CN-115880665-B - Three-dimensional reconstruction method, device and equipment for traffic sign position and storage medium

CN115880665BCN 115880665 BCN115880665 BCN 115880665BCN-115880665-B

Abstract

The embodiment of the specification discloses a three-dimensional reconstruction method, device and equipment for traffic sign positions and a storage medium. First, a position frame of a target traffic sign is determined in consecutive N frames of traffic images, and a first number of pixels between position frames in two adjacent frames of traffic images. Because the smaller the first number is, the greater the possibility that the two position frames corresponding to the first number correspond to the same target traffic object is, the target associated frame combination is determined in the position frames in the N-frame traffic image based on the first number. Further, three-dimensional reconstruction is performed based on the position information of the target position frame in the target associated frame combination and shooting pose information corresponding to the target traffic image to which the target position frame belongs, so that the three-dimensional position information of the target traffic sign is obtained. And carrying out three-dimensional reconstruction on a plurality of two-dimensional positions of the target traffic sign by shooting pose information, and accurately determining the three-dimensional position of the target traffic sign.

Inventors

ZHANG JIANCHI
XU LINKUN
LIU DEHAO
SUN LI

Assignees

广东鲲鹏空间信息技术有限公司

Dates

Publication Date: 20260512
Application Date: 20221117

Claims (13)

1. A method for three-dimensional reconstruction of traffic sign locations, the method comprising: Determining the position frames of a target traffic sign in N continuous traffic images, wherein a first number of pixels are arranged between the position frames in two adjacent traffic images, N is a positive integer greater than or equal to 2; determining target associated frame combinations in the position frames in the N frames of traffic images based on the first quantity, wherein the target associated frame combinations comprise a plurality of target position frames corresponding to the same target traffic sign; performing three-dimensional reconstruction according to the position information of the target position frame and shooting pose information corresponding to a target traffic image to which the target position frame belongs to obtain three-dimensional position information of the target traffic sign, wherein the shooting pose information is pose information of a traffic object at the shooting moment of the target traffic image; The determining, based on the first number, a target associated frame combination in the position frames in the N-frame traffic image includes: Determining two position frames corresponding to the target number smaller than the threshold value of the pixel number in the first number as an initial association frame combination, wherein the initial association frame combination has confidence that the two position frames included in the initial association frame combination correspond to the same target traffic sign; And determining the target associated frame combination based on the confidence of the initial associated frame combination in the initial associated frame combination.
2. The method of claim 1, wherein the confidence level is determined by a number of pixels between two position frames included in the initial association frame combination.
3. The method of claim 1, wherein the two position frames included in the initial association frame combination have a second number of pixels and a third number of pixels, respectively, and wherein the threshold number of pixels is determined by a number of pixels in a specified position frame, wherein the specified position frame is specified in the two position frames included in the initial association frame combination according to a comparison result of the second number and the third number.
4. The method of claim 1, wherein the two position frames included in the initial association frame combination are respectively marked as a first position frame and a second position frame having an initial connection relationship, the first position frame belonging to a first traffic image and the second position frame belonging to a second traffic image, wherein the determining the target association frame combination based on the confidence of the initial association frame combination in the initial association frame combination comprises: If any position frame in the first traffic image and a plurality of position frames in the second traffic image have an initial connection relationship, determining the position frame with a target connection relationship with any position frame in the plurality of position frames in the second traffic image according to the confidence degree of the initial association frame combination; And determining any position frame and the position frame with the target connection relation with any position frame as the target associated frame combination.
5. The method of claim 4, wherein the determining, from among the plurality of location frames in the second traffic image, a location frame having a target connection relationship with the any location frame according to the confidence level of the initial association frame combination comprises: and taking the position frame in the second traffic image corresponding to the maximum confidence coefficient as the position frame with the target connection relation with any position frame.
6. The method of claim 1, wherein the target traffic image is obtained by capturing the target traffic sign through an image capturing device installed on the traffic object, wherein the three-dimensional reconstructing is performed according to the position information of the target position frame and the capturing pose information corresponding to the target traffic image to which the target position frame belongs to obtain the three-dimensional position information of the target traffic sign, and the three-dimensional reconstructing comprises: Performing triangularization calculation based on the position information of the target position frame and the shooting pose information to obtain an estimated three-dimensional position of the target traffic sign; and optimizing the estimated three-dimensional position according to the internal parameters, the external parameters, the estimated three-dimensional position and the shooting pose information of the image acquisition device by taking the minimum reprojection error as a criterion to obtain the three-dimensional position information of the target traffic sign.
7. The method according to claim 1, wherein the method further comprises: Clustering is carried out on the basis of the three-dimensional position information of the target traffic sign obtained by three-dimensional reconstruction of a plurality of traffic objects to obtain a plurality of position clustering clusters, wherein the three-dimensional position information in the position clustering clusters corresponds to the same target traffic sign; And determining the three-dimensional position information of the target traffic sign corresponding to any position cluster according to the three-dimensional position information in any position cluster.
8. The method of claim 7, wherein the clustering based on the three-dimensional position information of the target traffic sign obtained for the three-dimensional reconstruction of the plurality of traffic objects to obtain a plurality of position clusters comprises: determining any one piece of three-dimensional position information as a data object point in the three-dimensional position information of the target traffic sign obtained by three-dimensional reconstruction of a plurality of traffic objects; And clustering the data object points serving as core points according to a preset neighborhood radius and a preset quantity threshold value of the target traffic sign in the preset neighborhood radius to obtain a plurality of position clustering clusters.
9. The method of claim 7, wherein determining the three-dimensional location information of the target traffic sign corresponding to any location cluster according to the three-dimensional location information in the any location cluster comprises: Carrying out average calculation on the three-dimensional position information in any position cluster to obtain an average three-dimensional position of the target traffic sign; And taking the average three-dimensional position of the target traffic sign as an initial position, and optimizing the average three-dimensional position by adopting a beam adjustment method to obtain the three-dimensional position information of the target traffic sign corresponding to any position cluster.
10. The method according to claim 9, wherein the method further comprises: and optimizing the external parameters of the image acquisition device by adopting a beam adjustment method to obtain the optimized external parameters.
11. A three-dimensional reconstruction device for traffic sign locations, the device comprising: the system comprises a position frame determining module, a position frame determining module and a position frame determining module, wherein the position frame determining module is used for determining the position frame of a target traffic sign in N continuous frame traffic images, wherein a first number of pixels are arranged between the position frames in two adjacent frame traffic images; the related frame combination determining module is used for determining target related frame combinations in the position frames in the N frames of traffic images based on the first quantity, wherein the target related frame combinations comprise a plurality of target position frames corresponding to the same target traffic sign; The three-dimensional position information determining module is used for carrying out three-dimensional reconstruction according to the position information of the target position frame and shooting pose information corresponding to the target traffic image to which the target position frame belongs to obtain the three-dimensional position information of the target traffic sign, wherein the shooting pose information is the pose information of a traffic object at the shooting moment of the target traffic image; The determining, based on the first number, a target associated frame combination in the position frames in the N-frame traffic image includes: Determining two position frames corresponding to the target number smaller than the threshold value of the pixel number in the first number as an initial association frame combination, wherein the initial association frame combination has confidence that the two position frames included in the initial association frame combination correspond to the same target traffic sign; And determining the target associated frame combination based on the confidence of the initial associated frame combination in the initial associated frame combination.
12. A three-dimensional reconstruction device of traffic sign locations, comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any one of claims 1 to 10.
13. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 10.

