Vol.69, No.2, 2021, pp.1503-1517, doi:10.32604/cmc.2021.017089
OPEN ACCESS
ARTICLE
Small Object Detection via Precise Region-Based Fully Convolutional Networks
  • Dengyong Zhang1,2, Jiawei Hu1,2, Feng Li1,2,*, Xiangling Ding3, Arun Kumar Sangaiah4, Victor S. Sheng5
1 Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation, Changsha University of Science and Technology, Changsha, 410114, China
2 School of Computer and Communication Engineering, Changsha University of Science and Technology, Changsha, 410114, China
3 School of Computer Science and Engineering, Hunan University of Science and Technology, Xiangtan, 411004, China
4 School of Computing Science and Engineering, Vellore Institute of Technology (VIT), Vellore, 632014, India
5 Department of Computer Science, Texas Tech University, Lubbock, 79409, TX, USA
* Corresponding Author: Feng Li. Email:
Received 20 January 2021; Accepted 29 March 2021; Issue published 21 July 2021
Abstract
In the past several years, remarkable achievements have been made in the field of object detection. Although performance is generally improving, the accuracy of small object detection remains low compared with that of large object detection. In addition, localization misalignment issues are common for small objects, as seen in GoogLeNets and residual networks (ResNets). To address this problem, we propose an improved region-based fully convolutional network (R-FCN). The presented technique improves detection accuracy and eliminates localization misalignment by replacing position-sensitive region of interest (PS-RoI) pooling with position-sensitive precise region of interest (PS-Pr-RoI) pooling, which avoids coordinate quantization and directly calculates two-order integrals for position-sensitive score maps, thus preventing a loss of spatial precision. A validation experiment was conducted in which the Microsoft common objects in context (MS COCO) training dataset was oversampled. Results showed an accuracy improvement of for object detection tasks and an increase of for small objects.
Keywords
Small object detection; precise R-FCN; PS-Pr-RoI pooling; two-stage detector
Cite This Article
Zhang, D., Hu, J., Li, F., Ding, X., Sangaiah, A. K. et al. (2021). Small Object Detection via Precise Region-Based Fully Convolutional Networks. CMC-Computers, Materials & Continua, 69(2), 1503–1517.
This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.