TF-YOLO: An Improved Incremental Network for Real-Time Object Detection
Source abstract
Abstract
In recent years, significant advances have been gained in visual detection, and an abundance of outstanding models have been proposed. However, state-of-the-art object detection networks have some inefficiencies in detecting small targets. They commonly fail to run on portable devices or embedded systems due to their high complexity. In this workpaper, a real-time object detection model, termed as Tiny Fast You Only Look Once (TF-YOLO), is developed to implement in an embedded system. Firstly, the k-means++ algorithm is applied to cluster the dataset, which contributes to more excellent priori boxes of the targets. Secondly, inspired by the multi-scale prediction idea in the Feature Pyramid Networks (FPN) algorithm, the framework in YOLOv3 is effectively improved and optimized, by three scales to detect the earlier extracted features. In this way, the modified network is sensitive for small targets. Experimental results demonstrate that the proposed TF-YOLO method is a smaller, faster and more efficient network model increasing the performance of end-to-end training and real-time object detection for a variety of devices.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Neural Network Applications · Visual Attention and Saliency Detection · Video Surveillance and Tracking Methods
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Aerospace Science and Technology, Xidian University, Xi’an 710071, China
Funding
National Natural Science Foundation of China
References (37)
Show source-provided references
1. Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (July, January 26). You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.
2. Jiang, H., Wang, J., Yuan, Z., Wu, Y., Zheng, N., and Li, S. (2013, January 23–28). Salient object detection: A discriminative regional feature integration approach. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Portland, OR, USA.10.1109/CVPR.2013.271 ↗
3. Tang, C., Ling, Y., Yang, X., Jin, W., and Zheng, C. (2018). Muti-view object detection based on deep learning. Appl. Sci., 8.10.3390/app8091423 ↗
4. Jeong, Y.N., Son, S.R., Jeong, E.H., and Lee, B.K. (2018). An Integrated Self-Diagnosis System for an Autonomous Vehicle Based on an IoT Gateway and Deep Learning. Appl. Sci., 7.10.3390/app8071164 ↗
5. Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014, January 24–27). Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.10.1109/CVPR.2014.81 ↗
6. He, K., Zhang, X., Ren, S., and Sun, J. (2014, January 6–12). Spatial pyramid pooling in deep convolutional networks for visual recognition. Proceedings of the European Conference on Computer Vision, Zurich, Switzerland.10.1007/978-3-319-10578-9_23 ↗
7. Girshick, R. (, January 8–10). Fast r-cnn. Proceedings of the IEEE International Conference on Computer Vison, Boston, MA, USA.
8. Ren, S., He, K., Girshick, R., and Sun, J. (2015, January 7–12). Faster r-cnn: Towards real-time object detection with region proposal networks. Proceedings of the International Conference on Neural Information Processing Systems, Cambridge, MA, USA.
9. Li, Y., He, K., and Sun, J. (2016, January 9). R-fcn: Object detection via region-based fully convolutional networks. Proceedings of the International Conference on Neural Information Processing Systems, Barcelona, Spain.
10. Object detection with discriminatively trained part-based models10.1109/TPAMI.2009.167 ↗
11. Perazzi, F., Krahenbuhl, P., Pritch, Y., and Hornung, A. (2012, January 16–21). Saliency filters: Contrast based filtering for salient region detection. Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA.10.1109/CVPR.2012.6247743 ↗
12. Real-time indoor assistive localization with mobile omnidirectional vision and cloud GPU acceleration10.3934/ElectrEng.2017.1.74 ↗
13. Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., and Darrell, T. (2014, January 37). Caffe: Convolutional architecture for fast feature embedding. Proceedings of the 22nd ACM International Conference on Multimedia, OR, Florida, FL, USA.10.1145/2647868.2654889 ↗
14. Multiscale Object Detection in Infrared Streetscape Images Based on Deep Learning and Instance Level Data Augmentation10.3390/app9030565 ↗
15. Vision-based pose estimation for textureless space objects by contour points matching10.1109/TAES.2018.2815879 ↗
16. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C., and Berg, A.C. (2016, January 8–16). SSD: Single shot multibox detector. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.10.1007/978-3-319-46448-0_2 ↗
17. Chang, C., Siagian, C., and Itti, L. (2010, January 18–22). Mobile robot vision navigation & localization using Gist and Saliency. Proceedings of the 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems, Taipei, Taiwan.
