Abstract
CNN-based detectors have achieved great success in pedestrian detection. However, poor localization of bounding boxes leads to high false positive detection errors to a large degree. This paper gives insight into reducing localization errors and better performing bounding box regression. We propose a novel loss named ComLoss to enforce predicted bounding boxes with the same designated target ground truth box to locate more compactly around the target, which minimizes the internal region distances of these predicted boxes to some extent. Evaluations on both CityPersons and Caltech dataset show the effectiveness of our method: (1) ComLoss yields an absolute 1.05% and 0.60% miss rate improvement on these two datasets respectively. (2) By adding ComLoss during training, our baseline detector achieves competitive results compared to state-of-the-arts on both datasets.
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
References
Brazil, G., Yin, X., Liu, X.: Illuminating pedestrians via simultaneous detection & segmentation. In: The IEEE International Conference on Computer Vision (ICCV), October 2017
Cai, Z., Fan, Q., Feris, R.S., Vasconcelos, N.: A unified multi-scale deep convolutional neural network for fast object detection. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 354–370. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_22
Dollár, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: a benchmark. In: CVPR, June 2009
Girshick, R.: Fast R-CNN. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1440–1448, December 2015. https://doi.org/10.1109/ICCV.2015.169
Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 580–587, June 2014. https://doi.org/10.1109/CVPR.2014.81
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778, June 2016. https://doi.org/10.1109/CVPR.2016.90
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)
Lin, C., Lu, J., Wang, G., Zhou, J.: Graininess-aware deep feature learning for pedestrian detection. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 745–761. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01240-3_45
Lin, T., Dollár, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 936–944, July 2017. https://doi.org/10.1109/CVPR.2017.106
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: 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
Pang, Y., Xie, J., Khan, M.H., Anwer, R.M., Khan, F.S., Shao, L.: Mask-guided attention network for occluded pedestrian detection. In: ICCV, October 2019
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: Towards real-time object detection with region proposal networks. In: Cortes, C., Lawrence, N.D., Lee, D.D., Sugiyama, M., Garnett, R. (eds.) Advances in Neural Information Processing Systems, VOL. 28, pp. 91–99. Curran Associates, Inc. (2015). http://papers.nips.cc/paper/5638-faster-r-cnn-towards-real-time-object-detection-with-region-proposal-networks.pdf
Tian, Y., Luo, P., Wang, X., Tang, X.: Deep learning strong parts for pedestrian detection. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1904–1912, December 2015. https://doi.org/10.1109/ICCV.2015.221
Wang, X., Xiao, T., Jiang, Y., Shao, S., Sun, J., Shen, C.: Repulsion loss: detecting pedestrians in a crowd. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018
Yu, J., Jiang, Y., Wang, Z., Cao, Z., Huang, T.S.: Unitbox: an advanced object detection network. CoRR abs/1608.01471 (2016). http://arxiv.org/abs/1608.01471
Zhang, L., Lin, L., Liang, X., He, K.: Is faster R-CNN doing well for pedestrian detection? (2016)
Zhang, S., Benenson, R., Omran, M., Hosang, J., Schiele, B.: How far are we from solving pedestrian detection? In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016
Zhang, S., Benenson, R., Schiele, B.: Citypersons: a diverse dataset for pedestrian detection. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017
Zhang, S., Yang, J., Schiele, B.: Occluded pedestrian detection through guided attention in CNNs. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018
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, C., Yang, M., Yuan, J.: Discriminative feature transformation for occluded pedestrian detection. In: ICCV, October 2019
Zhou, C., Yuan, J.: Multi-label learning of part detectors for heavily occluded pedestrian detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3486–3495 (2017)
Zhou, C., Yuan, J.: Bi-box regression for pedestrian detection and occlusion estimation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 138–154. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01246-5_9
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
Song, X., Feng, J., Du, T., Zhang, H. (2022). ComLoss: A Novel Loss Towards More Compact Predictions for Pedestrian Detection. In: Yu, S., et al. Pattern Recognition and Computer Vision. PRCV 2022. Lecture Notes in Computer Science, vol 13537. Springer, Cham. https://doi.org/10.1007/978-3-031-18916-6_30
Download citation
DOI: https://doi.org/10.1007/978-3-031-18916-6_30
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-18915-9
Online ISBN: 978-3-031-18916-6
eBook Packages: Computer ScienceComputer Science (R0)