Abstract
Recent advances in visual tracking methods allow following a given object or individual in presence of significant clutter or partial occlusions in a single or a set of overlapping camera views. The question of when person detections in different views or at different time instants can be linked to the same individual is of fundamental importance to the video analysis in large-scale network of cameras. This is the person reidentification problem. The paper focuses on algorithms that use the overall appearance of an individual as opposed to passive biometrics such as face and gait. Methods that effectively address the challenges associated with changes in illumination, pose, and clothing appearance variation are discussed. More specifically, the development of a set of models that capture the overall appearance of an individual and can effectively be used for information retrieval are reviewed. Some of them provide a holistic description of a person, and some others require an intermediate step where specific body parts need to be identified. Some are designed to extract appearance features over time, and some others can operate reliably also on single images. The paper discusses algorithms for speeding up the computation of signatures. In particular it describes very fast procedures for computing co-occurrence matrices by leveraging a generalization of the integral representation of images. The algorithms are deployed and tested in a camera network comprising of three cameras with non-overlapping field of views, where a multi-camera multi-target tracker links the tracks in different cameras by reidentifying the same people appearing in different views.
Similar content being viewed by others
Notes
In real scenarios occlusions may arise by other people, or objects, in the scene that are covering the imaged person. This paper does not consider such cases, and assumes that a person appears unobstructed in front of the camera.
\(P[\cdot]\) indicates a probability measure.
If the Fubini’s theorem for indefinite integrals holds, then F(x) exists.
The operation \(| \cdot |\) applied to a domain or a set indicates the area or the cardinality, respectively.
Note that \({a \in {\mathcal{A}}}\) is intended to index one of the elements of the m -dimensional vector \(G(\cdot,{\mathbf{x}}).\)
In (Savarese et al. 2006) \(|\nabla \cdot p|\) is part of the hidden constants. Here the dependency is made explicit to better compare that approach with this one.
Note that the analysis conducted here is independent of the cardinality of the label sets \({{\mathcal{S}}}\) and \({\mathcal{A}}.\)
Note that ψ is a concatenation of histograms.
Note that the approach in (Savarese et al. 2006) was originally designed for doing inter-category object recognition. Here it has been tested outside of its natural domain.
A point x is an adherent point for an open set B, if every open set containing x contains at least one point of B. A point x is an adherent point for B if and only if x is in the closure of B.
References
Amit Y, Kong A (1996) Graphical templates for model registration. IEEE Trans Pattern Anal Mach Intell 18(3):225–236
Bak S, Corvee E, BrTmond F, Thonnat M (2010a) Person re-identification using spatial covariance regions of human body parts. In: Proceedings of IEEE international conference on video and signal based surveillance
Bak S, Corvee E, BrTmond F, Thonnat T (2010b) Person re-identification using haar-based and dcd-based signature. In: Proceedings of the workshop on activity monitoring by multi-camera surveillance systems
Bäuml M, Bernardin K, Fischer M, Ekenel HK (2010) Multi-pose face recognition for person retrieval in camera networks. In: Proceedings of IEEE international conference on video and signal based surveillance
Bay H, Ess A, Tuytelaars T, Van Goo L (2008) Surf: Speeded up robust features. Comput Vis Image Underst 110(3):346–359
