Method, device, equipment and storage medium for determining target attitude

Abstract

The present application discloses a method, device, equipment and storage medium for determining a target attitude. The method is applied in a scene with a flat road surface, and includes: acquiring a target-to-be-processed image collected by a camera; inputting the target-to-be-processed image into a trained attitude estimation model, and outputting orientation information of the target; Orientation information, determine the yaw angle of the target; determine the pitch angle and roll angle of the target according to the relationship between the road surface and the camera coordinate system, and determine the yaw angle, pitch angle and roll angle as the target attitude information. The implementation process of the technical solution is simple, and the accuracy of the attitude information obtained is high.

Description

Technical field

[0001] The present disclosure relates generally to the field of computer vision technology, in particular to a target attitude determination method, apparatus, apparatus and storage medium. Background

[0002] Image recognition technology based on deep learning is widely used in the field of video surveillance, and the use of this technology breaks through the technical bottleneck of traditional algorithms in the past and achieves a high accuracy rate, but the implementation of this technology needs to rely on enough training data.

[0003] When the technique is applied to attitude estimation, due to the relationship between the camera shooting angle and the relative position of the target, the attitude of the target in the image does not truly reflect the real attitude of the target, so the real attitude cannot be directly obtained from the image, and the existing scheme usually has the following two types:

[0004] 1. Obtained through manual actual measurement ...

Examples

Embodiment Construction

[0048] The present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It will be appreciated that the specific embodiments described herein are used only to explain the invention in question and not to qualify the invention. It should also be noted that, in order to facilitate the description, only a portion of the invention is shown in the drawings.

[0049] It should be noted that, in the absence of conflict, the embodiments in the present application and the features in the embodiments may be combined with each other.

[0050] As mentioned in the background technology, the current method is generally based on the actual measurement or model method to achieve the target attitude estimation, these two methods have the problem of cumbersome and complex process, low accuracy and other issues.

[0051] Based on the above defects, the present application embodiment provides a target attitude determination method, by ob...

Technical field

[0001] The present disclosure relates generally to the field of computer vision technology, in particular to a target attitude determination method, apparatus, apparatus and storage medium. Background

[0002] Image recognition technology based on deep learning is widely used in the field of video surveillance, and the use of this technology breaks through the technical bottleneck of traditional algorithms in the past and achieves a high accuracy rate, but the implementation of this technology needs to rely on enough training data.

[0003] When the technique is applied to attitude estimation, due to the relationship between the camera shooting angle and the relative position of the target, the attitude of the target in the image does not truly reflect the real attitude of the target, so the real attitude cannot be directly obtained from the image, and the existing scheme usually has the following two types:

[0004] 1. Obtained through manual actual measurement ...

Examples

Embodiment Construction

[0048] The present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It will be appreciated that the specific embodiments described herein are used only to explain the invention in question and not to qualify the invention. It should also be noted that, in order to facilitate the description, only a portion of the invention is shown in the drawings.

[0049] It should be noted that, in the absence of conflict, the embodiments in the present application and the features in the embodiments may be combined with each other.

[0050] As mentioned in the background technology, the current method is generally based on the actual measurement or model method to achieve the target attitude estimation, these two methods have the problem of cumbersome and complex process, low accuracy and other issues.

[0051] Based on the above defects, the present application embodiment provides a target attitude determination method, by ob...

Images