Abstract
Pedestrian detection under occlusion scenes remains a formidable challenge in computer vision. Recently, anchor-free approach has been raised on the object detection and pedestrian detection field, anchor-free detector Center and Scale Prediction (CSP) has been proposed in pedestrian detection without special measures for occlusion. In this paper, we propose an anchor-free detector named OCSP with power ful occlusion handling ability to existing anchor-free detection network. OCSP integrates prior information into the network to handle occlusion. This high-fusion prior information gives the detector a hint about identifying the structural features of pedestrians. OCSP becomes more robust with the prior information which fusion the semantic head, the visible part, and the size and center body for each pedestrian. The detector enhances the perception of occlusion by predicting the semantic head and visible part. Besides, we design a head branch and add predicting the visible box to achieve a similar result. Experiments show that this fusion of prior information represents a suitable combination. We compare our OCSP with state-of-arts models on the Citypersons dataset, the proposed OCSP detector achieves the state-of-arts result on the CityPersons benchmark.
Keywords
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Cai, J., et al.: Pedestrian as points: an improved anchor-free method for center-based pedestrian detection. IEEE Access 8, 179666–179677 (2020)
Chi, C., Zhang, S., Xing, J., Lei, Z., Li, S.Z., Zou, X.: PedHunter: occlusion robust pedestrian detector in crowded scenes. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 10639–10646 (2020)
Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3213–3223 (2016)
Dollar, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: an evaluation of the state of the art. IEEE Trans. Pattern Anal. Mach. Intell. 34(4), 743–761 (2011)
Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440–1448 (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, pp. 580–587 (2014)
He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1026–1034 (2015)
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, pp. 770–778 (2016)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448–456. PMLR (2015)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Law, H., Deng, J.: CornerNet: detecting objects as paired keypoints. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision – ECCV 2018. LNCS, vol. 11218, pp. 765–781. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01264-9_45
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 (2017)
Liu, W., Liao, S., Hu, W., Liang, X., Chen, X.: Learning efficient single-stage pedestrian detectors by asymptotic localization fitting. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision – ECCV 2018. LNCS, vol. 11218, pp. 643–659. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01264-9_38
Liu, W., Liao, S., Ren, W., Hu, W., Yu, Y.: High-level semantic feature detection: A new perspective for pedestrian detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5187–5196 (2019)
Lu, R., Ma, H., Wang, Y.: Semantic head enhanced pedestrian detection in a crowd. Neurocomputing 400, 343–351 (2020)
Paszke, A., et al.: Automatic differentiation in PyTorch (2017)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: Towards real-time object detection with region proposal networks. arXiv preprint arXiv:1506.01497 (2015)
Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211–252 (2015)
Sha, M., Boukerche, A.: Semantic fusion-based pedestrian detection for supporting autonomous vehicles. In: 2020 IEEE Symposium on Computers and Communications (ISCC), pp. 1–6. IEEE (2020)
Shang, C., Ai, H., Zhuang, Z., Chen, L., Xing, J.: ZoomNet: deep aggregation learning for high-performance small pedestrian detection. In: Asian Conference on Machine Learning, pp. 486–501. PMLR (2018)
Song, T., Sun, L., Xie, D., Sun, H., Pu, S.: Small-scale pedestrian detection based on topological line localization and temporal feature aggregation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 554–569. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_33
Tarvainen, A., Valpola, H.: Weight-averaged, consistency targets improve semi-supervised deep learning results. CoRR vol. abs/1703 2017 (1780)
Ujjwal, U., Dziri, A., Leroy, B., Bremond, F.: A one-and-half stage pedestrian detector. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 776–785 (2020)
Wang, W.: Adapted center and scale prediction: more stable and more accurate. arXiv preprint arXiv:2002.09053 (2020)
Xie, J., Pang, Y., Cholakkal, H., Anwer, R., Khan, F., Shao, L.: PSC-Net: learning part spatial co-occurrence for occluded pedestrian detection. Sci. China Inf. Sci. 64(2), 1–13 (2021)
Zhang, H., et al.: ResNeSt: split-attention networks. arXiv preprint arXiv:2004.08955 (2020)
Zhang, J., et al.: Attribute-aware pedestrian detection in a crowd. IEEE Trans. Multimedia 23, 3085–3097 (2020)
Zhang, S., Benenson, R., Schiele, B.: CityPersons: a diverse dataset for pedestrian detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3213–3221 (2017)
Zhang, S., Wen, L., Bian, X., Lei, Z., Li, S.Z.: Occlusion-aware R-CNN: detecting pedestrians in a crowd. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 657–674. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01219-9_39
Zhou, X., Wang, D., Krähenbühl, P.: Objects as points. arXiv preprint arXiv:1904.07850 (2019)
Acknowledgments
This work was supported by the National Nature Science Foundation of China (61841602, 61806024), the Jilin Province Education Department Scientific Research Planning Foundation of China (JJKH20210753KJ, JJKH20200618KJ).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, H., Zhang, Y., Ke, H., Wei, N., Xu, Z. (2021). Semantic Structural and Occlusive Feature Fusion for Pedestrian Detection. In: Pham, D.N., Theeramunkong, T., Governatori, G., Liu, F. (eds) PRICAI 2021: Trends in Artificial Intelligence. PRICAI 2021. Lecture Notes in Computer Science(), vol 13031. Springer, Cham. https://doi.org/10.1007/978-3-030-89188-6_22
Download citation
DOI: https://doi.org/10.1007/978-3-030-89188-6_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-89187-9
Online ISBN: 978-3-030-89188-6
eBook Packages: Computer ScienceComputer Science (R0)