2012년도 대한전자공학회 하계학술대회 논문집, v. 35, NO. 1, Page. 1267-1268
Abstract
Pedestrian detection is a crucial problem in computer vision. In this paper, we propose a method to enhance accuracy of pedestrian detection by using difference between pixels and k-means clustering algorithm. By using the proposed method, we can eliminate false positive in pedestrian detection candidates.