Scale variant vehicle object recognition by CNN module of multipooling- PCA process

作     者：Yuxiang Guo Itsuo Kumazawa Chuyo Kaku 

作者机构：Department of Information and Communications EngineeringTokyo Institute of TechnologyTokyo 152-8550Japan Research and Development CenterJiangsu Chaoli Electric Manufacture Co.Ltd.Shanghai 212321China 

出 版 物：《Journal of Intelligent and Connected Vehicles》 (智能网联汽车（英文）)

年 卷 期：2023年第6卷第4期

页      面：227-236页

核心收录：

学科分类：08[工学] 080203[工学-机械设计及理论] 082303[工学-交通运输规划与管理] 0802[工学-机械工程] 082302[工学-交通信息工程及控制] 0823[工学-交通运输工程] 

基　　金：supported by the National Natural Science Foundation of China(Grant No.51875340) 

主　　题：object detection scale invariance spatial pyramid pooling multi-pooling convolutional neural network(CNN) 

摘      要：The moving vehicles present different scales in the image due to the perspective effect of different viewpoint *** premise of advanced driver assistance system(ADAS)system for safety surveillance and safe driving is early identification of vehicle targets in front of the ego *** recognition of the same vehicle at different scales requires feature learning with scale *** existing feature vector methods,the normalized PCA eigenvalues calculated from feature maps are used to extract scale-invariant *** study proposed a convolutional neural network(CNN)structure embedded with the module of multi-pooling-PCA for scale variant object *** validation of the proposed network structure is verified by scale variant vehicle image *** with scale invariant network algorithms of Scale-invariant feature transform(SIFT)and FSAF as well as miscellaneous networks,the proposed network can achieve the best recognition accuracy tested by the vehicle scale variant *** testify the practicality of this modified network,the testing of public dataset ImageNet is done and the comparable results proved its effectiveness in general purpose of applications.