밀집한 소형 물체의 정확한 위치 검출을 위한 다계층 중첩 윈도우를 이용한 YOLO 네트워크의 성능개선
Improving Performance of YOLO Network Using Multi-layer Overlapped Windows for Detecting Correct Position of Small Dense Objects
1
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
This paper proposes a new method using multi-layer overlapped windows to improve the performance of YOLO network which is vulnerable to detect small dense objects. In particular, the proposed method uses the YOLO Network based on the multi-layer overlapped windows to track small dense vehicles that approach from long distances. The method improves the detection performance for location and size of small vehicles. It allows crossing area of two multi-layer overlapped windows to track moving vehicles from a long distance to a short distance. And the YOLO network is optimized so that GPU computation time due to multi-layer overlapped windows should be reduced. The superiority of the proposed algorithm has been proved through various experiments using captured images from road surveillance cameras.
Abstract
This paper proposes a new method using multi-layer overlapped windows to improve the performance of YOLO network which is vulnerable to detect small dense objects. In particular, the proposed method uses the YOLO Network based on the multi-layer overlapped windows to track small dense vehicles that approach from long distances. The method improves the detection performance for location and size of small vehicles. It allows crossing area of two multi-layer overlapped windows to track moving vehicles from a long distance to a short distance. And the YOLO network is optimized so that GPU computation time due to multi-layer overlapped windows should be reduced. The superiority of the proposed algorithm has been proved through various experiments using captured images from road surveillance cameras.
참고문헌 (17)
- S. Russell, "rtificial Intelligence : A Modern Approach" (2009), Prentice Hall Press
- O. Russakovsky, "ImageNet large scale visual recognition challenge", Int. J. Comput. Vis, 115(3), pp.211~252 (2015)
- S. Ioffe, "Batch normalization :Accelerating deep network training by reducing internal covariate shift", Proc. ICML (2015)
- T. Young, "Recent Trends in Deep Learning Based Natural Language Processing", arXiv preprint arXiv : 1708. 02709, ~ (2017)
- K. He, "Mask R-CNN", ICCV, pp.2980~2988 (2017), IEEE
- O. Ronneberger, "Unet : Convolutional Networks for Biomedical Image Segmentation", International Conference on Medical image computing and computer-assisted intervention, pp.234~241 (2015)
- V. Badrinarayanan, "SegNet : A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation", arXiv preprint arXiv : 1511. 00561, ~ (2015)
- Y. Lecun, "Gradientbased learning applied to document recognition", Proceedings of the IEEE, 86(11), pp.2278~2324 (1998)
- K. Simonyan, "Very deep convolutional networks for large-scale image recognition", Proc. ICLR (2015)
- A. Krizhevsky, "Imagenet classification with deep convolutional neural networks", Advances in neural information processing systems, pp.1097~1105 (2012)
- C. Szegedy, "Going deeper with convolutions", Proc. CVPR (2015)
- R. Girshick, "Rich feature hierarchies for accurate object detection and semantic segmentation", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.580~587 (2014)
- R. Girshick, "Fast r-cnn", Proceedings of the IEEE International Conference on Computer Vision, pp.1440~1448 (2015)
- W. Liu, "SSD : Single shot multibox detector", Proc. ECCV, pp.21~37 (2016)
- J. Redmon, "You only look once : Unified, real-time object detection", Proc. CVPR (2016)
- J. Redmon, "YOLO9000 : Better, Faster, Stronger", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.779~788 (2016)
- J. Redmon, "YOLOv3 : An Incremental Improvement", arXiv preprint arXiv : 1804. 02767, ~ (2018)