Real-Time Object Detection Based on YOLO-v2 for Tiny Vehicle Object
Tóm tắt
Object detection plays an essential role in automatic driving system (ADS) and driver assistance system (DAS). However, existing real-time detection models for tiny vehicle objects have the problems of low precision and poor performance. To solve these issues, a novel real-time object detection model based on You Only Look Once Version 2 (YOLO-v2) deep learning framework is proposed for tiny vehicle objects, called Optimized You Only Look Once Version 2 (O-YOLO-v2). In the proposed model, a new architecture is introduced by adding the convolution layers at different locations to enhance the feature extraction ability of network. At the same time, the residual modules are added to solve the problem of gradient disappearance or dispersion caused by the increase of network depth. Furthermore, the low-level features and high-level features of the network are combined to improve the detection accuracy of tiny vehicle objects. Experimental results on the KITTI dataset show that the model not only improves the accuracy of tiny vehicle object detection but also improves the accuracy of vehicle detection (the accuracy reaches 94%) without decreasing the detection speed.
Tài liệu tham khảo
Sotelo MÁ, García MÁ, Flores R. Vision based intelligent system for autonomous and assisted downtown driving. In: International conference on computer aided systems theory. Berlin, Heidelberg: Springer; 2003. p. 326–36.
Fuchun L, Rongfen Z, Yuhong L. Design of intelligent auxiliary driving system based on deep learning. J Guizhou Univ. 2018;35(1):73–7.
Nguyen VD, Nguyen HV, Tran DT, Lee SJ, Jeon JW. Learning framework for robust obstacle detection, recognition, and tracking. IEEE Trans Intell Transp Syst. 2016;18(6):1633–46.
Gu Q, Yang J, Kong L, Yan WQ, Klette R. Embedded and real-time vehicle detection system for challenging on-road scenes. Opt Eng. 2017;56(6): 063102.
Liao S, Jain AK, Li SZ. A fast and accurate unconstrained face detector. IEEE Trans Pattern Anal Mach Intell. 2016;38(2):211–23.
Bourdev L, Brandt J. Robust object detection via soft cascade. In 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR’05). IEEE. 2005;2:236–43.
Dalal N, Triggs B. Histograms of oriented gradients for human detection. 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR’05). IEEE. 2005;1:886–93.
Meng Qingtao. Face detection based on haar-feature probability distribution and SVM. Doctoral dissertation, East China Normal University. 2008.
Zhu F, Lu Y, Ying N, Giakos G. Fast vehicle detection based on evolving convolutional neural network. In: 2017 IEEE International conference on imaging systems and techniques (IST). 2017, pp. 1–4. https://doi.org/10.1109/IST.2017.8261505.
Ren S, He K, Girshick R, J Sun, Faster R-CNN: towards real-time object detection with region proposal networks, in: Proceedings of the advances in neural information processing systems, 2015;91–99.
Lin W, Hehe Z. Application of Faster R-CNN Model in Vehicle Detection. J Comput Appl. 2018;38(3):666.
Jun SANG, Pei GUO, Zhili XIANG, Hongling LUO, Xin CHEN. Vehicle detection based on faster-RCNN. J Chongqing Univ. 2017;40(7):32–6.
Zhang Qi Hu, Guangdi LY, Xin Z. Binocular vision vehicle detection method on improved Fast-RCNN. J Appl Opt. 2018;39(06):75–81.
Gao Z, Li S, Chen J, Li Z. Pedestrian detection method based on YOLO network. Comput Eng. 2018;44(5):215–9, 226.
Tao J, Wang H, Zhang X, Li X, Yang H. An object detection system based on YOLO in traffic scene. 2017 6th International Conference on Computer Science and Network Technology (ICCSNT). IEEE. 2017.
Ren S, He K, Girshick R, Sun J. Faster r-cnn: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell. 2015;39(6):1137–49.
Redmon J, Divvala S, Girshick R, Farhadi A. You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016, pp. 779–788.
Redmon J, Farhadi A. IEEE 2017 IEEE conference on computer vision and pattern recognition (cvpr)—honolulu, hi (2017.7.21–2017.7.26) 2017 IEEE conference on computer vision and pattern recognition (cvpr)—yolo9000: better, faster, stronger. 2017; 6517–6525.
He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2016, pp. 770–778.
Redmon J, Divvala S, Girshick R, Farhadi A. You only look once: unified, real-time object detection. In Proceedings of the 2016 IEEE conference on computer vision and pattern recognition (CVPR), Las Vegas, NV, USA. 27–30 June 2016;779–788.
Redmon J, Farhadi A, YOLO9000: Better, faster, stronger. In Proceedings of the 2017 IEEE conference on computer vision and pattern recognition (CVPR), Honolulu, HI, USA, 21–26 July 2017; pp. 6517–6525.
Everingham M, Winn J. The pascal visual object classes challenge 2007 (voc2007) development kit. Int J Comput Vision. 2006;111(1):98–136.