Belongie S, Malik J, Puzicha J (2002) Shape matching and object recognition using shape contexts. IEEE Trans Pattern Anal Mach Intell 24:509–522
Bird N, Masoud O, Papanikolopoulos N, Isaacs A (2005) Detection of loitering individuals in public transportation areas. IEEE Trans Intell Transport Syst 6(2):167–177
Bissacco A, Soatto S (2009) Hybrid dynamical models of human motion for the recognition of human gaits. Int J Comput Vis 85(1):101–114
Blackman S, Popoli R (1999) Design and analysis of modern tracking systems. Artech House Publishers, Norwood
Bookstein FL (1986) Size and shape spaces for landmark data in two dimensions. Stat Sci 1(2):181–242
Cai Y, Huang K, Tan T (2008) Human appearance matching across multiple non-overlapping cameras. In: Proceedings of the international conference on pattern recognition
Canny J (1986) A computational approach to edge detection. IEEE Trans Pattern Anal Mach Intell 8(6):679–698
Cox IJ, Hingorani SL (1994) An efficient implementation and evaluation of reid’s multiple hypothesis tracking algorithm for visual tracking. In: Proceedings of the international conference on pattern recognition
Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition, vol 1. pp 886–893
Damen D, Hogg D (2007) Associating people dropping off and picking up objects. In: Proceedings of the British machine vision conference
Doretto G, Soatto S (2006) Dynamic shape and appearance models. IEEE Trans Pattern Anal Mach Intell 28(12):2006–2019
Doretto G, Wang X (2007) Integral computations: a framework to compute fast region based features. Tech. Rep. 2007GRC593, GE Global Research. Visualization and Computer Vision Laboratory, Niskayuna
Doretto G, Yao Y (2010) Region moments: fast invariant descriptors for detecting small image structures. In: Proceedings of the IEEE computer society conference on 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: Proceedings of the IEEE computer society conference on computer vision and pattern recognition
Fei-Fei L, Perona P (2005) A Bayesian hierarchical model for learning natural scene categories. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition, vol 2, pp 524–531
Felzenszwalb PF (2005) Representation and detection of deformable shapes. IEEE Trans Pattern Anal Mach Intell 27(2):208–220
Felzenszwalb PF, Huttenlocher D (2004) Efficient graph-based image segmentation. Int J Comput Vis 59(2):167–181
Forssen PE (2007) Maximally stable colour regions for recognition and matching. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition
Funt BV, Finlayson GD (1995) Color constant color indexing. IEEE Trans Pattern Anal Mach Intell 17:522–529
Gandhi T, Trivedi MM (2007) Person tracking and reidentification: introducing panoramic appearance map (PAM) for feature representation. Mach Vis Appl 18(3–4):207–220
Geusebroek J, Boomgaard R, Smeulders AWM, Geerts H (2001) Color invariance. IEEE Trans Pattern Anal Mach Intell 23:1338–1350
Gheissari N, Sebastian TB, Tu PH, Rittscher J, Hartley R (2006) Person reidentification using spatiotemporal appearance. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition, vol 2, pp 1528–1535
Gray D, Tao H (2008) Viewpoint invariant pedestrian recognition with an ensemble of localized features. In: Proceedings of the European conference on computer vision, pp 262–275
Guo Y, Hsu S, Shan Y, Sawhney H, Kumar R (2005) Vehicle fingerprinting for reacquisition & tracking in videos. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition, vol 2, pp 761–768
Hamdoun O, Moutarde F, Stanciulescu B, Steux B (2008) Person reidentification in multi-camera system by signature based on interest point descriptors collected on short video sequences. In: Proceedings of the ACM/IEEE international conference distributed smart cameras
Hu L, Wang Y, Jiang S, Huang Q, Gao W (2008) Human reappearance detection based on on-line learning. In: Proceedings of the international conference on pattern recognition
Huang J, Kumar SR, Mitra M, Zhu WJ, Zabih R (1997) Image indexing using color correlograms. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition, San Juan, pp 762–768
