Skip to main content
Erschienen in: International Journal of Computer Vision 3/2017

13.02.2017

Exemplar-Guided Similarity Learning on Polynomial Kernel Feature Map for Person Re-identification

verfasst von: Dapeng Chen, Zejian Yuan, Jingdong Wang, Badong Chen, Gang Hua, Nanning Zheng

Erschienen in: International Journal of Computer Vision | Ausgabe 3/2017

Einloggen

Aktivieren Sie unsere intelligente Suche um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Person re-identification is a crucial problem for video surveillance, aiming to discover the correct matches for a probe person image from a set of gallery person images. To directly describe the image pair, we present a novel organization of polynomial kernel feature map in a high dimensional feature space to break down the variability of positive person pairs. An exemplar-guided similarity function is built on the map, which consists of multiple sub-functions. Each sub-function is associated with an “exemplar” image being responsible for a particular type of image pair, thus excels at separating the persons with similar appearance. We formulate a unified learning problem including a relaxed loss term as well as two kinds of regularization strategies particularly designed for the feature map. The corresponding optimization algorithm jointly optimizes the coefficients of all the sub-functions and selects the proper exemplars for a better discrimination. The proposed method is extensively evaluated on six public datasets, where we thoroughly analyze the contribution of each component and verify the generalizability of our approach by cross-dataset experiments. Results show that the new method can achieve consistent improvements over state-of-the-art methods.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Anhänge
Nur mit Berechtigung zugänglich
Literatur
Zurück zum Zitat Ahmed, E., Jones, M., & Marks, T. K. (2015). An improved deep learning architecture for person re-identification. In: The IEEE conference on computer vision and pattern recognition (CVPR). Ahmed, E., Jones, M., & Marks, T. K. (2015). An improved deep learning architecture for person re-identification. In: The IEEE conference on computer vision and pattern recognition (CVPR).
Zurück zum Zitat Bak, S., Corvée, E., Brémond, F., & Thonnat, M. (2010). Person re-identification using spatial covariance regions of human body parts. In: International conference on advanced video and signal based surveillance. Bak, S., Corvée, E., Brémond, F., & Thonnat, M. (2010). Person re-identification using spatial covariance regions of human body parts. In: International conference on advanced video and signal based surveillance.
Zurück zum Zitat Baltieri, D., Vezzani, R., & Cucchiara, R. (2011). Sarc3d: A new 3D body model for people tracking and re-identification. In: International conference on image analysis and processing. Baltieri, D., Vezzani, R., & Cucchiara, R. (2011). Sarc3d: A new 3D body model for people tracking and re-identification. In: International conference on image analysis and processing.
Zurück zum Zitat Boyd, S. P., & Vandenberghe, L. (2004). Convex optimization. Cambridge: Cambridge university press.CrossRefMATH Boyd, S. P., & Vandenberghe, L. (2004). Convex optimization. Cambridge: Cambridge university press.CrossRefMATH
Zurück zum Zitat Boyd, S. P., Parikh, N., Chu, E., Peleato, B., & Eckstein, J. (2011). Distributed optimization and statistical learning via the alternating direction method of multipliers. Foundations and Trends in Machine Learning, 3(1), 1–122.CrossRefMATH Boyd, S. P., Parikh, N., Chu, E., Peleato, B., & Eckstein, J. (2011). Distributed optimization and statistical learning via the alternating direction method of multipliers. Foundations and Trends in Machine Learning, 3(1), 1–122.CrossRefMATH
Zurück zum Zitat Chen, D., Yuan, Z., Hua, G., Zheng, N., & Wang, J. (2015). Similarity learning on an explicit polynomial kernel feature map for person re-identification. In: Conference on computer vision and pattern recognition. Chen, D., Yuan, Z., Hua, G., Zheng, N., & Wang, J. (2015). Similarity learning on an explicit polynomial kernel feature map for person re-identification. In: Conference on computer vision and pattern recognition.
Zurück zum Zitat Chen, D., Yuan, Z., Chen, B., & Zheng, N. (2016). Similarity learning with spatial constraints for person re-identification. In: Conference on computer vision and pattern recognition. Chen, D., Yuan, Z., Chen, B., & Zheng, N. (2016). Similarity learning with spatial constraints for person re-identification. In: Conference on computer vision and pattern recognition.
