标题: | 行人侦测系统 Pedestrian Detection System |
作者: | 韩孝羽 Hsiao-Yu Han 林进灯 Chin-Teng Lin 电控工程研究所 |
关键字: | 行人侦测;小波转换;兴趣点;改善过的时间差异法;多层级倒传递网路;pedestrian detection;wavelet transform;interest point;modified temporal differencing method;multilayer BP neural network |
公开日期: | 2000 |
摘要: | 本论文提出一个新的行人侦测演算法,并且以此演算法发展出一套即时的行人侦测系统。这个行人侦测演算法可区分为两部分:移动物件侦测与行人辨识。在移动物件侦测部分,我们使用改善过的时间差异法(Modified Temporal Differencing Method)在场景中切割出移动的物件,这种改善过的时间差异法结合了一般的时间差异法与侦测网路(Detection Nets)的观念。在行人辨识部分,我们由输入影像取得多种类型的小波样板(Wavelet Template),再由小波样板取出兴趣点样板(Interest Point Template),我们利用小波样板的频率分析及多级别(Multi-scale)特性,并且结合兴趣点的区域性特征,由兴趣点样板中萃取出统计所得的特征点,最后,这些特征点输入一个训练过的多层级倒传递类神经网路(Multilayer Back-propagation Neural Network),类神经网路的输出就表示最后的结果—人或非人。此行人侦测演算法有以下几点优点:(1)经由大量影像训练而成,改善了一般以外形为基础的方法中需要手绘人形模型的缺点。(2)不用求得运动型别(Motion Pattern),在行人辨识处理中只需要一张影像就可得到结果。(3)不会受到行人的衣服、发型、性别、走路姿势及行走方向所影响。(4)演算法速度快,可应用于即时侦测系统中。(5)经由实验得知,此行人侦测系统的辨识率达到95%。我们将此演算法实现于即时的行人侦测系统中,行人侦测率达到89.58%。 In this thesis, we propose a new pedestrian detection algorithm, and use it to develop a real-time pedestrian detection system. The pedestrian detection algorithm can be functionally partitioned into two parts: moving object segmentation and pedestrian recognition. In moving object segmentation, we segment the moving objects in the scene by modified temporal differencing method. This method combines general temporal differencing method with detection nets. In pedestrian recognition, we obtain multi-type wavelet templates from input images. Interest points are extracted from wavelet templates. We exploit frequency analysis and multi-scale features in wavelet templates and local features in interest point templates. Then, feature points are extracted by statistical method from interest point templates. Finally, these feature points are fed into a trained multilayer back-propagation neural network. The output of the neural network implies the result – pedestrian or non-pedestrian. The pedestrian detection algorithm has the following advantages: (1) Learning from masses of example images: this avoids the drawback of general shape-based methods that need handcrafted models. (2) Not relying on motion patterns: the pedestrian recognition procedure only needs one image. (3) The system can detect pedestrians in variety of clothes, hairstyles, gender, walking poses and walking directions. (4) The processing speed in pedestrian detection is fast. This algorithm can be realized in real time. (5) From experiments, accuracy rate of recognition achieves 95%. We implement this algorithm in a real-time pedestrian detection system. The system can detect pedestrians in the scene in real time. The pedestrian detection rate is 89.58%. |
URI: | http://140.113.39.130/cdrfb3/record/nctu/#NT890591037 http://hdl.handle.net/11536/67805 |
显示于类别: | Thesis |