적외선 영상에서 피아식별 성능 향상을 위한 사람 검출

Abstract

Human detection plays an important role in identifying friend or foe. In this paper, we propose a method for human detection in IR images. The proposed method consists of three steps: (1)applying horizontal adaptive threshold, (2)generating gradient map, (3)detecting human regions by combining horizontal adaptive threshold and gradient map. Experimental results have shown that the proposed method achieves better performance than existing methods.