Monocular three-dimensional object detection method and device, equipment and product

Abstract

The invention provides a monocular three-dimensional object detection method and device, equipment and product, and relates to the technical field of computer vision, and the method comprises the following steps: obtaining a to-be-detected image; inputting the to-be-detected image into a monocular three-dimensional object detection model to obtain a two-dimensional detection result, an object depth, an observation angle and a size of the to-be-detected object output by the monocular three-dimensional object detection model; generating a three-dimensional center point of the to-be-detected object in the three-dimensional space according to the two-dimensional center point and the depth of the object; generating an orientation angle of the to-be-detected object according to the three-dimensional center point and the observation angle; according to the three-dimensional center point, the orientation angle and the size, generating a three-dimensional detection result. The prediction performance of the truncated object in monocular three-dimensional detection is remarkably optimized, the method is not limited to the type of the detection object, and monocular three-dimensional detection can be conducted on the normal object and the truncated object.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a monocular three-dimensional object detection method, device, equipment and product. Background technique [0002] With the emergence of large-scale datasets and the development of deep learning, image-based 2D object detection algorithms have made great progress and are widely used in autonomous driving, video surveillance, industrial inspection, image retrieval, and other fields. [0003] The classic computer vision problem is to identify objects and scenes in images through mathematical models or statistical learning, and then realize motion recognition, object trajectory tracking, behavior recognition, etc. on video time series. However, since the image is the projection of the three-dimensional space on the optical system, two-dimensional detection can only realize the recognition of the image level, and cannot perceive the real three-dimensional space. In all appl...

AI Technical Summary

Problems solved by technology

[0007] The present invention provides a monocular three-dimensional object detection method, device, equipment and products, which are used to solve the defect that there is a significant difference in visibility when the monocular three-dimensional detection detects truncated objects in the prior art, and achieves a significant optimization of the monocular three-dimensional object detection method. The prediction performance of truncated objects in three-dimensional detection, this method is not limited to the type of detection object, without considering the differences between objects

Images