Self-adaptive coal mining machine follow-up tracking multi-camera video splicing method

Abstract

The invention discloses a self-adaptive coal mining machine follow-up tracking multi-camera video splicing method, belongs to the technical field of intelligent monitoring, and combines a camera groupself-adaptive follow-up tracking method with a coal mining machine video splicing algorithm to improve the splicing effect of coal mining machine monitoring videos under the condition of large parallax of a coal mining working face. The influence of monitoring dead angles of the cameras on the state monitoring of the coal mining machine is reduced; firstly, a colorful fluorescent band is used formarking the position of a machine body, and real space coordinates are obtained through a camera calibration principle; the cameras deployed on a coal mining working surface are activated in groups based on a camera group self-adaptive follow-up tracking method, and the currently activated camera group completes a video splicing task of a coal mining machine picture. The coal mining machine videosplicing algorithm comprises the following steps: splicing corresponding frame images of two monitoring videos by using an image splicing algorithm; screening SIFT feature points based on an RANSAC algorithm for registration of the two images; and finally, splicing the two images by searching for the optimal suture line, and thus large-range monitoring of operation of the coal mining machine is achieved.

Description

technical field [0001] The invention belongs to the technical field of intelligent monitoring, and relates to a multi-camera video splicing method for self-adaptive shearer tracking. Background technique [0002] As an important equipment for the mechanization and modernization of coal mine production, if the shearer fails, it will lead to the interruption of the entire coal mining face, and its operation status directly affects the safety production level and economic production efficiency of the coal mine. Because the shearer is a large and complex system integrating machinery, electricity and hydraulics, its body is very long, and it has problems such as high operational complexity and failure to detect work failures in time. The traditional video surveillance system cannot cover the entire body. It will produce monitoring blind spots and increase the failure rate of missed detection. [0003] Therefore, the fault monitoring system for large-scale shearers needs the coop...

AI Technical Summary

Problems solved by technology

[0005] The above methods have proposed certain technical improvements for underground video surveillance splicing, but there is no adaptive dynamic scheduling for the camera group used for underground monitoring, mainly for static targets or environmental monitoring scenarios, and for dynamic large targets (such as coal shearers) ) follow-up monitoring has not been fully studied

At the same time, the existing stitching algorithm cannot handle the fuzzy and distorted video stitching results under the condition of large parallax in the mine well, which limits the vertical expansion of the monitoring range in the wide-view field and large parallax scene

Images