Zurück zum Zitat Cheng, D. S., Cristani, M., Stoppa, M., Bazzani, L., & Murino, V. (2011). Custom pictorial structures for re-identification. In: British machine vision conference. Cheng, D. S., Cristani, M., Stoppa, M., Bazzani, L., & Murino, V. (2011). Custom pictorial structures for re-identification. In: British machine vision conference.
Zurück zum Zitat Dalal, N., & Triggs, B. (2005). Histograms of oriented gradients for human detection. In: Computer vision and pattern recognition. Dalal, N., & Triggs, B. (2005). Histograms of oriented gradients for human detection. In: Computer vision and pattern recognition.
Zurück zum Zitat Ding, S., Lin, L., Wang, G., & Chao, H. (2015). Deep feature learning with relative distance comparison for person re-identification. Pattern Recognition, 48(10), 2993–3003.CrossRef Ding, S., Lin, L., Wang, G., & Chao, H. (2015). Deep feature learning with relative distance comparison for person re-identification. Pattern Recognition, 48(10), 2993–3003.CrossRef
Zurück zum Zitat Farenzena, M., Bazzani, L., Perina, A., Murino, V., & Cristani, M. (2010). Person re-identification by symmetry-driven accumulation of local features. In: Computer vision and pattern recognition. Farenzena, M., Bazzani, L., Perina, A., Murino, V., & Cristani, M. (2010). Person re-identification by symmetry-driven accumulation of local features. In: Computer vision and pattern recognition.
Zurück zum Zitat Fisher, R. A. (1936). The use of multiple measurements in taxonomic problems. Annals of Eugenics, 7, 179–188.CrossRef Fisher, R. A. (1936). The use of multiple measurements in taxonomic problems. Annals of Eugenics, 7, 179–188.CrossRef
Zurück zum Zitat Gong, S., Cristani, M., Yan, S., & Loy, C. C. (Eds.). (2014). Person re-identification. Advances in computer vision and pattern recognition. Berlin: Springer. Gong, S., Cristani, M., Yan, S., & Loy, C. C. (Eds.). (2014). Person re-identification. Advances in computer vision and pattern recognition. Berlin: Springer.
Zurück zum Zitat Gray, D., Brennan, S., & Tao, H. (2007). Evaluating appearance models for recognition, reacquisition, and tracking. In: International Workshop on PETS, Rio de Janeiro. Gray, D., Brennan, S., & Tao, H. (2007). Evaluating appearance models for recognition, reacquisition, and tracking. In: International Workshop on PETS, Rio de Janeiro.
Zurück zum Zitat Hirzer, M., Beleznai, C., Roth, P. M., & Bischof, H. (2011). Person re-identification by descriptive and discriminative classification. In: Scandinavian conference on image analysis (pp. 91–102). Hirzer, M., Beleznai, C., Roth, P. M., & Bischof, H. (2011). Person re-identification by descriptive and discriminative classification. In: Scandinavian conference on image analysis (pp. 91–102).
Zurück zum Zitat Hirzer, M., Roth, P. M., Kostinger, M., & Bischof, H. (2012). Relaxed pairwise learned metric for person re-identification. In: European conference on computer vision. Hirzer, M., Roth, P. M., Kostinger, M., & Bischof, H. (2012). Relaxed pairwise learned metric for person re-identification. In: European conference on computer vision.
Zurück zum Zitat Hotelling, H. (1936). Relations between two sets of variates. Biometrika, 28(3/4), 321–377.CrossRefMATH Hotelling, H. (1936). Relations between two sets of variates. Biometrika, 28(3/4), 321–377.CrossRefMATH
Zurück zum Zitat Jégou, H., & Chum, O. (2012). Negative evidences and co-occurences in image retrieval: The benefit of PCA and whitening. In: European conference on computer vision. Jégou, H., & Chum, O. (2012). Negative evidences and co-occurences in image retrieval: The benefit of PCA and whitening. In: European conference on computer vision.
Zurück zum Zitat Kjems, U., Hansen, L.K., & Strother, S. C. (2000). Generalizable singular value decomposition for ill-posed datasets. In: Neural information processing systems (pp. 549–555). Kjems, U., Hansen, L.K., & Strother, S. C. (2000). Generalizable singular value decomposition for ill-posed datasets. In: Neural information processing systems (pp. 549–555).
Zurück zum Zitat Köstinger, M., Hirzer, M., Wohlhart, P., Roth, P. M., & Bischof, H. (2012). Large scale metric learning from equivalence constraints. In: Computer vision and pattern recognition. Köstinger, M., Hirzer, M., Wohlhart, P., Roth, P. M., & Bischof, H. (2012). Large scale metric learning from equivalence constraints. In: Computer vision and pattern recognition.
Zurück zum Zitat Li, W., & Wang, X. (2013). Locally aligned feature transforms across views. In: Computer vision and pattern recognition. Li, W., & Wang, X. (2013). Locally aligned feature transforms across views. In: Computer vision and pattern recognition.
Zurück zum Zitat Li, W., Zhao, R., Xiao, T., & Wang, X. (2014). Deepreid: Deep filter pairing neural network for person re-identification. In IEEE conference on computer vision and pattern recognition (CVPR). Li, W., Zhao, R., Xiao, T., & Wang, X. (2014). Deepreid: Deep filter pairing neural network for person re-identification. In IEEE conference on computer vision and pattern recognition (CVPR).
