Small object detection via precise region-based fully convolutional networks

Dengyong Zhang, Jiawei Hu, Feng Li, Xiangling Ding, Arun Kumar Sangaiah, Victor S. Sheng

Research output: Contribution to journalArticlepeer-review

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 lowcomparedwith 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 positionsensitive 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 3.7% for object detection tasks and an increase of 6.0% for small objects.

Original languageEnglish
Pages (from-to)1503-1517
Number of pages15
JournalComputers, Materials and Continua
Volume69
Issue number2
DOIs
StatePublished - 2021

Keywords

  • PS-Pr-RoI pooling
  • Precise R-FCN
  • Small object detection
  • Two-stage detector

Fingerprint

Dive into the research topics of 'Small object detection via precise region-based fully convolutional networks'. Together they form a unique fingerprint.

Cite this