【摘要】 行人检测是计算机视觉中的关键问题,与之相关的一些应用对人们的生活质量有着潜在的积极影响。近年来,基于单眼图像行人检测方法的数量正稳步增长。使用特征金字塔方法对行人进行快速的检测,利用路面估计来设定感兴趣区域,对检测出的行人进行筛选,实验表明该方法相对FPDW方法在时间上并没有明显增加,而检测正确率则有明显提高。更多还原

【Abstract】 Pedestrian detection is a key problem in computer vision, with several applications that have the potential to positively impact quality of life. In recent years, the number of approaches to detecting pedestrians in monocular images has grown steadily. Detects pedestrians by using feature pyramids, then uses regions of interest(ROIs)extracted based on the road surface to confirm the candidate windows. Experiments show that the detection time isn’t increased remarkably comparing FPDW, but significantly improves the detection accuracy.更多还原