Zurück zum Zitat Li, Y., Wu, Z., & Radke, R.J. (2015). Multi-shot re-identification with random-projection-based random forests. In Winter conference on applications of computer vision. Li, Y., Wu, Z., & Radke, R.J. (2015). Multi-shot re-identification with random-projection-based random forests. In Winter conference on applications of computer vision.
Zurück zum Zitat Li, Z., Chang, S., Liang, F., Huang, T.S., Cao, L., & Smith, J.R. (2013). Learning locally-adaptive decision functions for person verification. In Computer vision and pattern recognition. Li, Z., Chang, S., Liang, F., Huang, T.S., Cao, L., & Smith, J.R. (2013). Learning locally-adaptive decision functions for person verification. In Computer vision and pattern recognition.
Zurück zum Zitat Liao, S., Zhao, G., Kellokumpu, V., Pietikäinen, M., & Li, S.Z. (2010). Modeling pixel process with scale invariant local patterns for background subtraction in complex scenes. In Conference on computer vision and pattern recognition (pp. 1301–1306). Liao, S., Zhao, G., Kellokumpu, V., Pietikäinen, M., & Li, S.Z. (2010). Modeling pixel process with scale invariant local patterns for background subtraction in complex scenes. In Conference on computer vision and pattern recognition (pp. 1301–1306).
Zurück zum Zitat Liao, S., Hu, Y., Zhu, X., & Li, S.Z. (2015). Person re-identification by local maximal occurrence representation and metric learning. In The IEEE conference on computer vision and pattern recognition (CVPR). Liao, S., Hu, Y., Zhu, X., & Li, S.Z. (2015). Person re-identification by local maximal occurrence representation and metric learning. In The IEEE conference on computer vision and pattern recognition (CVPR).
Zurück zum Zitat Loy, C.C., Liu, C., & Gong, S. (2013). Person re-identification by manifold ranking. In International conference on image processing. Loy, C.C., Liu, C., & Gong, S. (2013). Person re-identification by manifold ranking. In International conference on image processing.
Zurück zum Zitat Ma, B., Su, Y., & Jurie, F. (2012a). Bicov: A novel image representation for person re-identification and face verification. In British machine vision conference. Ma, B., Su, Y., & Jurie, F. (2012a). Bicov: A novel image representation for person re-identification and face verification. In British machine vision conference.
Zurück zum Zitat Ma, B., Su, Y., & Jurie, F. (2012b). Local descriptors encoded by fisher vectors for person re-identification. In ECCV workshops and demonstrations. Ma, B., Su, Y., & Jurie, F. (2012b). Local descriptors encoded by fisher vectors for person re-identification. In ECCV workshops and demonstrations.
Zurück zum Zitat Ma, L., Yang, X., & Tao, D. (2014). Person re-identification over camera networks using multi-task distance metric learning. IEEE Transactions on Image Processing, 23(8), 3656–3670.MathSciNetCrossRef Ma, L., Yang, X., & Tao, D. (2014). Person re-identification over camera networks using multi-task distance metric learning. IEEE Transactions on Image Processing, 23(8), 3656–3670.MathSciNetCrossRef
Zurück zum Zitat Mignon, A., & Jurie, F. (2012). PCCA: A new approach for distance learning from sparse pairwise constraints. In Computer vision and pattern recognition. Mignon, A., & Jurie, F. (2012). PCCA: A new approach for distance learning from sparse pairwise constraints. In Computer vision and pattern recognition.
Zurück zum Zitat Ojala, T., Pietikäinen, M., & Mäenpää, T. (2002). Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(7), 971–987. Ojala, T., Pietikäinen, M., & Mäenpää, T. (2002). Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(7), 971–987.
Zurück zum Zitat Paisitkriangkrai, S., Shen, C., & van den Hengel, A. (2015). Learning to rank in person re-identification with metric ensembles. In The IEEE conference on computer vision and pattern recognition (CVPR). Paisitkriangkrai, S., Shen, C., & van den Hengel, A. (2015). Learning to rank in person re-identification with metric ensembles. In The IEEE conference on computer vision and pattern recognition (CVPR).
Zurück zum Zitat Pedagadi, S., Orwell, J., Velastin, S.A., & Boghossian, B.A. (2013). Local fisher discriminant analysis for pedestrian re-identification. In Computer vision and pattern recognition. Pedagadi, S., Orwell, J., Velastin, S.A., & Boghossian, B.A. (2013). Local fisher discriminant analysis for pedestrian re-identification. In Computer vision and pattern recognition.
Zurück zum Zitat Prosser, B., Zheng, W., Gong, S., & Xiang, T. (2010). Person re-identification by support vector ranking. In British machine vision conference. Prosser, B., Zheng, W., Gong, S., & Xiang, T. (2010). Person re-identification by support vector ranking. In British machine vision conference.