Isard M, MacCormick J (2001) BraMBLe: aBayesian multiple-blob tracker. In: Proceedings of IEEE international conference on computer vision, pp 34–41
Jaffré G, Joly P (2004) Costume: a new feature for automatic video content indexing. In: Proceedings of RIAO, pp 314–325
Javed O, Rasheed Z, Shafique K, Shah M (2003) Tracking across multiple cameras with disjoint views. In: Proceedings of IEEE international conference on computer vision, pp 952–957
Javed O, Shafique K, Shah M (2005) Appearance modeling for tracking in multiple non-overlapping cameras. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition, vol 2, pp 26–33
Javed O, Shafique K, Rasheed Z, Shah M (2007) Modeling inter-camera space-time and appearance relationships for tracking accross non-overlapping views. Comput Vis Image Underst 109:146–162
Jurie F, Triggs B (2005) Creating efficient codebooks for visual recognition. In: Proceedings of IEEE international conference on computer vision
Ke Y, Sukthankar R, Hebert M (2005) Efficient visual event detection using volumetric features. In: Proceedings of IEEE international conference on computer vision, vol 1, pp 166–173
Khan SM, Shah M (2006) A multiview approach to tracking people in crowded scenes using a planar homography constraint. In: Proceedings of the European conference on computer vision, pp 133–146
Krahnstoever N, Tu P, Sebastian T, Perera A, Collins R (2006) Multi-view detection and tracking of travelers and luggage in mass transit environments. In: Proceeding of IEEE international workshop on performance evaluation of tracking and surveillance
Kumar S, Hebert M (2006) Discriminative random fields. Int J Comput Vis 68:179–201
Lazebnik S, Schmid C, Ponce J (2003) Affine-invariant local descriptors and neighborhood statistics for texture recognition. In: Proceedings of IEEE international conference on computer vision, pp 649–655
Lin Z, Davis LS (2008) Learning pairwise dissimilarity profiles for appearance recognition in visual surveillance. In: International symposium on visual computing, pp 23–34
Lo Presti L, Sclaroff S, La Cascia M (2009) Object matching in distributed video surveillance systems by lda-based appearance descriptors. In: Proceedings of the international conference on image analysis and processing
Lowe D (2004) Distinctive image features from scale-invariant key points. Int J Comput Vis 60:91–110
Ma X, Grimson WEL (2005) Edge-based rich representation for vehicle classification. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition, vol 2, pp 1185–1192
Ma Y, Soatto S, Kosecká J, Sastry SS (2004) An invitation to 3D vision: from images to geometric models. Springer, New York, Inc.
Madden C, Cheng E, Piccardi M (2007) Tracking people across disjoint camera views by an illumination-tolerant appearance representation. Mach Vis Appl 18(3):233–247
Makris D, Ellis TJ, Black JK (2004) Bridging the gaps between cameras. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition, pp 205–210
Mikolajczyk K, Schmid C (2005) A performance evaluation of local descriptors. IEEE Trans Pattern Anal Mach Intell 27:1615–1630
Mikolajczyk K, Schmid C, Zisserman A (2004) Human detection based on a probabilistic assembly of robust part detectors. In: Proceedings of the European conference on computer vision, pp 69–82
Mikolajczyk K, Tuytelaars T, Schmid C, Zisserman A, Matas J, Schaffalitzky F, Kadir T, Van Gool L (2005) A comparison of affine region detectors. Int J Comput Vis 65(1–2):43–72
Moon H, Phillips PJ (2001) Computational and performance aspects of PCA-based face-recognition algorithms. Perception 30(3):3003–3321
Mori G, Malik J (2006) Recovering 3d human body configurations using shape contexts. IEEE Trans Pattern Anal Mach Intell 28(7):1052–1062
Moscheni F, Bhattacharjee S, Kunt M (1998) Spatiotemporal segmentation based on region merging. IEEE Trans Pattern Anal Mach Intell 20(9):897–915
