Strong Interference UAV Motion Target Tracking Based on Target Consistency Algorithm

In recent years, unmanned aerial vehicle (UAV) image target tracking technology, which obtains motion parameters of moving targets and achieves a behavioral understanding by identifying, detecting in UAV images, has been widely used urban safety fields such as accident rescue, traffic monitoring personnel detection. Due to the problems complex backgrounds, small scale high density targets, well mutual occlusion among this leads inaccurate results single object (SOT). To solve problem loss caused results, paper proposes strong interference method based on consistency algorithm for SOT an interframe fusion trajectory confidence mechanism, fusing previous frames correction current frames, learning again from update model adjusting according duration. The experimental can show that accuracy proposed is improved 6.3% 2.6% compared with benchmark method, more suitable applications case background clutter, camera viewpoint change.