• Complex
  • Title
  • Keyword
  • Abstract
  • Scholars
  • Journal
  • ISSN
  • Conference
搜索

Author:

Du, Zhuoran (Du, Zhuoran.) | Ji, Junzhong (Ji, Junzhong.) (Scholars:冀俊忠) | Wang, Jingyi (Wang, Jingyi.) | Hu, Qipeng (Hu, Qipeng.) | Gao, Shan (Gao, Shan.) | Zhang, Xiaodan (Zhang, Xiaodan.)

Indexed by:

EI

Abstract:

Current object detection methods are mostly based on the Faster R-CNN which is composed of two stages: 1) the region proposal network which roughly sifts anchors and produces object proposals and 2) the detection network which inputs the generated region proposals and makes predictions of category and bounding box for each region. However, the object proposals are always treated individually in the detection network without taking their relationship into consideration. Specifically, most researches utilize the non-maximum suppression algorithm to reduce the number of proposals by subtracting the neighbouring proposals for either training or testing process. Though a single proposal may be not accurate enough, a union of its neighbouring proposals and itself would represent this object region more comprehensively. Since the neighbouring relationship can be expressed by an edge between two proposals (nodes), the set of region proposals can be modelled in a graph structure. In this paper, we propose a novel neighbouring relationship exploration model (NREM) to improve the object detection by aggregating the neighbouring proposal graph (NPG) based on the graph convolutional network (GCN). Owing to the effective exploration of complementary relationship among neighbouring proposals, our method can improve the detection results significantly. Experiments on the PASCAL VOC 2007 dataset demonstrate the superiority of our proposed method. © 2019 IEEE.

Keyword:

Graph structures Convolution Convolutional neural networks Object detection Object recognition

Author Community:

  • [ 1 ] [Du, Zhuoran]Beijing Municipal Key Laboratory of Multimedia and Intelligent Software Technology, Beijing University of Technology, China
  • [ 2 ] [Du, Zhuoran]Beijing Artificial Intelligence Institute, Beijing University of Technology, China
  • [ 3 ] [Ji, Junzhong]Beijing Municipal Key Laboratory of Multimedia and Intelligent Software Technology, Beijing University of Technology, China
  • [ 4 ] [Ji, Junzhong]Beijing Artificial Intelligence Institute, Beijing University of Technology, China
  • [ 5 ] [Wang, Jingyi]Xi'An Jiaotong University, Faculty of Electronic and Information Engineering, China
  • [ 6 ] [Hu, Qipeng]Beijing Municipal Key Laboratory of Multimedia and Intelligent Software Technology, Beijing University of Technology, China
  • [ 7 ] [Hu, Qipeng]Beijing Artificial Intelligence Institute, Beijing University of Technology, China
  • [ 8 ] [Gao, Shan]Unmanned System Research Institute, Northwestern Polytechnical University, China
  • [ 9 ] [Zhang, Xiaodan]Beijing Municipal Key Laboratory of Multimedia and Intelligent Software Technology, Beijing University of Technology, China
  • [ 10 ] [Zhang, Xiaodan]Beijing Artificial Intelligence Institute, Beijing University of Technology, China

Reprint Author's Address:

  • [zhang, xiaodan]beijing artificial intelligence institute, beijing university of technology, china;;[zhang, xiaodan]beijing municipal key laboratory of multimedia and intelligent software technology, beijing university of technology, china

Show more details

Related Keywords:

Related Article:

Source :

Year: 2019

Page: 178-183

Language: English

Cited Count:

WoS CC Cited Count: 0

SCOPUS Cited Count:

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 1

Online/Total:442/5316904
Address:BJUT Library(100 Pingleyuan,Chaoyang District,Beijing 100124, China Post Code:100124) Contact Us:010-67392185
Copyright:BJUT Library Technical Support:Beijing Aegean Software Co., Ltd.