Nakajima C, Pontil M, Heisele B, Poggio T (2003) Full-body person recognition system. Pattern Recognit 36(9):1997–2006
Oliveira de Oliveira I, de Souza Pio JL (2009) People reidentification in a camera network. In: Proceeding of the IEEE international conference on dependable, autonomic and secure computing
Ozcanli OC, Tamrakar A, Kimia BB, Mundy JL (2006) Augmenting shape with appearance in vehicle category recognition. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition, New York, NY, USA, vol 1, pp 935–942
Park A U Jain, Kitahara I, Kogure K, Hagita N (2006) ViSE: visual search engine using multiple networked cameras. In: Proceedings of the international conference on pattern recognition, pp 1204–1207
Patras L, Hendriks EA, Lagendijk RL (2001) Video segmentation by MAP labeling of watershed segments. IEEE Trans Pattern Anal Mach Intell 23(3):326–332
Pham TV, Worring M, Smeulders AWM (2007) A multi-camera visual surveillance system for tracking of recurrences of people. In: Proceedings of the ACM/IEEE international conference distributed smart cameras
Philbin J, Chum O, Isard M, Sivic J, Zisserman A (2008) Lost in quantization: improving particular object retrieval in large scale image databases. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition
Phillips P, Flynn P, Scruggs T, Bowyer K, Chang J, Hoffman K, Marques J, Min J, Worek W (2005) Overview of the face recognition grand challenge. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition, pp 947–954
Porikli F (2003) Inter-camera color calibration by correlation model function. In: Proceedings of IEEE international conference on image processing, vol 2, pp 133–136
Porikli F (2005) Integral histogram: a fast way to extract histograms in Cartesian spaces. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition, vol 1, pp 829–836
Prosser B, Gong S, Xiang T (2008) Multi-camera matching using bi-directional cumulative brightness transfer functions. In: Proceedings of the British machine vision conference
Rahimi A, Dunagan B, Darrel T (2004) Simultaneous calibration and tracking with a network of non-overlapping sensors. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition
Rasmussen C, Hager G (1998) Joint probabilistic techniques for tracking multi-part objects. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition, pp 16–21
Savarese S, Winn J, Criminisi A (2006) Discriminative object class models of appearance and shape by correlatons. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition, vol 2, pp 2033–2040
Schiele B, Crowley JL (2000) Recognition without correspondence using multidimensional receptive field histograms. Int J Comput Vis 36(1):31–50
Schwartz WR, Davis LS (2009) Learning discriminative appearance-based models using partial least squares. In: Brazilian symposium on computer graphics and image processing
Seigneur JM, Solis D, Shevlin F (2004) Ambient intelligence through image retrieval. In: International conference on image and video retrieval. Springer, Berlin, pp 526–534
Senior A, Hsu MA R Land Mottaleb, Jain AK (2002) Face detection in color images. IEEE transactions on pattern analysis and machine intelligence 24(5):696–706
Shotton J, Winn J, Rother C, Criminisi A (2006) TextonBoost: joint appearance, shape and context modeling for multi-class object recognition and segmentation. In: Proceedings of the European conference on computer vision, pp 1–15
Song Y, Goncalves L, Perona P (2003) Unsupervised learning of human motion. IEEE Trans Pattern Anal Mach Intell 25(7):814–827
Swain MJ, Ballard DH (1991) Color indexing. Int J Comput Vis 7(1):11–32
Teixeira LF, Corte-Real L (2009) Video object matching across multiple independent views using local descriptors and adaptive learning. Pattern Recognit Lett 30(2):157–167
Truong Cong DN, Achard C, Khoudour L, Douadi L (2009) Video sequences association for people re-identification across multiple non-overlapping cameras. In: Proceedings of the international conference on image analysis and processing