18. Zhang, J., Sclaroff, S., Lin, Z., Shen, X., Price, B., and Mech, R. (2015, January 11–18). Minimum barrier salient object detection at 80 FPS. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (ICCV), Santiago, Chile.10.1109/ICCV.2015.165 ↗
19. Redmon, J., and Farhadi, A. (2016). YOLO9000: Better, faster, stronger. arXiv, Available online: https://arxiv.org/abs/1612.08242.10.1109/CVPR.2017.690 ↗
20. Shafiee, M.J., Chywl, B., and Li, F. (2017). Fast YOLO: A fast you only look once system for real-time embedded object detection In video. arXiv.10.15353/vsnl.v3i1.171 ↗
21. Zhao, R., Ouyang, W., Li, H., and Wang, X. (2015, January 7–12). Saliency detection by multi-context deep learning. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.10.1109/CVPR.2015.7298731 ↗
22. Mousavian, A., and Kosecka, J. (2015). Deep convolutional features for image based retrieval and scene categorization. arXiv.
23. Wan, J., Wang, D., Hoi, S.C.H., Wu, P., Zhu, J., Zhang, Y., and Li, J. (2014, January 3–7). Deep Learning for Content-Based Image Retrieval: A Comprehensive Study. Proceedings of the ACM International Conference on Multimedia, Orlando, FL, USA.10.1145/2647868.2654948 ↗
24. Towards real-time object detection on embedded systems10.1109/TETC.2016.2593643 ↗
25. 3D Interpreter networks for viewer-centered wireframe modeling10.1007/s11263-018-1074-6 ↗
26. Selective Learning Confusion Class for Text-Based CAPTCHA Recognition10.1109/ACCESS.2019.2899044 ↗
27. Xiang, Y., Kim, W., Chen, W., Ji, J., Choy, C., Su, H., and Savarese, S. (2016, January 8–16). ObjectNet3D: A large-scale database for 3D object recognition. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.10.1007/978-3-319-46484-8_10 ↗
28. Huang, G., Liu, Z., and Van, D. (2017, January 21–26). Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Hawaii, HL, USA.10.1109/CVPR.2017.243 ↗
29. Yu, X., Zhou, F., and Chandraker, M. (2016, January 8–16). Deep deformation network for object landmark localization. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.10.1007/978-3-319-46454-1_4 ↗
30. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015, January 7–12). Going deeper with convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.10.1109/CVPR.2015.7298594 ↗
31. Ye, G., Tang, Z., Fang, D., Zhu, Z., Feng, Y., Xu, P., Chen, X., and Wang, Z. (2018, January 15–19). Yet Another Text Captcha Solver: A Generative Adversarial Network Based Approach. Proceedings of the ACM Conference on Computer and Communications Security, Toronto, ON, Canada.10.1145/3243734.3243754 ↗
32. Information fusion in content based image retrieval: A comprehensive overview10.1016/j.inffus.2017.01.003 ↗
33. Frintrop, S., Klodt, M., and Rome, E. (2007, January 21–24). A real-time visual attention system using integral images. Proceedings of the 5th International Conference on Computer Vision Systems, Bielefeld, Germany.
34. Sparse representation for 3D shape estimation: A convex relaxation approach10.1109/TPAMI.2016.2605097 ↗
35. A novel multiresolution spatiotemporal saliency detection model and its applications in image and video compression10.1109/TIP.2009.2030969 ↗
36. Sivic, J., and Zisserman, A. (2003, January 13–16). Video Google: A text retrieval approach to object matching in videos. Proceedings of the Ninth IEEE International Conference on Computer Vision, Nice, France.10.1109/ICCV.2003.1238663 ↗
37. Liu, D., Hua, G., Viola, P., and Chen, T. (2008, January 23–28). Integrated feature selection and higher-order spatial feature extraction for object categorization. Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, AK, USA.10.1109/CVPR.2008.4587403 ↗