Abstract
Pedestrian detection algorithms based on deep learning often rely on high-performance image processing platforms, and it does not adapt to high portability requirements of practical engineering. In order to solve the problem, an improved approach is proposed, which can be applied to embedded platforms. Firstly, reinforcing dense connectivity is adopted to connect the multiple layer features. Then the k-means++ algorithm is used to cluster the pedestrian targets, and the method of eliminating duplicate detection is optimized. Finally, the detection model is obtained through multi-scale training. Experiment results show that Dense-YOLOv3-tiny can detect pedestrian on UAV imagery in real time and exhibit higher precision and recall rate than the YOLOv3-tiny model in the embedded platforms.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zhang, S.S., Benenson, R., Omarn, M., Hosang, J.: How far are we from solving pedestrian detection. In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, pp. 1259–1267. IEEE Computer Society (2016)
Benenson, R., Omarn, M., Hosang, J., Schiele, B.: Ten years of pedestrian detection, what have we learned? In: Proceedings European Conference on Computer Vision, Zurich, Switzerland, pp. 613–627 (2014)
Shrestha, A., Mahmood, A.: Review of deep learning algorithms and architectures. IEEE Access 7, 53040–53065 (2019)
Lecun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521, 436–444 (2015)
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, Columbus, Ohio, USA, pp. 580–587. IEEE Computer Society (2014)
Girshick, R.: Fast R-CNN. In: 15th IEEE International Conference on Computer Vision, Santiago, Chile, pp. 1440–1448. Institute of Electrical and Electronics Engineers Inc. (2015)
Ren, S.Q., He, K.M., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Proceedings of the IEEE Transactions on Pattern Analysis and Machine Intelligence, Hawaii, HL, USA, vol. 39, pp. 1137–1149. IEEE Computer Society (2017)
Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)
Gao, H., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, pp. 2261–2269. Institute of Electrical and Electronics Engineers Inc., (2017)
Arthur, D., Vassilvitskii, S.: k-means++: the advantages of careful seeding. In: 18th Annual ACM-SIAM Symposium on Discrete Algorithms, New Orleans, LA, USA, January 2007, pp. 1027–1035. Association for Computing Machinery (2007)
Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: 30th IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, January 2017, pp. 6517–6525. Institute of Electrical and Electronics Engineers Inc., (2017)
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, Las Vegas, NV, USA, December 2016, pp. 779–788. IEEE Computer Society (2016)
Bodla, N., Singh, B., Chellappa, R., Davis, L.S.: Soft-NMS-improving object detection with one line of code. In: Proceedings IEEE International Conference on Computer Vision, Venice, Italy, October 2017, pp. 5562–5570. Institute of Electrical and Electronics Engineers Inc., (2017)
Acknowledgments
This work is supported by the National Natural Science Foundation of China (61571346). The research is also supported by the Fundamental Research Funds for the Central Universities and the Innovation Fund of Xidian University.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Yang, Y., Guo, B., Li, C., Zhi, Y. (2020). An Improved YOLOv3 Algorithm for Pedestrian Detection on UAV Imagery. In: Pan, JS., Lin, JW., Liang, Y., Chu, SC. (eds) Genetic and Evolutionary Computing. ICGEC 2019. Advances in Intelligent Systems and Computing, vol 1107. Springer, Singapore. https://doi.org/10.1007/978-981-15-3308-2_29
Download citation
DOI: https://doi.org/10.1007/978-981-15-3308-2_29
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-3307-5
Online ISBN: 978-981-15-3308-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)