| 改进型AdaBoost算法在车辆检测中的应用 |
| |
| 引用本文： | 刘天键,邱立达,张宁.改进型AdaBoost算法在车辆检测中的应用[J].闽江学院学报,2014(2):74-79. |
| |
| 作者姓名： | 刘天键 邱立达 张宁 |
| |
| 作者单位： | 闽江学院物理学与电子信息工程系,福建福州350121 |
| |
| 基金项目： | 福建省教育厅科技项目（JA12263,JB11127）;福州市科技计划项目（2013-G-86） |
| |
| 摘 要： | Adaboost算法通过特征选择把一组弱分类器组合成强分类器，并已成功地应用在人脸识别中．遵循Adaboost算法的基本思想，提出在联合空间进行Haar类特征的选择，并把该算法应用在车辆的检测中．使用基于联合特征空间的Adaboost算法，可以改善检测器的可靠性和快速性．实验结果表明与传统的Adaboost算法相比，可以提高分类器的目标击中率和降低虚警率．
|
| 关 键 词： | AdaBoost算法 联合特征空间 分类器 车辆检测 |
The application of improved AdaBoost algorithm in vehicle detection |
| |
| LIU Tian-jian,QIU Li-da,ZHANG Ning.The application of improved AdaBoost algorithm in vehicle detection[J].Journal of Minjiang University,2014(2):74-79. |
| |
| Authors: | LIU Tian-jian QIU Li-da ZHANG Ning |
| |
| Institution: | (Department of Physics and Electronic Information Engineering, Minjiang University, Fuzhou, Fujian 350121, China) |
| |
| Abstract: | Adaboost is used to select and combine weak classifiers from a very large pool of weak clas- sifiers and it has been proven to be very successful for detecting faces. We follow the approach and present a new Harr feature selection in joint feature space. It is applied to detect rear views of cars. By using Adaboost in joint feature spaces, a reliable and fast classification is got. Experiment shows this classification perform good hitting rate and litter false positive rate than traditional AdaBoost algorithm. |
| |
| Keywords: | AdaBoost algorithm joint feature spaces classifier car detector |
| 本文献已被 CNKI 维普 等数据库收录！ |
