Detecting pedestrians using patterns of motion and appearance
Detecting pedestrians using patterns of motion and appearance
复制标题
DOI：
10.1007/s11263-005-6644-8
复制
发表时间：
2005-07-01
影响因子：
19.5
通讯作者：
Snow, D
中科院分区：
文献类型：
--
作者：
Viola, P;Jones, MJ;Snow, D
本文介绍了一种行人检测系统，结合图像强度信息和运动信息。我们使用的检测风格的算法，扫描检测器在两个连续帧的视频序列。该检测器经过训练（使用AdaBoost），以利用运动和外观信息来检测行走的人。过去的方法已经建立了基于运动信息的检测器或基于外观信息的检测器，但我们是第一个将两种信息源联合收割机结合在一个检测器中的方法。所描述的实现以大约4帧/秒的速度运行，以非常小的尺度（小至20 x 15像素）检测行人，并且具有非常低的误报率。本文的新贡献包括：（一）发展的图像运动的表示，这是非常有效的，和（二）实施的最先进的行人检测系统，在困难的条件下（如雨和雪）低分辨率图像上操作。
This paper describes a pedestrian detection system that integrates image intensity information with motion information. We use a detection style algorithm that scans a detector over two consecutive frames of a video sequence. The detector is trained (using AdaBoost) to take advantage of both motion and appearance information to detect a walking person. Past approaches have built detectors based on motion information or detectors based on appearance information, but ours is the first to combine both sources of information in a single detector. The implementation described runs at about 4 frames/second, detects pedestrians at very small scales (as small as 20 x 15 pixels), and has a very low false positive rate.Our approach builds on the detection work of Viola and Jones. Novel contributions of this paper include: (i) development of a representation of image motion which is extremely efficient, and (ii) implementation of a state of the art pedestrian detection system which operates on low resolution images under difficult conditions (such as rain and snow).