Abstract
Real-time and accurate traffic object detection is one of the important technologies to support intelligent traffic management. Focusing on the problem of poor detection accuracy in aerial photography scenes of drones, the algorithm of lightweight design and multi-scale feature fusion for traffic object detection based on YOLOv5s (LMF-YOLOv5s) is proposed. First, a lightweight network is designed. Then a fast-spatial pyramid convolution module based on dilated convolution is constructed. Finally, an improved spatial pyramid pooling layer module is introduced before the detection layers of different scales, which can enhance the multi-scale feature fusion ability of the network. The experimental results in the public dataset VisDrone show that the detection accuracy of the proposed method is improved by 7.4% compared with YOLOv5s. The model's parameters are reduced by 67.3%, and the model's size is reduced by 63.2% compared with YOLOv5s.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zhao, P., Hu, H.: Geographical patterns of traffic congestion in growing megacities: big data analytics from Beijing. Cities 92, 164–174 (2019)
Bhaskaranand, M., Gibson, J.D.: Low-complexity video encoding for UAV reconnaissance and surveillance. In: 2011-MILCOM 2011 Military Communications Conference, pp. 1633–1638. IEEE Press, New York (2011)
Madawalagama, S., Munasinghe, N., Dampegama, S.D.P.J., Samarakoon, L.: Low cost aerial mapping with consumer-grade drones. In: 37th Asian Conference on Remote Sensing pp. 1–8 (2016)
Sa, I., Hrabar, S., Corke, P.: Outdoor flight testing of a pole inspection UAV incorporating high-speed vision. In: Mejias, L., Corke, P., Roberts, J. (eds.) Field and Service Robotics, pp. 107–121. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-07488-7_8
El-Sayed, H., Chaqfa, M., Zeadally, S., Puthal, D.: A traffic-aware approach for enabling unmanned aerial vehicles (UAVs) in smart city scenarios. IEEE Access 7, 86297–86305 (2019)
Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580–587. IEEE Press, New York (2014)
Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440–1448. IEEE Press, New York (2015)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, 28. (2015)
Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117–2125. IEEE Press, New York (2017)
Liu, W., et al.: SSD: single shot Multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21–37. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46448-0_2
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, pp. 779–788. IEEE Press, New York (2016)
Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980–2988. IEEE Press, New York (2017)
Zhang, P., Zhong, Y., Li, X.: SlimYOLOv3: narrower, faster and better for real-time UAV applications. In: Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, pp. 37–45. IEEE Press, New York (2019)
Wang, X., Li, W., Guo, W., Cao, K.: SPB-YOLO: an efficient real-time detector for unmanned aerial vehicle images. In: 2021 International Conference on Artificial Intelligence in Information and Communication (ICAIIC), pp. 099–104. IEEE Press, New York (2021)
Sun, W., Dai, L., Zhang, X., Chang, P., He, X.: RSOD: real-time small object detection algorithm in UAV-based traffic monitoring. Appl. Intell. 52(8), 8448–8463 (2021)
Redmon, J., & Farhadi, A.: YOLOv3: An Incremental Improvement. arXiv preprint arXiv:18 04.02767 (2018)
Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: YOLOv4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)
Wang, K., Liew, J.H., Zou, Y., Zhou, D., Feng, J.: PANet: few-shot image semantic segmentation with prototype alignment. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9197–9206. IEEE Press, New York (2019)
He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1904–1916 (2015)
Benjumea, A., Teeti, I., Cuzzolin, F., & Bradley, A.: YOLO-Z: improving small object detection in YOLOv5 for autonomous vehicles. arXiv preprint arXiv:2112.11798 (2021)
Zhu P, Du D, Wen L, et al.: VisDrone-VID2019: the vision meets drone object detection in video challenge results. In: Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, pp. 227–235. IEEE Press, New York (2019)
Ghiasi, G., Lin, T.Y., Le, Q.V.: NAS-FPN: learning scalable feature pyramid architecture for object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7029–7038. IEEE Press, New York (2019)
Li, C., Yang, T., Zhu, S., Chen, C., Guan, S.: Density map guided object detection in aerial images. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 737–746. IEEE Press, New York (2020)
Yang, F., Fan, H., Chu, P., Blasch, E., Ling, H.: Clustered object detection in aerial images. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 8311–8320. IEEE Press, New York (2019)
Acknowledgments
This work was supported by the National Key R&D Program Funding Project (No. 2020YFC1512601); Hefei Natural Science Foundation Project (No. 2022015).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Ma, X., Zhou, T., Ma, J., Jiang, G., Xu, X. (2022). UAV Aerial Photography Traffic Object Detection Based on Lightweight Design and Feature Fusion. In: Deng, W., et al. Biometric Recognition. CCBR 2022. Lecture Notes in Computer Science, vol 13628. Springer, Cham. https://doi.org/10.1007/978-3-031-20233-9_69
Download citation
DOI: https://doi.org/10.1007/978-3-031-20233-9_69
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20232-2
Online ISBN: 978-3-031-20233-9
eBook Packages: Computer ScienceComputer Science (R0)