Abstract
Person re-identification is an important video analysis problem that aims to track people over non-overlapping views in a large camera network. The purpose is to find the same person from disjoint camera views at different times and locations. Most of the existing re-identification approaches assume pre-selected people bounding box captured by two non-overlapping cameras to perform the re-identification task while ignoring the inter-camera relationships in the network. In this paper, we propose a multi-shot person re-identification approach in a large camera network that relies on the appearance and spatial-temporal features. Firstly, we introduce a novel algorithm that selects a set of key appearance images depicting the different body postures from the target’s trajectory. Secondly, we model the appearance characteristics by extracting the multi-level semantic appearance representation descriptor that encodes both low- and mid-level appearance characteristics. Then, a dynamic gallery set is constructed containing the candidate people to whom the probe person can correspond based on his spatial-temporal characteristics. A novel camera network spatial-temporal graph is introduced to model the inter-camera relationships of the network in terms of entry/exit points, transition time, etc. The proposed approach has been experimentally validated on HDA+ and VIPeR datasets. The outcomes of this evaluation show promising results and demonstrate the effectiveness of our approach.
Similar content being viewed by others
References
An, L., Chen, X., Kafai, M., Yang, S., Bhanu, B.: Improving person re-identification by soft biometrics based reranking. In: ICDSC, pp. 1–6 (2013)
Bak, S., Zaidenberg, S., Boulay, B., Bremond, F.: Improving person re-identification by viewpoint cues. In: AVSS, pp. 175–180 (2014)
Bazzani, L., Cristani, M., Murino, V.: Sdalf: modeling human appearance with symmetry-driven accumulation of local features. In: Person Re-Identification, pp. 43–69 (2014)
Bhattacharyya, A.: On a measure of divergence between two statistical populations defined by their probability distributions. Bull. Calcutta Math. Soc. 35, 99–109 (1943)
Buchsbaum, G.: A spatial processor model for object colour perception. J. Franklin Instit. 310(1), 1–26 (1980)
Cheng, D.S., Cristani, M., Stoppa, M., Bazzani, L., Murino, V.: Custom pictorial structures for re-identification. In: Bmvc 1, 6 (2011)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. CVPR 1, 886–893 (2005)
Derbel, A., Jemaa, Y.B., Canals, R., Emile, B., Treuillet, S., Hamadou, A.B.: Comparative study between color texture and shape descriptors for multi-camera pedestrians identification. In: International Conference on Image Processing Theory, Tools and Applications, pp. 313–318 (2012)
Doretto, G., Sebastian, T., Tu, P., Rittscher, J.: Appearance-based person reidentification in camera networks: problem overview and current approaches. J. Ambient Intell. Humanized Comput. 2(2), 127–151 (2011)
Fendri, E., Frikha, M., Hammami, M.: Adaptive person re-identification based on visible salient body parts in large camera network. Computer J. 60(11), 1590–1608 (2017)
Fendri, E., Frikha, M., Hammami, M.: Multi-level semantic appearance representation for person re-identification system. Pattern Recognit. Lett. 115, 30–38 (2018)
Figueira, D., Taiana, M., Nambiar, A., Nascimento, J., Bernardino, A.: The hda+ data set for research on fully automated re-identification systems. In: ECCV, pp. 241–255 (2014)
Frikha, M., Chebbi, O., Fendri, E., Hammami, M.: Key frame selection for multi-shot person re-identification. In: RFMI, pp. 97–110 (2016)
Frikha, M., Fendri, E., Hammami, M.: A new appearance signature for real time person re-identification. In: IDEAL, pp. 175–182 (2014)
Frikha, M., Fendri, E., Hammami, M.: Semantic attributes for people’s appearance description: an appearance modality for video surveillance applications. J. Electron. Imag. 26(5), 051405 (2017)
