객체 검출을 위한 CNN과 YOLO 성능 비교 실험

Comparison of CNN and YOLO for Object Detection

  • 이용환 (원광대학교 디지털콘텐츠공학과) ;
  • 김영섭 (단국대학교 전자전기공학부)
  • Lee, Yong-Hwan (Dept. of Digital Contents, Wonkwang University) ;
  • Kim, Youngseop (Dept. of Electronics and Electrical Engineering, Dankook University)
  • 투고 : 2020.03.15
  • 심사 : 2020.03.23
  • 발행 : 2020.03.31

초록

Object detection plays a critical role in the field of computer vision, and various researches have rapidly increased along with applying convolutional neural network and its modified structures since 2012. There are representative object detection algorithms, which are convolutional neural networks and YOLO. This paper presents two representative algorithm series, based on CNN and YOLO which solves the problem of CNN bounding box. We compare the performance of algorithm series in terms of accuracy, speed and cost. Compared with the latest advanced solution, YOLO v3 achieves a good trade-off between speed and accuracy.

키워드

참고문헌

  1. Asifullah Khan, Anabia Sohail, Umme Zahoora, Aqsa Saeed Qureshi, "A Survey of the Recent Architectures of Deep Convolutional Neural Networks", Computer Vision and Pattern Recognition, Available at https://arxiv.org/ftp/arxiv/papers/1901/1901.06032.pdf [Accessed Mar. 13, 2020].
  2. Ross Girshick, Jeff Donahue, Trevor Darrell, Jitendra Malik, "Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation", IEEE Conference on Computer Vision and Pattern Recognition, pp.580-587, 2013.
  3. Li Liu, Wanli Ouyang, Xiaogang Wang, Paul Fieguth, Jie Chen, Xinwang Liu, Matti Pietikainen, "Deep Learning for Generic Object Detection: A Survey", International Journal of Computer Vision, vol.128, pp.261-318 2020. https://doi.org/10.1007/s11263-019-01247-4
  4. Kaimin He, Xiangyu Zhang, Shaoqing Ren, Jian Sun, "Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition", European Conference on Computer Vision, Part 3, pp.346-361, 2014.
  5. Licheng Jiao, Fan Zhang, Fang Liu, Shuyuan Yang, Lingling Li, Zhizi Feng, Rong Qu, "A Survey of Deep Learning-based Object Detection", IEEE Access, vol.7, pp.128837-128868, , 2019. https://doi.org/10.1109/ACCESS.2019.2939201
  6. David G. Lowe, "Distinctive Image Features from Scale-Invariant Keypoints", International Journal of Computer Vision, vol.60, pp.91-110, 2004. https://doi.org/10.1023/B:VISI.0000029664.99615.94
  7. Juan Du, "Understanding of Object Detection based on CNN Family and YOLO", Journal of Physics, Conference Series, vol.1004, issue.1, 2018.
  8. Tsung-Yi Lin, Priya Goyal, Roos Girshick, Kaiming He, Piotr Dollar, "Focal Loss for Dense Object Detection", International Conference on Computer Vision, pp.2999-3007, 2017.
  9. Herbert Bay, Andreas Ess, Tinne Tuytelaars, Luc Van Gool, "Speeded-Up Robust Features (SURF)", Computer Vision and Image Understanding, vol.110, issue.3, pp.346-359, 2008. https://doi.org/10.1016/j.cviu.2007.09.014
  10. Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton, "ImageNet Classification with Deep Convolutional Neural Networks", Communications of the ACM, vol.60, no.6, 2017.
  11. Yurong Yang, Huajun Gong, Xinhua Wang, Peng Sun, "Aerial Target Tracking Algorithm Based on Faster RCNN Combined with Frame Differencing", Aerospace, vol.4, no.32, 2017.
  12. Kwanghyun Kim, Sungjun Hong, Baehoon Choi and Euntai Kim, "Probabilistic Ship Detection and Classification using Deep Learning", Applied Sciences, vol.8, no.6, 2018.