Description

Three-dimensional reconstruction method, device and equipment for traffic sign position and storage medium Technical Field The present invention relates to the field of autopilot technology, and in particular, to a method, apparatus, device, and storage medium for three-dimensional reconstruction of traffic sign positions. Background In the field of intelligent traffic, traffic signs play an important role in improving the traffic efficiency and safety of intersections and in intelligent traffic system application. But city modification often results in inconsistent position data for traffic signs in the map. Therefore, the position of the traffic sign can be three-dimensionally reconstructed based on the binocular vision method to determine the accurate position of the traffic sign. In the related art, the binocular vision-based method requires a plurality of cameras to reconstruct the traffic sign position in the common view area, and the relative positional relationship between the plurality of cameras needs to be calibrated in advance. However, the accuracy of the traffic sign position determined by three-dimensional reconstruction based on the binocular vision method is to be improved. Disclosure of Invention The embodiments of the present specification aim to solve at least one of the technical problems in the related art to some extent. To this end, the embodiments of the present specification provide a three-dimensional reconstruction method, apparatus, computer device, and storage medium for traffic sign positions. The embodiment of the specification provides a three-dimensional reconstruction method of a traffic sign position, which comprises the following steps: Determining the position frames of a target traffic sign in N continuous traffic images, wherein a first number of pixels are arranged between the position frames in two adjacent traffic images, N is a positive integer greater than or equal to 2; determining target associated frame combinations in the position frames in the N frames of traffic images based on the first quantity, wherein the target associated frame combinations comprise a plurality of target position frames corresponding to the same target traffic sign; and carrying out three-dimensional reconstruction according to the position information of the target position frame and shooting pose information corresponding to the target traffic image to which the target position frame belongs to obtain the three-dimensional position information of the target traffic sign, wherein the shooting pose information is the pose information of a traffic object at the shooting moment of the target traffic image. The embodiment of the specification provides a three-dimensional reconstruction device of traffic sign positions, wherein the device comprises; the system comprises a position frame determining module, a position frame determining module and a position frame determining module, wherein the position frame determining module is used for determining the position frame of a target traffic sign in N continuous frame traffic images, wherein a first number of pixels are arranged between the position frames in two adjacent frame traffic images; the related frame combination determining module is used for determining target related frame combinations in the position frames in the N frames of traffic images based on the first quantity, wherein the target related frame combinations comprise a plurality of target position frames corresponding to the same target traffic sign; The three-dimensional position information determining module is used for carrying out three-dimensional reconstruction according to the position information of the target position frame and shooting pose information corresponding to the target traffic image to which the target position frame belongs to obtain the three-dimensional position information of the target traffic sign, wherein the shooting pose information is the pose information of a traffic object at the shooting moment of the target traffic image. The present description provides a computer device comprising a memory and one or more processors communicatively coupled to the memory, the memory having stored therein instructions executable by the one or more processors to cause the one or more processors to implement the steps of the method of any of the above embodiments. The present description provides a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps of the method according to any of the above embodiments. The present description provides a computer program product comprising instructions which, when executed by a processor of a computer device, enable the computer device to perform the steps of the method of any one of the embodiments described above. In the above-described embodiments, first, the position frame of the target traffic sign and the first number of pixels bet