Abstract
This paper presents a real-time robust pedestrian detection algorithm based on Convolutional Neural Network (CNN). With the success of CNN in image recognition, CNN has also been used in pedestrian detection, but these methods are still difficult to use the case of real-time application. The proposed method makes full use of the powerful feature representation and faster recognition ability of CNN to meet the real-time request for pedestrian detection. To do so, we regard the pedestrian detection as a regression problem, and a CNN model is employed to solve it. Since a new loss function is introduced, the training can be completed end-to-end, and the trained CNN can directly map an image to the location and confidence of pedestrian bounding box without feature abstraction. We verify the proposed method on the common pedestrian detection dataset of Caltech, and experimental results show that it owns lower miss rate and higher detection frame rate compared with some popular methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Huang, K., Chen, X., Kang, Y., Tan, N.: Review of intelligent video surveillance. J. Comput
Wang, X.: Intelligent multi-camera video surveillance: a review. Pattern Recognit. Lett. 34(1), 3–19 (2013)
Dollár, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: an evaluation of the state of the art. IEEE Trans. Pattern Anal. Mach. Intell. 34, 212–226 (2012)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp. 886–893 (2005)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)
Ren, S., He, K., Girshick, R., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91–99 (2015)
Dollár, P., Appel, R., Belongie, S., Perona, P.: Fast feature pyramids for object detection. IEEE Trans. Pattern Anal. Mach. Intell. 36(8), 1532–1545 (2014)
Angelova, A., Krizhevsky, A.: Real-time pedestrian detection with deep network cascades. In: European Conference on Computer Vision, pp. 127–141 (2015)
Hosang, J.H., Omran, M., Benenson, R., Schiele, B.: Taking a deeper look at pedestrians. In: IEEE International Conference on Computer Vision, pp. 1305–1312 (2015)
Girshick, R.: Fast R-CNN. In: IEEE International Conference on Computer Vision, pp. 2544–2550 (2015)
Zhang, L., Lin, L., Liang, X., He, K.: Is faster R-CNN doing well for pedestrian detection. In: European Conference on Computer Vision, pp. 702–715 (2016)
Li, J., Liang, X., Shen, S., Xu, T., Yan, S.: Scale-aware fast R-CNN for pedestrian detection. In: European Conference on Computer Vision, pp. 83–596 (2016)
Li, Z., Chen, Z., Wu, Q.M.J., et al.: Real-time pedestrian detection with deep supervision in the wild. SIViP 13(8), 1–9 (2019)
Lu, P., Lu, K., Wang, W., Zhang, J., Chen, P., Wang, B.: Real-time pedestrian detection in monitoring scene based on head model. In: Huang, D.-S., Jo, K.-H., Huang, Z.-K. (eds.) ICIC 2019. LNCS, vol. 11644, pp. 558–568. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-26969-2_53
Acknowledgements
This research work is supported by the National Natural Science Foundation of China under Grant No. 61672024, 61170305 and 60873114, and National Key R&D Program of China (No. 2018YFB0904200 and 2018YFB2100500)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Song, W., Dong, W. (2020). Regression Network for Real-Time Pedestrian Detection. In: Li, K., Li, W., Wang, H., Liu, Y. (eds) Artificial Intelligence Algorithms and Applications. ISICA 2019. Communications in Computer and Information Science, vol 1205. Springer, Singapore. https://doi.org/10.1007/978-981-15-5577-0_63
Download citation
DOI: https://doi.org/10.1007/978-981-15-5577-0_63
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-5576-3
Online ISBN: 978-981-15-5577-0
eBook Packages: Computer ScienceComputer Science (R0)