Abstract
In order to solve the problems of insufficient accuracy of pedestrian bounding boxes in person search and large-scale person matching. A novel person search framework is proposed, which includes: (1) A multi-layer cascade heatmap mechanism (MCHM) is proposed, which aggregates pedestrian features by multi-layer heatmaps cascaded and improves the accuracy of the pedestrian bounding box by optimizating the offset between the center of the bounding box and the center point. (2) A learnable part-based pedestrian feature weight calculation module is proposed, which can learn the weight of the part according to the importance of the part-based feature instead of manually set hyperparameters. (3) A group feature correlation graph convolution network (GFCGCN) is proposed, which can calculate the similarity between group pedestrian features and provide a more accuracy end to end person search work. Some ablation studies and comparative experiments on datasets CUHK-SYSU, PRW show that our model can effectively achieve more accuracy pearch search with accuracy of 88.7% rank-1 and 78.2% mAP.
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
Wu, D., Zhang, K., Zheng, S.J., et al.: Random occlusion recovery for person re-identification. J. Imaging Sci. Technol. 63(3), 30405-1–30405-9 (2019)
Wu, Q., Dai, P., Chen, P., et al.: Deep adversarial data augmentation with attribute guided for person re-identification. Signal Image Video Process. 1–8 (2019). https://doi.org/10.1007/s11760-019-01523-3
Liu, H., Feng, J., Jie, Z., et al.: Neural person search machines. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 493–501 (2017)
Zheng, L., Zhang, H., Sun, S., et al.: Person re-identification in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1367–1376 (2017)
Guo, S., Bai, Q., Zhou, X.: Foreign object detection of transmission lines based on faster R-CNN. In: Kim, K.J., Kim, H.-Y. (eds.) Information Science and Applications. LNEE, vol. 621, pp. 269–275. Springer, Singapore (2020). https://doi.org/10.1007/978-981-15-1465-4_28
Lin, T.Y., Goyal, P., Girshick, R., et al.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980–2988 (2017)
Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7263–7271 (2017)
Durkee, M.S., Sibley, A., Ai, J., et al.: Improved instance segmentation of immune cells in human lupus nephritis biopsies with Mask R-CNN. In: Medical Imaging 2020: Digital Pathology, vol. 11320, p. 1132019. International Society for Optics and Photonics (2020)
Jiang, H., Li, S., Liu, W., et al.: Geometry-aware cell detection with deep learning. MSystems 5(1) (2020)
Hasan, I., Tsesmelis, T., Galasso, F., et al.: Tiny head pose classification by bodily cues. In: 2017 IEEE International Conference on Image Processing (ICIP), pp. 2662–2666. IEEE (2017)
Xiao, J., Xie, Y., Tillo, T., et al.: IAN: the individual aggregation network for person search. Pattern Recogn. 87, 332–340 (2019)
Jiang, M., Li, C., Kong, J., et al.: Cross-level reinforced attention network for person re-identification. J. Vis. Commun. Image Represent. 102775 (2020)
Şerbetçi, A., Akgül, Y.S.: End-to-end training of CNN ensembles for person re-identification. Pattern Recognit. 107319 (2020)
Zhao, C., Lv, X., Zhang, Z., et al.: Deep fusion feature representation learning with hard mining center-triplet loss for person re-identification. IEEE Trans. Multimedia (2020)
Zhang, C., Yue, J., Qin, Q.: Deep quadruplet network for hyperspectral image classification with a small number of samples. Remote Sens. 12(4), 647 (2020)
Ye, M., Shen, J., Lin, G., et al.: Deep Learning for Person Re-identification: A Survey and Outlook. arXiv preprint arXiv:2001.04193 (2020)
Xiao, T., Li, S., Wang, B., et al.: Joint detection and identification feature learning for person search. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3415–3424 (2017)
Zhu, X., Chen, C., Zheng, B., et al.: Automatic recognition of lactating sow postures by refined two-stream RGB-D faster R-CNN. Biosyst. Eng. 189, 116–132 (2020)
Mai, X., Zhang, H., Jia, X., et al.: Faster R-CNN with classifier fusion for automatic detection of small fruits. IEEE Trans. Autom. Sci. Eng. (2020)
Zhou, J., Chen, B., Zhang, J., et al.: Multi-scales feature integration single shot multi-box detector on small object detection. In: MIPPR 2019: Pattern Recognition and Computer Vision, vol. 11430, p. 114300E. International Society for Optics and Photonics (2020)
Law, H., Deng, J.: Cornernet: detecting objects as paired keypoints. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 734–750 (2018)
Duan, K., Bai, S., Xie, L., et al.: Centernet: keypoint triplets for object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 6569–6578 (2019)
Zhao, R., Ouyang, W., Wang, X.: Unsupervised salience learning for person re-identification. In: CVPR, pp. 3586–3593 (2013)
Kostinger, M., Hirzer, M., Wohlhart, P., Roth, P.M., Bischof, H.: Large scale metric learning from equivalence constraints. In: CVPR, pp. 2288–2295 (2012)
Ktena, S.I., et al.: Distance metric learning using graph convolutional networks: application to functional brain networks. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10433, pp. 469–477. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-66182-7_54
He, Z., Zhang, L.: End-to-end detection and re-identification integrated net for person search. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11362, pp. 349–364. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-20890-5_23
Acknowledgments
This research is supported by National Natural Science Foundation of China (61972183, 61672268) and National Engineering Laboratory Director Foundation of Big Data Application for Social Security Risk Perception and Prevention.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Liu, Q., Cheng, K., Wu, B. (2020). Person Search via Anchor-Free Detection and Part-Based Group Feature Similarity Estimation. In: Peng, Y., et al. Pattern Recognition and Computer Vision. PRCV 2020. Lecture Notes in Computer Science(), vol 12306. Springer, Cham. https://doi.org/10.1007/978-3-030-60639-8_21
Download citation
DOI: https://doi.org/10.1007/978-3-030-60639-8_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-60638-1
Online ISBN: 978-3-030-60639-8
eBook Packages: Computer ScienceComputer Science (R0)