Dong Wu, Man-Wen Liao, Wei-Tian Zhang, Xing-Gang Wang, Xiang Bai, Wen-Qing Cheng, Wen-Yu Liu. YOLOP: You Only Look Once for Panoptic Driving Perception. Machine Intelligence Research, vol. 19, no. 6, pp.550-562, 2022. https://doi.org/10.1007/s11633-022-1339-y
Citation: Dong Wu, Man-Wen Liao, Wei-Tian Zhang, Xing-Gang Wang, Xiang Bai, Wen-Qing Cheng, Wen-Yu Liu. YOLOP: You Only Look Once for Panoptic Driving Perception. Machine Intelligence Research, vol. 19, no. 6, pp.550-562, 2022. https://doi.org/10.1007/s11633-022-1339-y

YOLOP: You Only Look Once for Panoptic Driving Perception

doi: 10.1007/s11633-022-1339-y
More Information
  • Author Bio:

    Dong Wu is a senior undergraduate student in electronic information engineering at School of Electronics Information and Communications, Huazhong University of Science and Technology (HUST), China. His research interests include computer vision, machine learning and autonomous driving. E-mail: riserwu@hust.edu.cn ORCID iD: 0000-0002-2306-5769

    Man-Wen Liao is a senior undergraduate student in electronic information engineering at School of Electronics Information and Communications, Huazhong University of Science and Technology, China. His research interests include computer vision, machine learning, robotics and autonomous driving. E-mail: mwliao@hust.edu.cn

    Wei-Tian Zhang is a senior undergraduate student in electronic information engineering at Huazhong University of Science and Technology, China. Her research interests include computer vision and machine learning. E-mail: wtzhang@hust.edu.cn

    Xing-Gang Wang received the B. Sc. and Ph. D. degrees in electronics and information engineering from Huazhong University of Science and Technology, China in 2009 and 2014, respectively. He is currently an associate professor with School of Electronic Information and Communications, HUST, China. He services as Associate Editors for Pattern Recognition and Image and Vision Computing and an editorial board member of Electronics. His research interests include computer vision and machine learning. E-mail: xgwang@hust.edu.cn (Corresponding author) ORCID iD: 0000-0001-6732-7823

    Xiang Bai received the B. Sc., M. Sc., and Ph. D. degrees in electronics and information engineering from Huazhong University of Science and Technology, China in 2003, 2005, and 2009, respectively. He is currently a professor with School of Artificial Intelligence and Automation, HUST, China. His research interests include object recognition, shape analysis, and scene text recognition. E-mail: xbai@hust.edu.cn

    Wen-Qing Cheng received the B. Sc. degree in telecommunication engineering and the Ph. D. degree in electronics and information engineering from Huazhong University of Science and Technology, Wuhan, China in 1985 and 2005, respectively. She is currently a professor and associate dean with School of Electronic Information and Communications, HUST, China. Her research interests include information systems and e-learning applications. E-mail: chengwq@hust.edu.cn

    Wen-Yu Liu received the B. Sc. degree in computer science from Tsinghua University, China in 1986, and the M. Sc. and Ph. D. degrees, in electronics and information engineering from Huazhong University of Science and Technology, China in 1991 and 2001, respectively. He is now a professor of School of Electronic Information and Communications, HUST, China. His research interests include computer vision, multimedia, and machine learning. E-mail: liuwy@hust.edu.cn

  • Received Date: 2022-03-25
  • Accepted Date: 2022-05-10
  • Publish Online: 2022-11-07
  • Publish Date: 2022-11-22
  • A panoptic driving perception system is an essential part of autonomous driving. A high-precision and real-time perception system can assist the vehicle in making reasonable decisions while driving. We present a panoptic driving perception network (you only look once for panoptic (YOLOP)) to perform traffic object detection, drivable area segmentation, and lane detection simultaneously. It is composed of one encoder for feature extraction and three decoders to handle the specific tasks. Our model performs extremely well on the challenging BDD100K dataset, achieving state-of-the-art on all three tasks in terms of accuracy and speed. Besides, we verify the effectiveness of our multi-task learning model for joint training via ablative studies. To our best knowledge, this is the first work that can process these three visual perception tasks simultaneously in real-time on an embedded device Jetson TX2(23 FPS), and maintain excellent accuracy. To facilitate further research, the source codes and pre-trained models are released at https://github.com/hustvl/YOLOP.