Zurück zum Zitat Schwartz, W.R., & Davis, L.S. (2009). Learning discriminative appearance-based models using partial least squares. In XXII Brazilian symposium on computer graphics and image processing. Schwartz, W.R., & Davis, L.S. (2009). Learning discriminative appearance-based models using partial least squares. In XXII Brazilian symposium on computer graphics and image processing.
Zurück zum Zitat Tuzel, O., Porikli, F., & Meer, P. (2006). Region covariance: A fast descriptor for detection and classification. In European conference on computer vision. Tuzel, O., Porikli, F., & Meer, P. (2006). Region covariance: A fast descriptor for detection and classification. In European conference on computer vision.
Zurück zum Zitat Wu, Z., Li, Y., & Radke, R. J. (2015). Viewpoint invariant human re-identification in camera networks using pose priors and subject-discriminative features. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(5), 1095–1108.CrossRef Wu, Z., Li, Y., & Radke, R. J. (2015). Viewpoint invariant human re-identification in camera networks using pose priors and subject-discriminative features. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(5), 1095–1108.CrossRef
Zurück zum Zitat Xiong, F., Gou, M., Camps, O.I., & Sznaier, M. (2014). Person re-identification using kernel-based metric learning methods. In European conference on computer vision. Xiong, F., Gou, M., Camps, O.I., & Sznaier, M. (2014). Person re-identification using kernel-based metric learning methods. In European conference on computer vision.
Zurück zum Zitat Xu, Y., Lin, L., Zheng, W., & Liu, X. (2013). Human re-identification by matching compositional template with cluster sampling. In International conference on computer vision (pp. 3152–3159). Xu, Y., Lin, L., Zheng, W., & Liu, X. (2013). Human re-identification by matching compositional template with cluster sampling. In International conference on computer vision (pp. 3152–3159).
Zurück zum Zitat Yang, Y., Yang, J., Yan, J., Liao, S., Yi, D., & Li, S.Z. (2014). Salient color names for person re-identification. In European conference on computer vision. Yang, Y., Yang, J., Yan, J., Liao, S., Yi, D., & Li, S.Z. (2014). Salient color names for person re-identification. In European conference on computer vision.
Zurück zum Zitat Zhang, Z., Chen, Y., & Saligrama, V. (2014). A novel visual word co-occurrence model for person re-identification. In: ECCV workshops. Zhang, Z., Chen, Y., & Saligrama, V. (2014). A novel visual word co-occurrence model for person re-identification. In: ECCV workshops.
Zurück zum Zitat Zhao, R., Ouyang, W., & Wang, X. (2013). Unsupervised salience learning for person re-identification. In Computer vision and pattern recognition. Zhao, R., Ouyang, W., & Wang, X. (2013). Unsupervised salience learning for person re-identification. In Computer vision and pattern recognition.
Zurück zum Zitat Zhao, R., Ouyang, W., & Wang, X. (2014). Learning mid-level filters for person re-identification. In Conference on computer vision and pattern recognition. Zhao, R., Ouyang, W., & Wang, X. (2014). Learning mid-level filters for person re-identification. In Conference on computer vision and pattern recognition.
Zurück zum Zitat Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., Bu, J., & Tian, Q. (2015). Scalable person re-identification: A benchmark. In International conference on computer vision. Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., Bu, J., & Tian, Q. (2015). Scalable person re-identification: A benchmark. In International conference on computer vision.
Zurück zum Zitat Zheng, W., Gong, S., & Xiang, T. (2009). Associating groups of people. In British machine vision conference. Zheng, W., Gong, S., & Xiang, T. (2009). Associating groups of people. In British machine vision conference.
Zurück zum Zitat Zheng, W., Gong, S., & Xiang, T. (2013). Reidentification by relative distance comparison. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(3), 653–668.CrossRef Zheng, W., Gong, S., & Xiang, T. (2013). Reidentification by relative distance comparison. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(3), 653–668.CrossRef
Metadaten
Titel
Exemplar-Guided Similarity Learning on Polynomial Kernel Feature Map for Person Re-identification
verfasst von
Dapeng Chen
Zejian Yuan
Jingdong Wang
Badong Chen
Gang Hua
Nanning Zheng
Publikationsdatum
13.02.2017
Verlag
Springer US
Erschienen in
International Journal of Computer Vision / Ausgabe 3/2017
Print ISSN: 0920-5691
Elektronische ISSN: 1573-1405
DOI
https://doi.org/10.1007/s11263-017-0991-0

Weitere Artikel der Ausgabe 3/2017

International Journal of Computer Vision 3/2017 Zur Ausgabe