Truong Cong DN, Khoudour L, Achard C, Meurie C, Lezoray O (2010) People re-identification by spectral classification of silhouettes. Signal Process 90(8):2362–2374
Tu PH, Doretto G, Krahnstoever NO, Perera AAG, Wheeler FW, Liu X, Rittscher J, Sebastian TB, Yu T, Harding KG (2007) An intelligent video framework for homeland protection. In: Carapezza EM (ed) Proceedings of SPIE defence and security symposium—unattended ground, sea, and air sensor technologies and applications IX, Orlando, vol 6562
Tuzel O, Porikli F, Meer P (2006) Region covariance: a fast descriptor for detection and classification. In: Proceedings of the European conference on computer vision, pp 589–600
Varma M, Zisserman A (2005) A statistical approach to texture classification from single images. Int J Comput Vis 62:61–81
Vedaldi A, Soatto S (2006) Local features, all grown up. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition, vol 2, pp 1753–1760
Vincent L, Soille P (1991) Watersheds in digital spaces: an efficient algorithm based on immersion simulations. IEEE Trans Pattern Anal Mach Intell 13(6):583–598
Viola P, Jones MJ (2004) Robust real-time face detection. Int J Comput Vis 57:137–154
Wang L, Tan T, Ning H, Hu W (2003) Silhouette analysis-based gait recognition for human identification. IEEE Trans Pattern Anal Mach Intell 25(12):1505–1518
Wang X, Doretto G, Sebastian TB, Rittscher J, Tu PH (2007) Shape and appearance context modeling. In: Proceedings of IEEE international conference on computer vision, pp 1–8
Winn J, Criminisi A, Minka T (2005) Object categorization by learned universal visual dictionary. In: Proceedings of IEEE international conference on computer vision, vol 2, pp 1800–1807
Wolf L, Bileschi S (2006) A critical view of context. Int J Comput Vis 69(2):251–261
Wu H, Liu X, Doretto G (2008) Face alignment using boosted ranking models. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition, pp 1–8
Zhang J, Collins R, Liu Y (2003) Representation and matching of articulated shapes. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition, pp II:342–349
Zhao Q, Tao H (2005) Object tracking using color correlogram. In: IEEE international workshop on visual surveillance and performance evaluation of tracking and surveillance, pp 263–270
Zitnick CL, Jojic N, Kang SB (2005) Consistent segmentation for optical flow estimation. In: Proceedings of IEEE international conference on computer vision, pp 1308–1315
Acknowledgments
The authors are grateful to Xiaogang Wang, Niloofar Gheissari, and Richard Hartley for their valuable contributions to the development of the approaches outlined in this manuscript. This report was prepared by GE GRC as an account of work sponsored by Lockheed Martin Corporation. Information contained in this report constitutes technical information which is the property of Lockheed Martin Corporation. Neither GE nor Lockheed Martin Corporation, nor any person acting on behalf of either; a. Makes any warranty or representation, expressed or implied, with respect to the use of any information contained in this report, or that the use of any information, apparatus, method, or process disclosed in this report may not infringe privately owned rights; or b. Assume any liabilities with respect to the use of, or for damages resulting from the use of, any information, apparatus, method or process disclosed in this report.
Author information
Authors and Affiliations
Corresponding authors
Appendix
Appendix
