标题: 基于自适应增强演算法的串联式分类器及物件估测之车辆侦测与追踪系统
A Vehicle Detection and Tracking System based on a Cascade Classifier applying AdaBoost Algorithm and Object Estimation
作者: 曹哲玮
Tsau,Che-Wei
吴炳飞
Wu, Bing-Fei
电控工程研究所
关键字: 车辆侦测;物件估测;粒子滤波器;自适应增强;Vehicle detection;object estimation;particle filter;Adaboost
公开日期: 2015
摘要: 近年科技的发展人们对于车辆的需求越来越高,科技所带来的方便但仍伴随着危险性而产生,人们在行车的过程中往往一个不注意就引发交通事故,因此本论文发展出一套车辆侦测系统,希望透过本系统的警告能够必免不必要的交通意外事故,不同于其他复杂的环境设置,对于内部软体本论文只需要将事前所训练好的资料库输入道系统端就能够进行侦测,对于外部设定只要将网路摄影机架设到车向就能够结合电脑就能够即时车辆侦测,同时本论文也发展出一套人机介面,透过单一按键就能轻易控制系统去侦测车外环境资讯。
本论文主要分为三大部分:物件估测、车辆侦测与物件追踪,第一部分物件估测透过事前决定的正负样本,使用二进制范梯度(Binary Normal Gradient)形成特征结合线性支持迹向量求得影像中物件的可能位置与其尺寸,第二部分车辆侦测本论文使用自适应性增益来训练一组弱分类器,组成一组强分器,同时弱分类器是使用哈尔特征的基本五个型态来描述事前已知的样本,第三部分车辆侦测本论文使用粒子滤波器结合侦测到的物件颜色来描述并追踪物件,最后本论文依据上架构实现出一套针对车辆的侦测与追踪系统,所得的最高侦测率有94%以上而误侦测率最低只有7%左右的数值。
In recent years, the traffic accidents happen because drivers are not concentrating on the front vehicles. This thesis develops a vehicle detection and tracking system which can avoid traffic accidents. Unlike other complex hardware or software system, this dissertation uses USB camera and computer to build a hardware architecture. The software architecture contains an offline training model.
This paper has three part: object estimation, object detection and object tracking In first part, the object estimation calculates the object probable position and scale size in processing image by offline training model .The offline model is combined with positive samples and negatives samples which using the BING(Binary Normal Gradient) and support vector machine. In second part , the several weak classifiers use AdaBoost algorithm to estimate the cascade classifiers, and then the weak classifier is calculated by five kinds of Haar like features which are described with offline positive and negative samples. In third part, the detection object tracked by particle filter, the particle filter’s likelihood function is yielded with the object’s color features. Finally, our method is combined with three parts and applied to vehicle detection and tracking system. The thesis has the highest 94% detection rate and the lowest 7% false alarm in our experiments
URI: http://140.113.39.130/cdrfb3/record/nctu/#GT070260014
http://hdl.handle.net/11536/127520
显示于类别:Thesis