Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Journal of Tianjin Normal University(Natural Science Edition)》 2018-05
Add to Favorite Get Latest Update

Vehicle detection algorithm based on parallel crossover PCANet

ZHU Shidong;JIANG Lifen;SUN Huazhi;MA Chunmei;College of Computer and Information Engineering,Tianjin Normal University;  
Aiming at the problem of traditional machine learning vehicle detection algorithms for low vehicle detection rate in complex scenes,a parallel crossover PCANet vehicle detection algorithm is proposed. The algorithm uses two PCANet,extracted with the actual vehicle image data set and convolutional neural network. The vehicle profile image dataset trains two feature extractors and fuses the extracted features as a final vehicle feature to train the SVM classifier. The experimental results show that the vehicle detection algorithm presented has a simpler structure,shorter training time,more sufficient learning and higher recognition efficiency compared with the traditional vehicle detection algorithm,and has achieved better classification effect and detection effect.
【Fund】: 国家自然科学基金资助项目(61702370);; 天津市国际科技合作资助项目(14RCGFGX00847);; 天津市自然科学基金资助项目(17JCYBJC16400);; 天津市科技计划资助项目(17ZLZXZF00530);; 天津师范大学131三层次人选资助项目(043/135305QS20);天津师范大学博士基金资助项目(043/135202XB1615 043/135202XB1705)
【CateGory Index】: TP391.41
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved