본문 바로가기
  • Home

Improved CNN Algorithm for Object Detection in Large Images

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2020, 25(1), pp.45-53
  • DOI : 10.9708/jksci.2020.25.01.045
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science
  • Received : October 22, 2019
  • Accepted : December 11, 2019
  • Published : January 31, 2020

Seong Bong Yang 1 Soojin Lee 1

1국방대학교

Accredited

ABSTRACT

Conventional Convolutional Neural Network(CNN) algorithms have limitations in detecting small objects in large image. In this paper, we propose an improved model which is based on Region Of Interest(ROI) selection and image dividing technique. We prepared YOLOv3 / Faster R-CNN algorithms which are transfer-learned by airfield and aircraft datasets. Also we prepared large images for testing. In order to verify our model, we selected airfield area from large image as ROI first and divided it in two power n orders. Then we compared the aircraft detection rates by number of divisions. We could get the best size of divided image pieces for efficient small object detection derived from the comparison of aircraft detection rates. As a result, we could verify that the improved CNN algorithm can detect small object in large images.

Citation status

* References for papers published after 2023 are currently being built.