  13. Rohith Gandhi, "R-CNN, Fast R-CNN, Faster R-CNN, YOLO - Object Detection Algorithms," 2018. Available at https://towardsdatascience.com/r-cnn-fast-r-cnn-fasterr-cnn-yolo-object-detection-algorithms-36d53571365e. [Accessed: Mar. 13, 2020].
  14. N. Dalal, B. Triggs, "Histograms of Oriented Gradients for Human Detection", IEEE Conference on Computer Vision and Pattern Recognition, pp.886-893, 2005.
  15. Joseph Redmon, Santosh Divvala, Ross Girshick, Ali Farhadi, "You Only Look Once: Unified, Real-time Object Detection", IEEE Conference on Computer Vision and Pattern Recognition, pp.779-788, 2015.
  16. Joseph Redmon, Ali Farhadi, "YOLO9000: Better, Faster, Stronger", IEEE Conference on Computer Vision and Pattern Recognition, pp.6517-6525, 2016.
  17. Joseph Redmon, Ali Farhadi, "YOLO v3: An Incremental Improvement", Computer Vision and Pattern Recognition, 2018. Available at https://pjreddie.com/media/files/papers/YOLOv3.pdf [Accessed Mar.13, 2020].
  18. Qi-Chao Mao, Hong-Mei Sun, Yan-Bo Liu, Rui-Sheng Jia, "Mini-YOLOv3: Real-time Object Detector for Embedded Applications", IEEE Access, vol.7, pp.133529-133538, 2019. https://doi.org/10.1109/ACCESS.2019.2941547
  19. Adrian Carrio, Sai Vemprala, Andres Ripoll, Srikanth Saripalli, Pascual Campoy, "Drone Detection using Depth Maps", International Conference on Intelligent Robots and Systems, pp.1032-1037, 2018.
  20. University of Oxford, "Pascal Visual Object Classes Homepage", Available at http://host.robots.ox.ac.uk/ pascal/VOC/index.html [Accessed: Mar.13, 2020].
  21. Jonathan Huang, Vivek Rathod, Chen Sun, Menglong Zhu, Anoop Korattikara, "Speed/Accuracy Trade-offs for Modern Convolutional Object Detectors", IEEE Conference on Computer Vision and Pattern Recognition, pp.7310-7319, 2017.
  22. Pedro F. Felzenszwalb, Ross B. Girshick, David McAllester, Deva Ramanan, "Object Detection with Discriminatively Trained Part-based Models", IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.32, issue.9, 2010.
  23. Ali Sharif Razavian, Hossein Azizpour, Josephine Sullivan, Stefan Carlsson, "CNN Features Off-the-Shelf: An Astounding Baseline for Recognition", IEEE Conference on Computer Vision and Pattern Recognition, pp.512-519, 2014.
  24. Ross Girshick, "Fast R-CNN", Computer Vision and Pattern Recognition, pp.1440-1448, 2015.
  25. Hyochang Ahn, Yong-Hwan Lee, "A Research of CNNbased Object Detection for Multiple Object Tracking in Image", Journal of the Semiconductor and Display Technology, vol.18, no.3, 2019.
  26. Yong-Hwan Lee, Youngseop Kim, "Implementation of Object Feature Extraction within Image for Object Tracking", Journal of the Semiconductor and Display Technology, vol.17, no.3, 2018.
  27. Rahul Haridas, Jyothi RL, "Convolutional Neural Networks: A Comprehensive Survey", International Journal of Applied Engineering Research, vol.14, no.3, pp.780-789, 2019. https://doi.org/10.37622/IJAER/14.3.2019.780-789
  28. Akshi Kumar, Sukriti Verma, Himanshu Mangla, "A Survey of Deep Learning Techniques in Speed Recognition", International Conference on Advances in Computing, Communication Control and Networking, pp.179-185, 2018.
  29. M. Sornam, Kavitha Muthusubash, V. Vanitha, "A Survey on Image Classification and Activity Recognition using Deep Convolutional Neural Network Architecture", International Conference on Advanced Computing, pp.121-126, 2017.
  30. Azeddine Elhasouny, Florentin Smarandache, "Trends in deep convolutional neural networks architectures: a review", International Conference of Computer Science and Renewable Energies, pp.1-8, 2019.