Discriminatively trained patch-based model for occupant classification

作     者：Huang, S. -S. 

作者机构：Natl Kaohsiung First Univ Sci & Technol Dept Comp & Commun Engn Kaohsiung Taiwan 

出 版 物：《IET INTELLIGENT TRANSPORT SYSTEMS》 (IET Intel. Transport Syst.)

年 卷 期：2012年第6卷第2期

页      面：132-138页

核心收录：

学科分类：0808[工学-电气工程] 08[工学] 0823[工学-交通运输工程] 

主　　题：Traffic engineering computing generative models computer vision vision-based occupant classification method Computer vision and image processing techniques Knowledge engineering techniques misclassification problem patch selection vehicle occupancy Optical, image and video signal processing discriminatively trained patch-based model image classification boosting algorithm Gaussian distribution learning (artificial intelligence) road safety intraclass variance Other topics in statistics traffic engineering computing 

摘      要：This study presents a vision-based occupant classification method which is essential for developing a system that can intelligently decide when to turn on airbags based on vehicle occupancy. To circumvent intra-class variance, this work considers the empty class as a reference and describes the occupant class by using appearance difference rather than the traditional methods of using appearance itself. Each class in this work is modelled using a set of representative parts called patches. Each patch is represented by a Gaussian distribution. This approach successfully alleviates the mis-classification problem resulting from severe lighting change which makes the image locally overexposed or underexposed. Instead of using maximum likelihood for patch selection and estimating the parameters of the proposed generative models, the proposed method discriminatively learns models through a boosting algorithm by minimising training error. Experimental results from many videos (approximately 1 630 000 frames) from a camera deployed on a moving platform demonstrate the effectiveness of the proposed approach.