A depth imaging and information acquisition method based on binocular vision

Abstract

The present invention provides a depth imaging and information acquisition method based on binocular vision. The method performs spatial calibration on images captured by binocular cameras through distortion correction and epipolar line correction, and constructs a two-dimensional parallax label set based on calibrated image pairs. , select different label combinations as source-sink points each time to construct a network graph and design edge weights, use the maximum flow algorithm to iteratively obtain the minimum cut set of the network, and complete the two-dimensional disparity label assignment of pixels according to the designed label update strategy, When the iteration is terminated, a relatively dense disparity map can be obtained, and the depth information of the scene can be calculated by combining the principle of triangulation ranging, and the calculation result can be further optimized by collecting the depth information of key points. Both location and physical scale information of an object can be obtained.

Description

technical field [0001] The invention belongs to the field of depth imaging, and in particular relates to a binocular vision-based depth imaging method and an information acquisition method. 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 to be applied in intelligent video surveillance, driverless cars, intelligent transportation, security and robot automatic control and other fields. In actual scenarios, it can be used for pedestrian detection in important places such as subways, stations, squares, shopping malls, parks, and 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 stereo monitoring camera, opt...

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