Frikha, M., Fendri, E., Hammami, M.: People search based on attributes description provided by an eyewitness for video surveillance applications. Multimed. Tools Appl. 78, 1–28 (2018)
Gray, D., Tao, H.: Viewpoint invariant pedestrian recognition with an ensemble of localized features. ECCV pp. 262–275 (2008)
Huang, W., Hu, R., Liang, C., Yu, Y., Wang, Z., Zhong, X., Zhang, C.: Camera network based person re-identification by leveraging spatial-temporal constraint and multiple cameras relations. In: ICMM, pp. 174–186 (2016)
Jain, A.K., Farrokhnia, F.: Unsupervised texture segmentation using gabor filters. Pattern Recogn. 24(12), 1167–1186 (1991)
Karaman, S., Lisanti, G., Bagdanov, A.D., Del Bimbo, A.: Leveraging local neighborhood topology for large scale person re-identification. Pattern Recogn. 47(12), 3767–3778 (2014)
Khamis, S., Kuo, C.H., Singh, V.K., Shet, V.D., Davis, L.S.: Joint learning for attribute-consistent person re-identification. In: ECCV, pp. 134–146 (2014)
Kuo, C.H., Khamis, S., Shet, V.: Person re-identification using semantic color names and rankboost. In: IEEE Workshop on Applications of Computer Vision, pp. 281–287 (2013)
Kviatkovsky, I., Adam, A., Rivlin, E.: Color invariants for person reidentification. IEEE Trans. Pattern Anal. Mach. Intell. 35(7), 1622–1634 (2013)
Layne, R., Hospedales, T.M., Gong, S.: Attributes-based re-identification. In: Person Re-Identification, pp. 93–117 (2014)
Li, W., Wang, X.: Locally aligned feature transforms across views. In: CVPR, pp. 3594–3601 (2013)
Meden, B., Lerasle, F., Sayd, P.: Mcmc supervision for people re-identification in nonoverlapping cameras. In: BMVC, pp. 1–11 (2012)
Nambiar, A., Taiana, M., Figueira, D., Nascimento, J., Bernardino, A.: A multi-camera video dataset for research on high-definition surveillance. Inter. J. Mach. Intell. Sensory Signal Process. 1(3), 267–286 (2014)
Nguyen, N.B., Nguyen, V.H., Duc, T.N., Le, D.D., Duong, D.A.: Attrel: an approach to person re-identification by exploiting attribute relationships. ICMM 8936, 50 (2015)
Prates, R., Dutra, C.R., Schwartz, W.R.: Predominant color name indexing structure for person re-identification. In: ICIP, pp. 779–783 (2016)
Prosser, B., Zheng, W.S., Gong, S., Xiang, T., Mary, Q.: Person re-identification by support vector ranking. BMVC 2, 6 (2010)
Pudil, P., Novovičová, J., Kittler, J.: Floating search methods in feature selection. Pattern Recogn. Lett. 15(11), 1119–1125 (1994)
Schmid, C.: Constructing models for content-based image retrieval. In: CVPR, vol. 2, pp. II–II (2001)
Swain, M.J., Ballard, D.H.: Color indexing. Int. J. Computer Vision 7(1), 11–32 (1991)
Umeda, T., Sun, Y., Irie, G., Sudo, K., Kinebuchi, T.: Attribute discovery for person re-identification. In: ICMM, pp. 268–276 (2016)
Wang, T., Gong, S., Zhu, X., Wang, S.: Person re-identification by discriminative selection in video ranking. IEEE Trans. Pattern Anal. Mach. Intell. 38(12), 2501–2514 (2016)
Yang, Y., Yang, J., Yan, J., Liao, S., Yi, D., Li, S.Z.: Salient color names for person re-identification. In: ECCV, pp. 536–551 (2014)
Zeng, M., Wu, Z., Tian, C., Zhang, L., Hu, L.: Efficient person re-identification by hybrid spatiogram and covariance descriptor. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 48–56 (2015)
Zheng, W.S., Gong, S., Xiang, T.: Reidentification by relative distance comparison. IEEE Trans. Pattern Anal. Mach. Intell. 35(3), 653–668 (2013)
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Frikha, M., Fendri, E. & Hammami, M. Multi-shot person re-identification based on appearance and spatial-temporal cues in a large camera network. Machine Vision and Applications 32, 85 (2021). https://doi.org/10.1007/s00138-021-01213-6
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s00138-021-01213-6