Improved CNN Algorithm for Object Detection in Large Images

Seong Bong Yang; Soojin Lee

doi:10.9708/jksci.2020.25.01.045

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

KCI Citation Counts (5)
열림/닫힘 버튼
REFERENCES (15)
열림/닫힘 버튼
* 2021년 이후 발행 논문의 참고문헌은 현재 구축 중입니다.

[journal] 유재형 / 2019 / Improving Performance of YOLO Network Using Multi-layer Overlapped Windows for Detecting Correct Position of Small Dense Objects / 한국컴퓨터정보학회논문지 / 한국컴퓨터정보학회 24(3) : 19~27 / https://doi.org/10.9708/jksci.2019.24.03.019

[confproc] M. Kisantal / 2019 / Augmentation for small object detection / Computer Vision and Pattern Recognition (CVPR)

[confproc] G. Cao / 2018 / Feature-fused SSD: fast detection for small objects / 9th International Conference on Graphic and Image Processing (ICGIP)

[book] Y. Ren / 2018 / Small Object Detection in Optical Remote Sensing Images via Modified Faster R-CNN / Multidisciplinary Digital Publishing Institute (MDPI)

[journal] Min Peng / 2016 / NIRFaceNet: A Convolutional Neural Network for Near-Infrared Face Identification / Information / MDPI AG 7(4) : 61~ / 10.3390/info7040061

[journal] Shaoqing Ren / 2017 / Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks / IEEE Transactions on Pattern Analysis and Machine Intelligence / Institute of Electrical and Electronics Engineers (IEEE) 39(6) : 1137~1149 / 10.1109/TPAMI.2016.2577031

[confproc] J. Dai / 2016 / R-FCN: Object Detection via Region-based Fully Convolutional Networks / Neural Information Processing Systems(NIPS)

[confproc] W. Liu / 2016 / SSD: Single Shot MultiBox Detector / European Conference on Computer Vision(ECCV) 2016 : 21~37

[confproc] J. Redmon / 2016 / You Only Look Once:Unified, Real-Time Object Detection / The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) : 779~788

[confproc] I. Goodfellow / 2014 / Generative Adversarial Networks / Neural Information Processing Systems(NIPS)

[confproc] A. Mikołajczyk / 2018 / Data augmentation for improving deep learning in image classification problem / Conference: 2018 International Interdisciplinary PhD Workshop (IIPhDW) : 117~122

[journal] Hoo-Chang Shin / 2016 / Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning / IEEE Transactions on Medical Imaging / Institute of Electrical and Electronics Engineers (IEEE) 35(5) : 1285~1298 / 10.1109/TMI.2016.2528162

[web] Digitalglobe. com / 2017 / Worldview-3 Data sheet / https://dgv4-cms-production.s3.amazonaws.com/uploads/document/file/128/DG2017_WorldView-3_DS.pdf

[confproc] J. Redmon / 2018 / YOLOv3: An Incremental Improvement / Computer Vision and Pattern Recognition (cs.CV)

[web] Tzutalin / LabelImg, Git code / https://github.com/tzutalin/labelImg

KJC Korea
Journal Central

Statistics

Tools

Sharing

Issue List

Citation status