Technology of Graphic & Image
|
3492-3495

Object detection based on convolutional feature fusion

Wang Wei1
Pan Qiuyu1,2
Wang Mingming1
Wang Daoshun2
1. College of Computer Science, Xi'an Polytechnic University, Xi'an 710600, China
2. Dept. of Computer Science & Technology, Tsinghua University, Beijing 100084, China

Abstract

Aiming at the problem that existing detection algorithms are easily affected by some complex factors, such as the image scale, object occlusion or truncation, this paper studied the influence of features originating from different levels of CNN on the detection results and proposed an object detection algorithm based on convolutional features fusion in deep network. The algorithm adopted multi-stage feature reuse and feature fusion to reduce the loss of correlation between features, which made the mAP value reaching 84.21% in the PASCAL VOC 2007 test dataset. Compared with the non-fusion and traditional fusion methods, the proposed algorithm improves the mAP value of 4.41% and 2.71% respectively.

Foundation Support

国家自然科学基金资助项目(61601358,6197225)
陕西省教育厅专项科研计划资助项目(15JK1317)
国家新闻出版广电总局数字内容防伪与安全取证重点实验室项目

Publish Information

DOI: 10.19734/j.issn.1001-3695.2019.05.0241
Publish at: Application Research of Computers Printed Article, Vol. 37, 2020 No. 11
Section: Technology of Graphic & Image
Pages: 3492-3495
Serial Number: 1001-3695(2020)11-059-3492-04

Publish History

[2020-11-05] Printed Article

Cite This Article

王伟, 潘秋羽, 王明明, 等. 基于卷积特征融合的通用目标检测方法 [J]. 计算机应用研究, 2020, 37 (11): 3492-3495. (Wang Wei, Pan Qiuyu, Wang Mingming, et al. Object detection based on convolutional feature fusion [J]. Application Research of Computers, 2020, 37 (11): 3492-3495. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.


Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)