Abstract
In the world of security and surveillance, it is very common to localize the person in the video. The localization turns to be non-trivial when the search is based on a linguistic query. This is due to the semantic gap between language based query and its processing by a machine. Typically query uses attributes like height, cloth color, cloth type, gender, and hair color, e.g., a tall male with a black t-shirt and pink short. Such attributes are known as soft biometrics. Conventionally, searching the person in the surveillance video is done manually by scouring through hours of videos, which is inefficient and time-consuming. Thus, an automatic person retrieval algorithm is an active area of research.
The chapter discusses automatic person retrieval algorithm using soft biometric attributes namely height, cloth color, gender. The algorithm uses Mask R-CNN for detection and semantic segmentation of the person. This removes background clutter and allows a precise color patch extraction for better classification. The algorithm uses the geometric model for height classification while color and gender models are built using the AlexNet: a deep neural network. The proposed algorithm is tested on the AVSS 2018 challenge II dataset and it analyzes person retrieval in challenging conditions.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
A. Dantcheva, C. Velardo, A. D’Angelo, J.L. Dugelay, Bag of soft biometrics for person identification. Multimed. Tools Appl. 51(2), 739–77 (2011)
A. Dantcheva, P. Elia, A. Ross, What else does your biometric data reveal? a survey on soft biometrics. IEEE Trans. Inf. Forensics Secur. 11(3), 441–67 (2016)
J. Deng, W. Dong, R. Socher, L.J. Li, K. Li, L. Fei-Fei, ImageNet: a large-scale hierarchical image database, in IEEE Conference on 2009 Computer Vision and Pattern Recognition, CVPR (IEEE, Piscataway, 2009), pp. 248–255
Y. Deng, P. Luo, C.C. Loy, X. Tang, Pedestrian attribute recognition at far distance, in Proceedings of the 22nd ACM international conference on Multimedia (ACM, New York, 2014), pp. 789–792
S. Denman, M. Halstead, C. Fookes, S. Sridharan, Searching for people using semantic soft biometric descriptions. Pattern Recogn. Lett. 68, 306–315 (2015)
H. Galiyawala, K. Shah, V. Gajjar, M.S. Raval, Person retrieval in surveillance video using height, color, and gender, in 15th IEEE International Conference on Advanced Video and Signal based Surveillance (AVSS) (IEEE, New Zealand 2018)
D. Gray, S. Brennan, H. Tao, Evaluating appearance models for recognition, reacquisition, and tracking. In Proceedings of IEEE International Workshop on Performance Evaluation for Tracking and Surveillance (PETS), vol. 3, no. 5, (2007), pp. 1–7. Citeseer
M. Halstead, S. Denman, S. Sridharan, C.B. Fookes, Locating people in video from semantic descriptions: a new database and approach, in Proceedings of the 22nd International Conference on Pattern Recognition (IEEE, Piscataway, 2014), pp. 4501–4506
M. Halstead, S. Denman, C. Fookes, Y. Tian, M. Nixon, Semantic person retrieval in surveillance using soft biometrics: AVSS 2018 challenge II, in IEEE International Conference on Advanced Video and Signal based Surveillance (AVSS) (IEEE, New Zealand, 2018)
K. He, G. Gkioxari, P. Dollar, R. Girshick, Mask R-CNN, in 2017 IEEE International Conference on Computer Vision (ICCV) (IEEE, Piscataway, 2017), pp. 2980–2988
A.K. Jain, S.C. Dass, K. Nandakumar, Soft biometric traits for personal recognition systems, in International Conference on Biometric Authentication (ICBA) (Springer, Berlin, 2004), pp. 731–738
A. Krizhevsky, I. Sutskever, G.E. Hinton, ImageNet classification with deep convolutional neural networks, in Advances in Neural Information Processing Systems (2012), pp. 1097–1105
R. Layne, T.M. Hospedales, S. Gong, Q. Mary, Person re-identification by attributes. In BMVC, vol. 2, no. 3, (2012), p. 8
D. Li, X. Chen, K. Huang, Multi-attribute learning for pedestrian attribute recognition in surveillance scenarios, in 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR), (IEEE, Piscataway, 2015), pp. 111–115
D. Li, Z. Zhang, X. Chen, K. Huang, A richly annotated pedestrian dataset for person retrieval in real surveillance scenarios. IEEE Trans. Image Process. 28(4), 1575–1590 (2019)
