Depth imaging and information acquisition method based on binocular vision

Abstract

The invention provides a depth imaging and information acquisition method based on binocular vision. The method is characterized by carryin gout the spatial calibration on an image shot by a binocular camera through the distortion correction and the polar line correction, constructing a two-dimensional parallax label set based on the calibrated image pairs; selecting different label combinations as the source confluence points each time to construct a network graph and design the edge weights; iteratively solving a minimum cut set of the network by adopting a maximum flow algorithm; completing the two-dimensional parallax label distribution of the pixel points according to a designed label updating strategy. When the iteration is finished, a dense disparity map can be obtained, the depth information of a scene is obtained through calculation by combining a triangular distance measurement principle, a calculation result is further optimized by collecting the depth information of the key points, and by combining the GPS data, the height and angle information of camera erection, the position and the physical scale information of any target in the scene can be obtained.

Description

Technical field [0001] The invention belongs to the field of depth imaging, and in particular relates to a depth imaging method and information acquisition method based on binocular vision. Background technique [0002] Depth imaging is a technology that uses imaging equipment to extract scene depth information and express the depth information as a depth image. This technology can be combined with target detection, target recognition, image segmentation and other technologies, and applied to fields such as intelligent video surveillance, driverless cars, intelligent transportation, security and automatic robot control. In actual scenes, it can be used for pedestrian detection in important places such as subways, stations, squares, shopping malls, parks and densely crowded areas. The present invention innovatively proposes a binocular depth imaging method in the presence of two-dimensional parallax, combined with an intelligent three-dimensional monitoring camera, optimizes the ...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a depth imaging and information acquisition method based on binocular vision, which can overcome the problem that the existing binocular depth imaging algorithm is difficult to adapt to the existence of two-dimensional parallax, and improve the parallax calculation ability of the algorithm itself. In the presence of parallax, the network map, weight and label update strategy can calculate a more accurate parallax value, and combine the camera erection angle, height information and GPS data to realize the physical scale calculation of the target in the scene and the acquisition of world position information

Images