physical capture device including a radar device as an example, the first motion information of the first target includes category information, and the second motion information of the second target includes information such as the position, direction, and speed of the target. Since the first target and the second target are the same target, the fused motion information of the target, that is, information such as the position, direction, speed, and category of the target, can be obtained.

[0123] The embodiment of the present application provides a device for determining target motion information, as Figure 6 shown. The device 60 for determining target motion information may include: an acquisition module 601, a first determination module 602, a second determination module 603, and a third determination module 604, where

[0124] The acquisition module 601 is configured to acquire a first image acquired by an image acquisition device and a second image captured by a target physical capture device for the same area at the same moment.

[0125] The first determination module 602 is configured to determine a first reference target in the first image, and respectively determine first relative position information between at least one first target in the first image and the first reference target.

[0126] The second determination module 603 is configured to determine a second reference target in the second image, and respectively determine second relative position information between at least one second target in the second image and the second reference target.

[0127] The third determination module 604 is configured to determine the fused motion information of the target at the current moment in the area according to the first relative position information and the second relative position information.

[0128] The target motion information determination device in this embodiment can execute the target motion information determination method shown in the foregoing embodiments of this application. The implementation principle is similar and will not be described herein again.

[0129] The beneficial effects brought by the technical solution provided by this application are as follows:

[0130] By acquiring a first image collected by a first acquisition device and a second image collected by a second acquisition device for the same area at the same moment, this application can provide reference materials for determining the motion information of the target in the current area at the current moment; by determining the relative position information between each target and the reference target, the position information of each target in each image can be determined; according to the first relative position information and the second relative position information, the first target in the first image and the second target in the second image can be automatically matched, improving the matching efficiency. The matched targets can respectively extract the motion information collected in the first image and the second image, and finally obtain the fused motion information of the target in the current area at the current moment, making the determined fused motion information more comprehensive.

[0131] In an embodiment of this application, an electronic device is provided. The electronic device includes: a memory and a processor; at least one program stored in the memory and used to be executed by the processor. Compared with the prior art, the beneficial effects brought by the technical solution provided by this application are as follows: By acquiring a first image collected by a first acquisition device and a second image collected by a second acquisition device for the same area at the same moment, this application can provide reference materials for determining the motion information of the target in the current area at the current moment; by determining the relative position information between each target and the reference target, the position information of each target in each image can be determined; according to the first relative position information and the second relative position information, the first target in the first image and the second target in the second image can be automatically matched, improving the matching efficiency. The matched targets can respectively extract the motion information collected in the first image and the second image, and finally obtain the fused motion information of the target in the current area at the current moment, making the determined fused motion information more comprehensive.

[0132] In an alternative embodiment, an electronic device is provided, such as Figure 7 shown Figure 7 The electronic device 4000 shown in the figure includes: a processor 4001 and a memory 4003. Among them, the processor 4001 and the memory 4003 are connected, such as being connected through a bus 4002. Optionally, the electronic device 4000 may further include a transceiver 4004, and the transceiver 4004 may be used for data interaction between this electronic device and other electronic devices, such as data sending and / or data receiving, etc. It should be noted that in practical applications, the transceiver 4004 is not limited to one, and the structure of the electronic device 4000 does not constitute a limitation to the embodiments of the present application.

[0133] The processor 4001 may be a CPU (Central Processing Unit, central processor), a general-purpose processor, a DSP (Digital Signal Processor, data signal processor), an ASIC (Application Specific Integrated Circuit, application-specific integrated circuit), an FPGA (Field Programmable Gate Array, field programmable gate array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It can implement or execute various exemplary logic blocks, modules and circuits described in combination with the disclosure of the present application. The processor 4001 may also be a combination that realizes computing functions, such as a combination including one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0134] The bus 4002 may include a path for transmitting information between the above components. The bus 4002 may be a PCI (Peripheral Component Interconnect, peripheral component interconnect standard) bus or an EISA (Extended Industry Standard Architecture, extended industry standard architecture) bus, etc. The bus 4002 may be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, Figure 7 only a thick line is used to represent it in the figure, but it does not mean that there is only one bus or one type of bus.

[0135] The memory 4003 can be a ROM (Read Only Memory), or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory), or other types of dynamic storage devices that can store information and instructions. It can also be an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory), or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0136] The memory 4003 is used to store the application program code (computer program) for implementing the solution of this application, and is controlled and executed by the processor 4001. The processor 4001 is used to execute the application program code stored in the memory 4003 to implement the content shown in the foregoing method embodiments.

