The Application of Improved YOLO V3 in Multi-Scale Target Detection
Source abstract
Abstract
Target detection is one of the most important research directions in computer vision. Recently, a variety of target detection algorithms have been proposed. Since the targets have varying sizes in a scene, it is essential to be able to detect the targets at different scales. To improve the detection performance of targets with different sizes, a multi-scale target detection algorithm was proposed involving improved YOLO (You Only Look Once) V3. The main contributions of our work include: (1) a mathematical derivation method based on Intersection over Union (IOU) was proposed to select the number and the aspect ratio dimensions of the candidate anchor boxes for each scale of the improved YOLO V3; (2) To further improve the detection performance of the network, the detection scales of YOLO V3 have been extended from 3 to 4 and the feature fusion target detection layer downsampled by 4× is established to detect the small targets; (3) To avoid gradient fading and enhance the reuse of the features, the six convolutional layers in front of the output detection layer are transformed into two residual units. The experimental results upon PASCAL VOC dataset and KITTI dataset show that the proposed method has obtained better performance than other state-of-the-art target detection algorithms.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Neural Network Applications · Infrared Target Detection Methodologies · Advanced Image and Video Retrieval Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110169, China
University of Chinese Academy of Sciences, Beijing 100049, China
Key Laboratory of Opto-Electronic Information Processing, Chinese Academy of Science, Shenyang 110016, China
The Key Lab of Image Understanding and Computer Vision, Shenyang 110016, China
References (36)
Show source-provided references
1. Van de Sande, K.E.A., Uijlings, J.R.R., Gevers, T., and Smeulders, A.W.M. (2011, January 6–13). Segmentation as selective search for object recognition. Proceedings of the IEEE International Conference on Computer Vision, Barcelona, Spain.10.1109/ICCV.2011.6126456 ↗
2. Girshick, R., Donahue, J., Darrelland, T., and Malik, J. (2014, January 24–27). Rich feature hierarchies for object detection and semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.10.1109/CVPR.2014.81 ↗
3. A novel framework for intelligent surveillance system based on abnormal human activity detection in academic environments10.1007/s00521-016-2363-z ↗
4. Nguyen-Meidine, L.T., Granger, E., Kiran, M., and Blais-Morin, L.A. (2018). A Comparison of CNN-based Face and Head Detectors for Real-Time Video Surveillance Applications. arXiv.10.1109/IPTA.2017.8310113 ↗
5. Yu, R., Wang, H., and Davis, L.S. (2018). RemoteNet: Efficient Relevant Motion Event Detection for Large-scale Home Surveillance Videos. arXiv.10.1109/WACV.2018.00183 ↗
6. Chen, X., Ma, H., Wan, J., Li, B., and Xia, T. (2016, January 27–30). Multi-view 3d object detection network for autonomous driving. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2017.691 ↗
7. Object recognition and detection with deep learning for autonomous driving applications10.1177/0037549717709932 ↗
8. Vehicle detection from high-resolution satellite imagery using morphological shared-weight neural networks10.1016/j.imavis.2006.12.011 ↗
9. Wang, L., Lu, Y., Wang, H., Zheng, Y., Ye, H., and Xue, X. (2016). Evolving Boxes for Fast Vehicle Detection. arXiv.10.1109/ICME.2017.8019461 ↗
10. Deep learning10.1038/nature14539 ↗
11. Liu, L., Ouyang, W., Wang, X., Fieguth, P., Chen, J., Liu, X., and Pietikäinen, M. (2018). Deep learning for generic object detection: A survey. arXiv.10.1007/s11263-019-01247-4 ↗
12. Tian, Y., Ping, L., Wang, X., and Tang, X. (2015, January 8–10). Pedestrian detection aided by deep learning semantic tasks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.10.1109/CVPR.2015.7299143 ↗
13. Levi, G., and Hassncer, T. (2015, January 8–10). Age and gender classification using convolution neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.10.1109/CVPRW.2015.7301352 ↗
14. Hu, P., and Ramanan, D. (2017, January 22–25). Finding Tiny Faces. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.166 ↗
15. Attia, A., and Dayan, S. (2018). Detecting and counting tiny faces. arXiv.
16. Zhou, Y., Liu, L., Shao, L., and Mellor, M. (2016). DAVE: A Unified Framework for Fast Vehicle Detection and Annotation. arXiv.10.1007/978-3-319-46475-6_18 ↗
17. Fast multi class vehicle detection on aerial images10.1109/LGRS.2015.2439517 ↗
18. Real-world railway traffic detection based on faster better network10.1109/ACCESS.2018.2879270 ↗
19. Gradient based learning applied to document recognition10.1109/5.726791 ↗
20. Srivastava, R.K., Greff, K., and Schmidhuber, J. (2015). Training very deep networks. arXiv.
21. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
22. Gao, H., Zhuang, L., Maaten, L.V.D., and Weinberger, K.Q. (2017, January 22–25). Densely Connected Convolutional Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.243 ↗
23. Girshick, R. (2015, January 8–10). Fast R-CNN. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.10.1109/ICCV.2015.169 ↗
24. Faster R-CNN: Towards real-time object detection with region proposal networks10.1109/TPAMI.2016.2577031 ↗
25. He, K., Gkioxari, G., Dollar, P., and Girshick, R. (2017, January 22–29). Mask R-CNN. Proceedings of the International Conference on Computer Vision (ICCV), Venice, Italy.10.1109/ICCV.2017.322 ↗
26. Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., and Lecun, Y. (2013). Overfeat: Integrated recognition, localization and detection using convolutional networks. arXiv.
27. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., and Fu, C.Y. (2016, January 8–16). SSD: Single shot multi Box detector. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.10.1007/978-3-319-46448-0_2 ↗
28. Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27–30). You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.91 ↗
29. Redmon, J., and Farhadi, A. (2017, January 22–25). YOLO 9000: Better, Faster, Stronger. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.690 ↗
30. Redmon, J., and Farhadi, A. YOLOv3: An Incremental Improvement. Available online: https://arxiv.org/abs/1804.02767.
31. Van Etten, A. You only Look Twice: Rapid Multi-Scale Object Detection in Satellite Imagery. Available online: https://arxiv.org/abs/1805.09512.
32. Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., and Belongie, S. (2017, January 22–25). Feature pyramid networks for object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.106 ↗
33. Eggert, C., Zecha, D., Brehm, S., and Lienhart, R. (2017, January 6–9). Improving Small Object Proposals for Company Logo Detection. Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval, Bucharest, Romania.10.1145/3078971.3078990 ↗
34. Fu, C., Liu, W., Ranga, A., Tyagi, A., and Berg, A.C. DSSD: Deconvolutional Single Shot Detector. Available online: https://arxiv.org/abs/1701.06659.
35. A light weight small object detection algorithm based on improved SSD10.3788/IRLA201847.0703005 ↗
36. Vehicle detection in aerial imagery: A small target detection benchmark10.1016/j.jvcir.2015.11.002 ↗