基于BING和HOG-LSS特征的行人检测算法研究

Research on Pedestrian Detection Algorithm Based on BING and HOG-LSS Feature

近年来,基于计算机视觉技术的行人检测方法一直是智能交通领域研究的热点问题之一。基于HOG和局部自相似(LSS)特征融合的行人检测算法在检测效果上优于传统HOG特征的行人检测算法,但是同时也存在如下挑战:1) 算法检测的速度不够快;2) 在遮挡面积过大的情况下,无法有效地进行处理。针对这些挑战问题,本文提出了一种使用BING特征、HOG-LSS特征和数据轨迹融合的行人检测优化框架,并通过对实验结果进行验证可知,检测效果优于HOG-LSS特征的行人检测方法。

In recent years, pedestrian detection, based on computer vision, has been one of the hottest topics in the field of intelligent transportation. The pedestrian detection algorithm, based on HOG and local self-similarity (LSS) feature fusion, is better than the traditional HOG detection algorithm, and also it has the following challenges: 1) low efficiency;2) failing to effectively handle the occlusion problem. Aiming at these challenges, this paper proposes a pedestrian detection optimization framework based on BING feature, HOG-LSS feature and data trajectory fusion. It is proved that the detection result is superior to the HOG-LSS pedestrian detection method.