[0137] The embodiments of this application provide a computer-readable storage medium, on which a computer program is stored. When it runs on a computer, it enables the computer to execute the corresponding content in the foregoing method embodiments.

[0138] It should be understood that although the steps in the flowchart of the accompanying drawings are shown sequentially according to the indication of the arrows, these steps are not necessarily executed sequentially according to the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and they can be executed in other orders. Moreover, at least some of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed alternately or alternately with at least a part of other steps or sub-steps or stages of other steps.

[0139] The above are only some embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A method for determining target motion information, characterized in that, it includes: Obtain, at the same moment for the same area, a first image collected by an image acquisition device and a second image captured by a target physical capture device, where the target physical capture device includes a radar device; Determine a first reference target in the first image, and respectively determine first relative position information between at least one first target in the first image and the first reference target; Determine a second reference target in the second image, and respectively determine second relative position information between at least one second target in the second image and the second reference target; Determine the fused motion information of the target at the current moment in this area according to the first relative position information and the second relative position information; The determining the fused motion information of the target at the current moment in this area according to the first relative position information and the second relative position information includes: Determine second targets respectively matching at least one first target according to the first relative position information and the second relative position information; Fuse the first motion information of the first target and the second motion information of the matching second target to obtain the fused motion information of the target at the current moment in this area.

2. The method according to claim 1, characterized in that, the determining the first relative position information between at least one first target in the first image and the first reference target includes: Obtain a first distance between the first reference target and the image acquisition device; Obtain a second distance between the at least one first target and the image acquisition device; Determine the first relative position information according to the ratio of the second distance to the first distance.

3. The method according to claim 2, characterized in that, the first image includes an image containing a lane; the obtaining the first distance between the first reference target and the image acquisition device includes: Obtain the focal length of the image acquisition device, the actual width of the lane in the first image, and the lane pixel width for each target in the first image; Determine the first distance between the first reference target and the image acquisition device based on the focal length of the image acquisition device, the actual width of the lane in the first image, and the lane pixel width of the first reference target in the first image; the obtaining the second distance between the at least one first target and the image acquisition device includes: Determine the second distance between the at least one first target and the image acquisition device based on the focal length of the image acquisition device, the actual width of the lane in the first image, and the lane pixel width of at least one first target in the first image.

4. The method according to claim 2, characterized in that, the determining the second relative position information between the second target in the second image and the second reference target includes: Obtain a third distance between the second reference target and the radar device; Obtain a fourth distance between the at least one second target and the radar device; Determine the second relative position information according to the ratio of the fourth distance to the second distance.

5. The method according to claim 1, wherein, the determining the fused motion information of the target at the current moment in the area according to the first relative position information and the second relative position information includes: determining the information error between the first relative position information and the second relative position information; if the error is less than a preset error value, determining the fused motion information of the target at the current moment in the area according to the first relative position information and the second relative position information.

6. The method according to claim 1, wherein, the method further includes: determining the comprehensive information error between the first relative position information of the first images at different moments in multiple areas and the second relative position information of the second images at different moments; if the comprehensive error is less than a preset error value, determining second targets respectively matching at least one first target according to the first relative position information at each moment in the area and the second relative position information at each moment in the area; fusing the first motion information of the first target at each moment in the area with the second motion information of the second target that matches, to obtain the fused motion information of the target at different moments in the area.

7. An apparatus for determining target motion information, wherein, it includes: an acquisition module, configured to acquire a first image acquired by an image acquisition device and a second image captured by a target physical capture device for the same area at the same moment, and the target physical capture device includes a radar device; a first determination module, configured to determine a first reference target in the first image, and respectively determine the first relative position information between at least one first target in the first image and the first reference target; a second determination module, configured to determine a second reference target in the second image, and respectively determine the second relative position information between at least one second target in the second image and the second reference target; a third determination module, configured to determine the fused motion information of the target at the current moment in the area according to the first relative position information and the second relative position information; the determining the fused motion information of the target at the current moment in the area according to the first relative position information and the second relative position information includes: determining second targets respectively matching at least one first target according to the first relative position information and the second relative position information; fusing the first motion information of the first target with the second motion information of the second target that matches, to obtain the fused motion information of the target at the current moment in the area.

8. An electronic device, wherein, the electronic device includes: one or more processors; a memory; one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to: execute the method for determining target motion information according to any one of claims 1 to 6.

9. A computer-readable storage medium, on which a computer program is stored, wherein, When the computer program is executed by a processor, it implements the method for determining the target motion information according to any one of claims 1-6.

Images