Authors:
Zejin Lu
1
;
2
;
Jinqi Liao
1
;
Jiyang Lv
1
and
Fengjun Chen
1
;
2
Affiliations:
1
National Engineering Research Center for High Efficiency Grinding, Hunan University, Changsha, Hunan, China
;
2
State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body, Hunan University, Changsha, Hunan, China
Keyword(s):
Target Matching, Object Detection, Deep Learning, Relocation Strategy, Loss Function.
Abstract:
Target matching is a common task in the field of computer vision, which has a wide range of implements in the fields of target tracking, medical image analysis, robot navigation, etc. The tasks in these scenarios have high requirements for locating accuracy, reliability and robustness, but the existing methods cannot meet these requirements. To improve the algorithm performance in these aspects, a novel practical target matching framework is proposed in this paper. We firstly present a new bounding box regression metric called Coverage-Intersection over Union (Co-IoU) to obtain higher positioning accuracy performance compared to previous bounding regression strategies. Also, a reasonable region validation and filter strategy is proposed to reduce the false positive matches and the Region of Interest (ROI) adjustment and relocation matching strategy are innovatively present to acquire higher locating accuracy. Our experiments show that the proposed framework is more robust, accurate a
nd reliable than the previous relevant algorithms. Besides, Coverage-Intersection over Union Loss and relocation strategy proposed in this paper can significantly improve the performance of the general object detector as well.
(More)