Tracking method of airborne unmanned aerial vehicle multi-target tracking system based on deep learning

Abstract

The invention discloses a tracking method of an airborne unmanned aerial vehicle multi-target tracking system based on deep learning, and belongs to the field of unmanned aerial vehicle target tracking. Real-time image information is obtained through a pan-tilt camera; after basic preprocessing is carried out, multiple targets in the image are detected and tracked through a deep learning algorithm, meanwhile, a data association algorithm is used for carrying out association of adjacent frame motions on the targets, one-to-one matching is completed, and current state estimation and historical motion recording of the multiple targets are achieved; according to the position and speed prediction results of the targets, the holder is adjusted to keep the targets in the center of the image, monocular distance measurement is realized, and tracking flight of the targets is realized in combination with the position and speed of the targets. The method does not depend on a GPS, realizes visual angle maintenance in the tracking process, can rapidly, accurately and stably track multiple targets and perform selective tracking, and can better solve the problems that tracking disappears and thenappears and the like; meanwhile, interaction with a user can be performed through wireless communication, and a tracking state is fed back.

Description

technical field [0001] The invention belongs to the field of UAV target tracking, and in particular relates to a tracking method of an airborne UAV multi-target tracking system based on deep learning. Background technique [0002] UAV usually refers to a pilotless aircraft that is combined with an onboard computer system and a ground system and can complete flight tasks by itself. Compared with manned aircraft, it has the advantages of small size, light weight, low production and operation and maintenance costs, good maneuverability, and no crew safety issues. It can be widely used in military tasks such as low-altitude reconnaissance, anti-terrorist strikes, and intelligence collection. In terms of civil use, it can be used in many fields such as meteorological detection, disaster monitoring, geological exploration, map surveying and mapping, agricultural plant protection, public security fire protection, etc. In recent years, as technological progress has brought down the...

AI Technical Summary

Problems solved by technology

The invention utilizes visual information and information of airborne sensors to realize multi-target tracking and motion estimation, and at the same time controls the pan-tilt so that the ground target is always kept at the image center of the camera during the tracking process of the UAV, so as to solve the problem of the prior art Unable to track multiple targets, relying on GPS, unstable viewing angle, etc.

Images