     

  • 1 E, D, S and W refer to encoder, detection head, two segment heads and whole network. Therefore, Algorithm 1 can be marked as ED-S-W, and the same for the others.
    2 R, C, D-Aug, and E-SPP refer to the Resnet50 backbone, the CSPDarknet backbone, data augmentation and the extra SPP module in two segment heads. Rec means the recall of the traffic object detection task, and Acc means the accuracy of the lane detection task. This part of the experiment is run on an NVIDIA GeForce 3090. We ensured that all the other hyper-parameters of training and testing are the same under all different settings, which can be found in our GitHub repository: https://github.com/hustvl/YOLOP.
  • loading
  • [1]
    S. Q. Ren, K. M. He, R. Girshick, J. Sun. Faster R-CNN: Towards real-time object detection with region proposal networks. In Proceedings of the 28th International Conference on Neural Information Processing Systems, Montreal, Canada, vol. 1, pp. 91–99, 2015.
    [2]
    A. Bochkovskiy, C. Y. Wang, H. Y. M. Liao. YOLOv4: Optimal speed and accuracy of object detection. DOI: 10.48550/arxiv.2004.10934, 2020.
    [3]
    A. Paszke, A. Chaurasia, S. Kim, E. Culurciello. ENet: A deep neural network architecture for real-time semantic segmentation. DOI: 10.48550/arxiv.1606.02147, 2016.
    [4]
    H. S. Zhao, J. P. Shi, X. J. Qi, X. G. Wang, J. Y. Jia. Pyramid scene parsing network. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Honolulu, USA, pp. 6230–6239, 2017. DOI: 10.1109/CVPR.2017.660.
    [5]
    X. G. Pan, J. P. Shi, P. Luo, X. G. Wang, X. O. Tang. Spatial as deep: Spatial CNN for traffic scene understanding. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence, New Orleans, USA, pp. 7276–7283, 2018. DOI: 10.1609/aaai.v32i1.12301.
    [6]
    Y. N. Hou, Z. Ma, C. X. Liu, C. C. Loy. Learning lightweight lane detection CNNs by self attention distillation. In Proceedings of IEEE/CVF International Conference on Computer Vision, IEEE, Seoul, Korea, pp. 1013–1021, 2019. DOI: 10.1109/ICCV.2019.00110.
    [7]
    C. Y. Wang, A. Bochkovskiy, H. Y. M. Liao. Scaled-YOLOv4: Scaling cross stage partial network. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Nashville, USA, pp. 13024–13033, 2021. DOI: 10.1109/CVPR46437.2021.01283.
    [8]
    K. M. He, G. Gkioxari, P. Dollár, R. Girshick. Mask R-CNN. In Proceedings of IEEE International Conference on Computer Vision, IEEE, Venice, Italy, pp. 2980–2988, 2017. DOI: 10.1109/ICCV.2017.322.
    [9]
    F. Yu, W. Q. Xian, Y. Y. Chen, F. C. Liu, M. K. Liao, V. Madhavan, T. Darrell. BDD100K: A diverse driving video database with scalable annotation tooling. DOI: 10.48550/arxiv.1805.04687, 2018.
    [10]
    R. Girshick, J. Donahue, T. Darrell, J. Malik. Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Columbus, USA, pp. 580–587, 2014. DOI: 10.1109/CVPR.2014.81.
    [11]
    R. Girshick. Fast R-CNN. In Proceedings of the IEEE International Conference on Computer Vision, IEEE, Santiago, Chile, pp. 1440–1448, 2015. DOI: 10.1109/ICCV.2015.169.
    [12]
    J. F. Dai, Y. Li, K. M. He, J. Sun. R-FCN: Object detection via region-based fully convolutional networks. In Proceedings of the 30th International Conference on Neural Information Processing Systems, Barcelona, Spain, pp. 379–387, 2016.
    [13]
    W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C. Y. Fu, A. C. Berg. SSD: Single shot MultiBox detector. In Proceedings of the 14th European Conference on Computer Vision, Springer, Amsterdam, The Netherlands, pp. 21–37, 2016. DOI: 10.1007/978-3-319-46448-0_2.
    [14]
    J. Redmon, S. Divvala, R. Girshick, A. Farhadi. You only look once: Unified, real-time object detection. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Las Vegas, USA, pp. 779–788, 2016. DOI: 10.1109/CVPR.2016.91.
    [15]
    J. Redmon, A. Farhadi. YOLO9000: Better, faster, stronger. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Honolulu, USA, pp. 6517–6525, 2017. DOI: 10.1109/CVPR.2017.690.
    [16]
    J. Redmon, A. Farhadi. YOLOv3: An incremental improvement. [Online], Availabe: https://arxiv.org/abs/1804.02767, 2018.
    [17]
