Infrared video aerial weak moving target detecting and tracking method

Abstract

The invention provides an infrared video aerial weak moving target detecting and tracking method. According to the method, a rapid and accurate skyline judgment strategy is provided, a sky scene areais obtained through perception, and under the guidance of a sky scene area perception result, an aerial potential target is obtained from airspace detection through the significance difference betweena target and a background, so that it is ensured that a real target is not missed. A target motion trend is introduced, multi-target similarity comprehensive evaluation is introduced to remove falsealarm interference, and background motion compensation is combined to further confirm a moving target, thereby solving the problem of accurate tracking of the moving target. Experimental results showthat the method is good in robustness, and accurate and steady tracking can be carried out under the complex conditions that the target is shielded, overlapped and disappeared, background changes andthe target is ignored and darkened.

Description

technical field [0001] The invention relates to a method for detecting and tracking weak and small moving targets in the air in infrared video, and belongs to the technical field of computer vision. Background technique [0002] With the rapid development of precision-guided weapons, future warfare puts forward higher requirements on the overall performance of weapon systems, especially the adaptability. Infrared guidance technology is widely used in various types of missiles, aircraft and ground systems due to its strong anti-jamming capability, high guidance accuracy, and good concealment, and has become the second-generation guidance technology for controllable weapon systems. It has also been gradually promoted and applied in civilian systems. An infrared guidance system generally consists of functional modules such as target detection, target recognition, target tracking and attack point selection. Among them, target detection and target tracking, as the front-end pro...

AI Technical Summary

Problems solved by technology

The method of tracking first and then detecting has insufficient adaptability to weak and small targets, especially slow-moving targets, under complex interference. When the platform moves, complex background and other similar objects interfere, the target is occluded, and the target maneuvers, this type of method is not suitable. Continuous, accurate, robust long-term tracking is difficult

Images