Abstract
Pedestrian attributes recognition is a very important problem in video surveillance and video forensics. Traditional methods assume the pedestrian attributes are independent and design handcraft features for each one. In this paper, we propose a joint hierarchical multi-task learning algorithm to learn the relationships among attributes for better recognizing the pedestrian attributes in still images using convolutional neural networks (CNN). We divide the attributes into local and global ones according to spatial and semantic relations, and then consider learning semantic attributes through a hierarchical multi-task CNN model where each CNN in the first layer will predict each group of such local attributes and CNN in the second layer will predict the global attributes. Our multi-task learning framework allows each CNN model to simultaneously share visual knowledge among different groups of attribute categories. Extensive experiments are conducted on two popular and challenging benchmarks in surveillance scenarios, namely, the PETA and RAP pedestrian attributes datasets. On both benchmarks, our framework achieves superior results over the state-of-the-art methods by 88.2\(\%\) on PETA and 83.25\(\%\) on RAP, respectively.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Lin, Y.T., Liang, Z., Zeng, Z.D.: Improving person re-identification by attribute and identity learning, arXiv preprint arXiv:1703.07220 (2017)
Tian, Y., Luo, P., Wang, X.: Pedestrian detection aided by deep learning semantic task. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 5079–5087 (2015)
Vaquero, D.A., Feris, R.S., Duan, T.: Attribute-based people search in surveillance environments. In: Proceedings of IEEE Workshop on Applications of Computer Vision, pp. 1–8 (2009)
Deng, Y., Luo, P., Chen, C.: Pedestrian attribute recognition at far distance. In: Proceedings of ACM International Conference on Multimedia, pp. 789–792 (2014)
Zhu, J., Liao, S., Lei, Z.: Pedestrian attribute classification in surveillance: database and evaluation. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 331–338 (2013)
Bourdev, L., Maji, S., Malik, J.: Describing people: a poselet-based approach to attribute classification. In: Proceedings of IEEE International Conference on Computer Vision, pp. 1543–1550 (2012)
Dangei, L., Zhang, Z., Tang, C.X.: A richly annotated dataset for pedestrian attribute recognition, arXiv preprint arXiv:1603.07054 (2016)
Layne, R., Hospedaes, T.M., Gong, S.G.: Person Re-identification by attributes. In: British Machine Vision Conference (2012)
He, K., Zhang, X., Ren, S.Q.: Deep residual learning for image recognition. In: Proceedings of IEEE Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Bengio, Y., Courville, A., Vincent, P.: Representation learning: a review and new perspectives. IEEE Trans. Patt. Anal. Mach. Intell. 35(8), 1798–828 (2013)
Jayaraman, D., Fei, S., Grauman, K.: Decorrelating semantic visual attributes by resisting the urge to share. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1629–1636. IEEE Computer Society (2014)
Zhu, J., Liao, S., Yi, D.: Multi-label CNN based pedestrian attribute learning for soft biometrics. In: Proceedings of the IEEE International Conference on Biometrics, pp. 535–540 (2015)
Yu, K., Leng, B., Zhang, Z.: Weakly-supervised learning of mid-level features for pedestrian attribute recognition and localization, arXiv preprint arXiv:1611.05603 (2016)
Emily, M.H., Rama, C.B.: Attributes for improved attributes: a multi-task network utilizing implicit and explicit relationships for facial attribute classification. In: Proceedings of AAAI Conference on Artificial Intelligence, pp. 4068–4074 (2017)
Sudowe, P., Spitzer, H., Leibe, B.: Person attribute recognition with a jointly-Trained holistic CNN model. In: Proceedings of IEEE International Conference on Computer Vision Workshop, pp. 329–337 (2015)
Zhu, J., Liao, S., Lei, Z.: Multi-label convolutional neural network based pedestrian attribute classification. Image Vis. Comput. 58, 224–229 (2016)
Acknowledgment
This research is based upon work supported by National Nature Science Founda- tion of China (No. U1736206),National Nature Science Foundation of China(61671336), National Nature Science Foundation of China(61671332),Technology Research Program of Ministry of Public Security (No. 2016JSYJA12),Hubei Province Technological Innovation Major Project(No. 2016AAA015),Hubei Province Tech- nological Innovation Major Project2017AAA123),The National Key Research and Development Program of China(No.2016YFB0100901),Nature Science Foun- dation of Jiangsu Province (No. BK20160386) and National Nature Science Foundation of China(61502354).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Fang, W., Chen, J., Lu, T., Hu, R. (2018). Pedestrian Attributes Recognition in Surveillance Scenarios with Hierarchical Multi-task CNN Models. In: Hong, R., Cheng, WH., Yamasaki, T., Wang, M., Ngo, CW. (eds) Advances in Multimedia Information Processing – PCM 2018. PCM 2018. Lecture Notes in Computer Science(), vol 11165. Springer, Cham. https://doi.org/10.1007/978-3-030-00767-6_70
Download citation
DOI: https://doi.org/10.1007/978-3-030-00767-6_70
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-00766-9
Online ISBN: 978-3-030-00767-6
eBook Packages: Computer ScienceComputer Science (R0)