    J. Long, E. Shelhamer, T. Darrell. Fully convolutional networks for semantic segmentation. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Boston, USA, pp. 3431–3440, 2015. DOI: 10.1109/CVPR.2015.7298965.
    [18]
    H. Y. Han, Y. C. Chen, P. Y. Hsiao, L. C. Fu. Using channel-wise attention for deep CNN based real-time semantic segmentation with class-aware edge information. IEEE Transactions on Intelligent Transportation Systems, vol. 22, no. 2, pp. 1041–1051, 2021. DOI: 10.1109/TITS.2019.2962094.
    [19]
    D. Neven, B. De Brabandere, S. Georgoulis, M. Proesmans, L. Van Gool. Towards end-to-end lane detection: An instance segmentation approach. In Proceedings of IEEE Intelligent Vehicles Symposium, IEEE, Changshu, China, pp. 286–291, 2018. DOI: 10.1109/IVS.2018.8500547.
    [20]
    K. W. Duan, L. X. Xie, H. G. Qi, S. Bai, Q. M. Huang, Q. Tian. Location-sensitive visual recognition with cross-IOU loss. [Online], Available: https://arxiv.org/abs/2104.04899v1, 2021.
    [21]
    M. Teichmann, M. Weber, M. Zöllner, R. Cipolla, R. Urtasun. MultiNet: Real-time joint semantic reasoning for autonomous driving. In Proceedings of IEEE Intelligent Vehicles Symposium, IEEE, Changshu, China, pp. 1013–1020, 2018. DOI: 10.1109/IVS.2018.8500504.
    [22]
    Y. Q. Qian, J. M. Dolan, M. Yang. DLT-Net: Joint detection of drivable areas, lane lines, and traffic objects. IEEE Transactions on Intelligent Transportation Systems, vol. 21, no. 11, pp. 4670–4679, 2020. DOI: 10.1109/TITS.2019.2943777.
    [23]
    J. Zhang, Y. Xu, B. B. Ni, Z. Y. Duan. Geometric constrained joint lane segmentation and lane boundary detection. In Proceedings of the 15th European Conference on Computer Vision, Springer, Munich, Germany, pp. 502–518, 2018. DOI: 10.1007/978-3-030-01246-5_30.
    [24]
    Z. L. Kang, K. Grauman, F. Sha. Learning with whom to share in multi-task feature learning. In Proceedings of the 28th International Conference on International Conference on Machine Learning, Bellevue, USA, pp. 521–528, 2011.
    [25]
    C. Y. Wang, H. Y. M. Liao, Y. H. Wu, P. Y. Chen, J. W. Hsieh, I. H. Yeh. CSPNet: A new backbone that can enhance learning capability of CNN. In Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, IEEE, Seattle, USA, pp. 1571–1580, 2020. DOI: 10.1109/CVPRW50498.2020.00203.
    [26]
    K. M. He, X. Y. Zhang, S. Q. Ren, J. Sun. Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 37, no. 9, pp. 1904–1916, 2015. DOI: 10.1109/TPAMI.2015.2389824.
    [27]
    T. Y. Lin, P. Dollár, R. Girshick, K. M. He, B. Hariharan, S. Belongie. Feature pyramid networks for object detection. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Honolulu, USA, pp. 936–944, 2017. DOI: 10.1109/CVPR.2017.106.
    [28]
    S. Liu, L. Qi, H. F. Qin, J. P. Shi, J. Y. Jia. Path aggregation network for instance segmentation. In Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Salt Lake City, USA, pp. 8759–8768, 2018. DOI: 10.1109/CVPR.2018.00913.
    [29]
    T. Y. Lin, P. Goyal, R. Girshick, K. M. He, P. Dollár. Focal loss for dense object detection. In Proceedings of IEEE International Conference on Computer Vision, IEEE, Venice, Italy, pp. 2999–3007, 2017. DOI: 10.1109/ICCV.2017.324.
    [30]
    Z. H. Zheng, P. Wang, W. Liu, J. Z. Li, R. G. Ye, D. W. Ren. Distance-IoU loss: Faster and better learning for bounding box regression. In Proceedings of the 34th AAAI Conference on Artificial Intelligence, New York, USA, pp. 12993–13000, 2020. DOI: 10.1609/aaai.v34i07.6999.
    [31]
    I. Loshchilov, F. Hutter. SGDR: Stochastic gradient descent with warm restarts. In Proceedings of the 5th International Conference on Learning Representations, Toulon, France, 2017.
    [32]
    K. M. He, X. Y. Zhang, S. Q. Ren, J. Sun. Deep residual learning for image recognition. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Las Vegas, USA, pp. 770–778, 2016. DOI: 10.1109/CVPR.2016.90.
  • 加载中

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Figures(8)  / Tables(8)

    用微信扫码二维码

    分享至好友和朋友圈

    Article Metrics

    Article views (97) PDF downloads(10) Cited by()
    Proportional views
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return