T.Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollar, C.L. Zitnick, Microsoft coco: common objects in context, in European Conference on Computer Vision (Springer, Cham, 2014), pp. 740–755
C. Liu, S. Gong, C.C. Loy, X. Lin, Person re-identification: what features are important?, in European Conference on Computer Vision (Springer, Berlin, 2012) pp. 391–401
M.D. MacLeod, J.N. Frowley, J.W. Shepherd, Whole body information: its relevance to eyewitnesses, in Adult Eyewitness Testimony: Current Trends and Developments, eds. by D.F. Ross, J.D. Read, M.P. Toglia (Cambridge University Press, New York, 1994), pp. 125–143
M.S. Raval, Digital video forensics: description based person identification. CSI Commun. 39(12), 9–11 (2016)
D.A. Reid, M.S. Nixon, Imputing human descriptions in semantic biometrics, in Proceedings of the 2nd ACM Workshop on Multimedia in Forensics, Security and Intelligence 2010 (ACM, New York, 2010), pp. 25–30
D.A. Reid, S. Samangooei, C. Chen, M.S. Nixon, A. Ross, Soft biometrics for surveillance: an overview, in Handbook of Statistics, vol. 31 (Elsevier, Amsterdam, 2013), pp. 327–352
S. Ren, K. He, R. Girshick, J. Sun, Faster R-CNN: towards real-time object detection with region proposal networks, in Advances in Neural Information Processing Systems (2015), pp. 91–99
S. Samangooei, M. Nixon, B. Guo, The use of semantic human description as a soft biometric, in Proceedings of 2008 IEEE Second International Conference on Biometrics: Theory, Applications and Systems (IEEE, Arlington, 2008)
M.S. Sarfraz, A. Schumann, Y. Wang, R. Stiefelhagen, Deep view-sensitive pedestrian attribute inference in an end-to-end model, in BMVC, 2017.
P. Shah, M.S. Raval, S. Pandya, S. Chaudhary, A. Laddha, H. Galiyawala, Description based person identification: use of clothes color and type, in Computer Vision, Pattern Recognition, Image Processing, and Graphics: 6th National Conference, NCVPRIPG 2017 (Mandi, 2017), Revised Selected Papers 6 (Springer, Singapore, 2018), pp. 457–469
P. Sudowe, H. Spitzer, B. Leibe, Person attribute recognition with a jointly-trained holistic CNN model, in Proceedings of the IEEE International Conference on Computer Vision Workshops (2015), pp. 87–95
R. Tsai, A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses. IEEE J. Robot. Autom. 3(4), 323–344 (1987)
D.A. Vaquero, R.S. Feris, D. Tran, L. Brown, A. Hampapur, M. Turk, Attribute-based people search in surveillance environments, in 2009 Workshop on Applications of Computer Vision (WACV) (IEEE, Piscataway, 2009), pp. 1–8
J. Wang, X. Zhu, S. Gong, W. Li, Attribute recognition by joint recurrent learning of context and correlation, in IEEE International Conference on Computer Vision (ICCV) (2017)
C. Yao, B. Feng, D. Li, J. Li, Hierarchical pedestrian attribute recognition based on adaptive region localization, in 2017 IEEE International Conference on Multimedia and Expo Workshops (ICMEW) (IEEE, Piscataway, 2017), pp. 471–476
J. Zhu, S. Liao, Z. Lei, D. Yi, S. Li, Pedestrian attribute classification in surveillance: database and evaluation, in Proceedings of the IEEE International Conference on Computer Vision Workshops (2013), pp. 331–338
J. Zhu, S. Liao, D. Yi, Z. Lei, S.Z. Li, Multi-label CNN based pedestrian attribute learning for soft biometrics, in 2015 International Conference on Biometrics (ICB) (IEEE, Piscataway, 2015), pp. 535–540
Acknowledgements
The authors would like to thank the Board of Research in Nuclear Sciences (BRNS) for a generous grant (36(3)/14/20/2016-BRNS/36020). We acknowledge the support of NVIDIA Corporation for a donation of the Quadro K5200 GPU used for this research. We would also like to thank the SAIVT Research Labs at Queensland University of Technology (QUT) for creating the challenging dataset. Thanks to Kenil Shah and Vandit Gajjar for their help during the implementation of the work.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Galiyawala, H.J., Raval, M.S., Laddha, A. (2020). Person Retrieval in Surveillance Videos Using Deep Soft Biometrics. In: Jiang, R., Li, CT., Crookes, D., Meng, W., Rosenberger, C. (eds) Deep Biometrics. Unsupervised and Semi-Supervised Learning. Springer, Cham. https://doi.org/10.1007/978-3-030-32583-1_9
Download citation
DOI: https://doi.org/10.1007/978-3-030-32583-1_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-32582-4
Online ISBN: 978-3-030-32583-1
eBook Packages: EngineeringEngineering (R0)