Abstract
In this work, we propose a novel context-aware framework towards long-term person re-identification. In contrast to the classical context-unaware architecture, in this method we exploit contextual features that can be identified reliably and guide the re-identification process in a much faster and accurate manner. The system is designed for the long-term Re-ID in walking scenarios, so persons are characterized by soft-biometric features (i.e., anthropometric and gait) acquired using a Kinect\(^\mathrm {TM}\) v.2 sensor. Context is associated to the posture of the person with respect to the camera, since the quality of the data acquired from the used sensor significantly depends on this variable. Within each context, only the most relevant features are selected with the help of feature selection techniques, and custom individual classifiers are trained. Afterwards, a context-aware ensemble fusion strategy which we term as ‘Context specific score-level fusion’, merges the results of individual classifiers. In typical ‘in-the-wild’ scenarios the samples of a person may not appear in all contexts of interest. To tackle this problem we propose a cross-context analysis where features are mapped between contexts and allow the transfer of the identification characteristics of a person between different contexts. We demonstrate in this work the experimental verification of the performance of the proposed context-aware system against the classical context-unaware system. We include in the results the analysis of switching context conditions within a video sequence through a pilot study of circular path movement. All the analysis accentuate the impact of contexts in simplifying the searching process by bestowing promising results.
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
Notes
- 1.
‘in-the-wild’ refers to the unconstrained settings.
- 2.
More details on KS20 VisLab Multi-View Kinect skeleton dataset is available in the laboratory website http://vislab.isr.ist.utl.pt/vislab_multiview_ks20/.
- 3.
- 4.
We used ‘SpineShoulder’ i.e., the base of the neck refering to joint number 20 of Kinect\(^\mathrm {TM}\) v.2 ( https://msdn.microsoft.com/en-us/library/microsoft.kinect.jointtype.aspx) as the torso joint towards context detection, since it remains more or less stable while walking.
- 5.
KS20 VisLab Multi-View Kinect skeleton dataset: http://vislab.isr.ist.utl.pt/vislab_multiview_ks20/. Access to the Vislab Multi-view KS20 dataset is available upon request. Contact the corresponding author if you are interested in this dataset.
- 6.
For body joint types and enumeration, refer to the link: https://msdn.microsoft.com/en-us/library/microsoft.kinect.jointtype.aspx.
- 7.
In the publicly available dataset also, only the skeleton data is provided. Nevertheless, color and depth information can be made available on demand.
- 8.
1-context and 2-contexts work only for the full cover scenario, and hence other sparse cover and single cover scenarios for the same are represented via crossmark, refering ‘Not Applicable’.
References
Nambiar, A., Bernardino, A., Nascimento, J.C., Fred, A.: Context-aware person re-identification in the wild via fusion of gait and anthropometric features. In: B-Wild Workshop at 12th IEEE International Conference on Automatic Face & Gesture Recognition, pp. 973–980 (2017)
Barbosa, I.B., Cristani, M., Del Bue, A., Bazzani, L., Murino, V.: Re-identification with RGB-D sensors. In: Fusiello, A., Murino, V., Cucchiara, R. (eds.) ECCV 2012. LNCS, vol. 7583, pp. 433–442. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33863-2_43
Gianaria, E., Grangetto, M., Lucenteforte, M., Balossino, N.: Human classification using gait features. In: Cantoni, V., Dimov, D., Tistarelli, M. (eds.) International Workshop on Biometric Authentication, pp. 16–27. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-13386-7_2
Andersson, V.O., de Araújo, R.M.: Person identification using anthropometric and gait data from kinect sensor. In: AAAI, pp. 425–431 (2015)
Munaro, M., Fossati, A., Basso, A., Menegatti, E., Van Gool, L.: One-shot person re-identification with a consumer depth camera. In: Gong, S., Cristani, M., Yan, S., Loy, C.C. (eds.) Person Re-Identification. ACVPR, pp. 161–181. Springer, London (2014). https://doi.org/10.1007/978-1-4471-6296-4_8
Context definition. https://en.wiktionary.org/wiki/context
Palmisano, C., Tuzhilin, A., Gorgoglione, M.: Using context to improve predictive modeling of customers in personalization applications. IEEE Trans. Knowl. Data Eng. 20, 1535–1549 (2008)
Ding, Y., Meng, X., Chai, G., Tang, Y.: User identification for instant messages. In: Lu, B.-L., Zhang, L., Kwok, J. (eds.) ICONIP 2011. LNCS, vol. 7064, pp. 113–120. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-24965-5_13
Panniello, U., Hill, S., Gorgoglione, M.: Using context for online customer re-identification. Expert Syst. Appl. 64, 500–511 (2016)
Alldieck, T., Bahnsen, C.H., Moeslund, T.B.: Context-aware fusion of RGB and thermal imagery for traffic monitoring. Sensors 16, 1947 (2016)
Wei, L., Shah, S.K.: Human activity recognition using deep neural network with contextual information. In: International Conference on Computer Vision Theory and Applications, pp. 34–43 (2017)
Zhang, L., Kalashnikov, D.V., Mehrotra, S., Vaisenberg, R.: Context-based person identification framework for smart video surveillance. Mach. Vis. Appl. 25, 1711–1725 (2014)
Leng, Q., Hu, R., Liang, C., Wang, Y., Chen, J.: Person re-identification with content and context re-ranking. Multimedia Tools Appl. 74, 6989–7014 (2015)
Garcia, J., Martinel, N., Micheloni, C., Gardel, A.: Person re-identification ranking optimisation by discriminant context information analysis. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1305–1313 (2015)
Silva, H., Fred, A.: Feature subspace ensembles: a parallel classifier combination scheme using feature selection. In: Haindl, M., Kittler, J., Roli, F. (eds.) MCS 2007. LNCS, vol. 4472, pp. 261–270. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-72523-7_27
Whitney, A.W.: A direct method of nonparametric measurement selection. IEEE Trans. Comput. C-20(9), 1100–1103 (1971)
Pohjalainen, J., Räsänen, O., Kadioglu, S.: Feature selection methods and their combinations in high-dimensional classification of speaker likability, intelligibility and personality traits. Comput. Speech Lang. 29, 145–171 (2015)
Ross, A.A., Nandakumar, K., Jain, A.: Handbook of Multibiometrics, vol. 6. Springer, Heidelberg (2006). https://doi.org/10.1007/0-387-33123-9
Nambiar, A., Bernardino, A., Nascimento, J.C., Fred, A.: Towards view-point invariant person re-identification via fusion of anthropometric and gait features from Kinect measurements, pp. 108–119 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Nambiar, A., Bernardino, A. (2019). A Context-Aware Method for View-Point Invariant Long-Term Re-identification. In: Cláudio, A., et al. Computer Vision, Imaging and Computer Graphics – Theory and Applications. VISIGRAPP 2017. Communications in Computer and Information Science, vol 983. Springer, Cham. https://doi.org/10.1007/978-3-030-12209-6_16
Download citation
DOI: https://doi.org/10.1007/978-3-030-12209-6_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-12208-9
Online ISBN: 978-3-030-12209-6
eBook Packages: Computer ScienceComputer Science (R0)