Abstract
As pedestrian detection plays a critical role in various real-world applications, real-time processing becomes a natural demand. However, the existing pedestrian detectors either are far from being real-time or fall behind in performance. From our observation, two-stage detectors yield stronger performance but their speed is limited by the propose-then-refine pipeline; Current single-stage detectors are significantly faster yet haven’t addressed the occlusion problem in the pedestrian detection task, which leads to poor performance. Thus, we propose FastNFusion, which enjoys the merit of anchor-free single-stage detectors and mitigates the occlusion problem by fusing head features into the body features using body-head offset since heads suffer from occlusion more rarely. Particularly, our body-head fusion module introduces marginal computational overhead, which enables the real-time processing. In addition, we design an auxiliary training task to further boost the learning of full-body bounding box and body-head offset prediction, which is cost-free during inference. As a result, FastNFusion improves the \(\hbox {MR}^{-2}\) by 3.6% to 41.77% on the CrowdHuman dataset, which is state-of-the-art, while runs at 16.8 fps on single Tesla P40.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
In this paper, we consider real-time as over 15 fps.
References
Bodla, N., Singh, B., Chellappa, R., Davis, L.S.: Soft-nms-improving object detection with one line of code. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5561–5569 (2017)
Cai, Z., Vasconcelos, N.: Cascade r-cnn: delving into high quality object detection. In: CVPR, pp. 6154–6162 (2018)
Chi, C., Zhang, S., Xing, J., Lei, Z., Li, S.Z., Zou, X.: Pedhunter: occlusion robust pedestrian detector in crowded scenes. arXiv preprint arXiv:1909.06826 (2019)
Chi, C., Zhang, S., Xing, J., Lei, Z., Li, S.Z., Zou, X.: Relational learning for joint head and human detection. arXiv preprint arXiv:1909.10674 (2019)
Chu, X., Zheng, A., Zhang, X., Sun, J.: Detection in crowded scenes: one proposal, multiple predictions. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)
Dai, J., et al.: Deformable convolutional networks. In: ICCV, pp. 764–773 (2017)
Girshick, R.: Fast r-cnn. In: CVPR, pp. 1440–1448 (2015)
He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask r-cnn. In: ICCV, pp. 2961–2969 (2017)
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)
He, Y., Zhu, C., Wang, J., Savvides, M., Zhang, X.: Bounding box regression with uncertainty for accurate object detection. In: CVPR, pp. 2888–2897 (2019)
Huang, X., Ge, Z., Jie, Z., Yoshie, O.: Nms by representative region: towards crowded pedestrian detection by proposal pairing. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10750–10759 (2020)
Jaderberg, M., Simonyan, K., Zisserman, A., et al.: Spatial transformer networks. In: NIPS, pp. 2017–2025 (2015)
Law, H., Deng, J.: Cornernet: detecting objects as paired keypoints. In: ECCV, pp. 734–750 (2018)
Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR, pp. 2117–2125 (2017)
Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. In: CVPR, pp. 2980–2988 (2017)
Liu, S., Huang, D., Wang, Y.: Adaptive NMS: refining pedestrian detection in a crowd. In: CVPR, pp. 6459–6468 (2019)
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
Liu, W., Liao, S., Hu, W., Liang, X., Chen, X.: Learning efficient single-stage pedestrian detectors by asymptotic localization fitting. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 618–634 (2018)
Liu, W., Liao, S., Ren, W., Hu, W., Yu, Y.: High-level semantic feature detection: a new perspective for pedestrian detection. In: CVPR, pp. 5187–5196 (2019)
Lu, R., Ma, H.: Semantic head enhanced pedestrian detection in a crowd. arXiv preprint arXiv:1911.11985 (2019)
Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 483–499. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46484-8_29
Pang, Y., Xie, J., Khan, M.H., Anwer, R.M., Khan, F.S., Shao, L.: Mask-guided attention network for occluded pedestrian detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4967–4975 (2019)
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: CVPR, pp. 779–788 (2016)
Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. In: CVPR, pp. 7263–7271 (2017)
Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)
Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. In: NIPS, pp. 91–99 (2015)
Shao, S., et al.: Crowdhuman: a benchmark for detecting human in a crowd. arXiv preprint arXiv:1805.00123 (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: Proceedings of the European Conference on Computer Vision (ECCV), pp. 536–551 (2018)
Tian, Y., Luo, P., Wang, X., Tang, X.: Deep learning strong parts for pedestrian detection. In: CVPR, pp. 1904–1912 (2015)
Tian, Z., Shen, C., Chen, H., He, T.: Fcos: fully convolutional one-stage object detection. In: ICCV (2019)
Wang, X., Xiao, T., Jiang, Y., Shao, S., Sun, J., Shen, C.: Repulsion loss: detecting pedestrians in a crowd. In: CVPR, pp. 7774–7783 (2018)
Xiao, B., Wu, H., Wei, Y.: Simple baselines for human pose estimation and tracking. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 466–481 (2018)
Xie, J., Pang, Y., Cholakkal, H., Anwer, R.M., Khan, F.S., Shao, L.: Psc-net: learning part spatial co-occurence for occluded pedestrian detection. arXiv preprint arXiv:2001.09252 (2020)
Yu, F., Wang, D., Shelhamer, E., Darrell, T.: Deep layer aggregation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2403–2412 (2018)
Zhang, K., Xiong, F., Sun, P., Hu, L., Li, B., Yu, G.: Double anchor r-cnn for human detection in a crowd. arXiv preprint arXiv:1909.09998 (2019)
Zhang, S., Benenson, R., Omran, M., Hosang, J., Schiele, B.: How far are we from solving pedestrian detection? In: CVPR, pp. 1259–1267 (2016)
Zhang, S., Benenson, R., Schiele, B.: Citypersons: a diverse dataset for pedestrian detection. In: CVPR, 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: Proceedings of the European Conference on Computer Vision (ECCV), pp. 637–653 (2018)
Zhou, C., Yuan, J.: Bi-box regression for pedestrian detection and occlusion estimation. In: ECCV, pp. 135–151 (2018)
Zhou, P., et al.: Noh-nms: Improving pedestrian detection by nearby objects hallucination. arXiv preprint arXiv:2007.13376 (2020)
Zhou, X., Wang, D., Krähenbühl, P.: Objects as points. arXiv preprint arXiv:1904.07850 (2019)
Acknowledgements
This work was supported in part by the Zhejiang Provincial Natural Science Foundation of China (No. LY21F020019) and in part by the National Science Foundation of China under Grants 61802100,61971172 and 61971339. This work was also supported in part by the China Post-Doctoral Science Foundation under Grant 2019M653563.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Huang, J., Gu, X., Liu, X., Peng, P. (2021). Fast and Fusion: Real-Time Pedestrian Detector Boosted by Body-Head Fusion. In: Ma, H., et al. Pattern Recognition and Computer Vision. PRCV 2021. Lecture Notes in Computer Science(), vol 13019. Springer, Cham. https://doi.org/10.1007/978-3-030-88004-0_6
Download citation
DOI: https://doi.org/10.1007/978-3-030-88004-0_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-88003-3
Online ISBN: 978-3-030-88004-0
eBook Packages: Computer ScienceComputer Science (R0)