This appendix first introduces some notation and then gives the proofs of Theorem 1, and Theorem 2. The variable \({\varvec{\nu}}\) can be interpreted as partitioning \({{\mathbb{R}}^k}\) into its 2k open orthants \({O_{{\varvec{\nu}}} \doteq \{ {\mathbf{x}} \in {\mathbb{R}}^k | x_i > 0 \; \hbox{if} \; \nu_i=1, \; \hbox{or} \; x_i < 0 \; \hbox{if} \; \nu_i=0, i=1, \ldots, k \}}\) (see Fig. 5 for an example where k = 2). Let us introduce the notation \(O_{{\varvec{\nu}}}({\mathbf{x}}) \doteq \{ {\mathbf{x}} + {\mathbf{y}} | {\mathbf{y}} \in O_{{\varvec{\nu}}} \},\) and also a function \({\beta_{{\mathbf{x}}} ({\varvec{\nu}}) : {\mathbb{B}}^k \rightarrow {\mathbb{B}},}\) such that: (1) \(\beta_{{\mathbf{x}}} ({\varvec{\nu}} ) = 1\) if x is an adherent pointFootnote 15 for the open set \(D \cap O_{{\varvec{\nu}}}({\mathbf{x}});\) (2) \(\beta_{{\mathbf{x}}} ({\varvec{\nu}} ) = 0\) otherwise (see Fig. 5 for an example where k = 2). It is trivial to prove that: I) \({\mathbf{x}} \in D \setminus \partial D \Longleftrightarrow \beta_{{\mathbf{x}}}({\varvec{\nu}}) = 1 \forall {\varvec{\nu}};\) II) \({\mathbf{x}}\setminus\, D \Longleftrightarrow \beta_{{\mathbf{x}}} ({\varvec{\nu}}) = 0 \forall {\varvec{\nu}}.\) Finally, if \({\varvec{\nu}}_j\) represents j out of the k components of \({\varvec{\nu}},\) and if \({\varvec{\nu}}_{k-j}\) represents the remaining k − j components, then edges and corners of the boundary ∂D are defined as follows: A point \({\mathbf{x}} \in \partial D\) lays on an edge if there exist j components of \({\varvec{\nu}},\) with \(1\, \le\, j \,\le\, k-1,\) such that \(\beta_{{\mathbf{x}}}({\varvec{\nu}})\) does not depend on \({\varvec{\nu}}_{k-j},\) i.e. \(\beta_{{\mathbf{x}}}({\varvec{\nu}}) = \beta_{{\mathbf{x}}}({\varvec{\nu}}_j), \forall {\varvec{\nu}}.\) If x does not lay on an edge, it is a corner. The set of corners of D is indicated with \(\nabla \cdot D.\)
Proof of Theorem 5
Let \({\{u_{i,1}, u_{i,2}, \ldots | u_{i,j} \in {\mathbb{R}}, u_{i,j} < u_{i,j+1}, i = 1, \cdots, k \},}\) be the set of points along { x i }, such that D is made of portions of hyperplanes passing through these points. Fig. 5 illustrates an example for k = 2. The intersection of the hyperplanes with D defines a partition \(D\, \doteq\, \bigcup_{i} R_i\) into rectangular regions {R i }, which allows to write \(\int_D f({\mathbf{x}}) \hbox{d} {\mathbf{x}} = \sum_i \int_{R_i} f({\mathbf{x}}) \hbox{d} {\mathbf{x}},\) and apply Eq. 17 to each term of the summation. By rearranging the terms, and using the function \(\beta_{{\mathbf{x}}}({\varvec{\nu}}),\) the integral can be rewritten as \({\sum_{{\mathbf{x}} \in {\mathcal{D}}} \alpha_D ({\mathbf{x}}) F({\mathbf{x}}),}\) where \({{\mathcal{D}}}\) is the set of all the corner points of the regions {R i } (note that \({\nabla \cdot D \subseteq {\mathcal{D}}}\)), and \(\alpha_D ({\mathbf{x}}) \,\doteq\, \sum_{{\varvec{\nu}}} (-1)^{{\varvec{\nu}}^T {\mathbf{1}}} \beta_{{\mathbf{x}}}({\varvec{\nu}}).\) Now recall that if \({{\mathbf{x}} \in {\mathcal{D}} \setminus \partial D,}\) then \(\beta_{{\mathbf{x}}}({\varvec{\nu}}) = 1,\) which implies \(\alpha_D ({\mathbf{x}}) = 0.\) On the other hand, if x is on an edge, then one can write \(\alpha_D ({\mathbf{x}}) = \sum_{{\varvec{\nu}}_j} (-1)^{{\varvec{\nu}}_j^T {\mathbf{1}}} \beta_{{\mathbf{x}}}({\varvec{\nu}}_j) \sum_{{\varvec{\nu}}_{k-j}} (-1)^{{\varvec{\nu}}_{k-j}^T{\mathbf{1}}} = 0,\) and Eq. 23 is valid. When x is a corner described by \(\beta_{{\mathbf{x}}},\) one should proceed with a direct computation of α D (x). For k = 2, α D (x) is different then zero only for the 10 cases depicted in Fig. 5, in which it assumes the values indicated.□
Proof of Theorem 2
According to Eq. 15, \(\Uptheta\) can be computed by using Eq. 21, and subsequently applying Theorem 1, giving
where
Now note that h(a, p(u)) can be computed through the integral histogram of A
and by applying Theorem 1, resulting in
By combining Eq. 36 with Eq. 34 follows that
From the definition of p(u), it follows that |p(u)| = |p|, and \(\nabla \cdot p({\mathbf{u}}) = \{ {\mathbf{u}}+{\mathbf{y}} |{\mathbf{y}} \in \nabla \cdot p \},\) and also that \(\alpha_{p({\mathbf{u}})} ({\mathbf{u}}+{\mathbf{y}}) = \alpha_{p} ({\mathbf{y}}).\) Therefore, after the change of variable z = u + y, in Eq. 37 it is possible to switch the order between the integral and the summation, yielding
By substituting Eq. 38 into Eq. 33, and by taking into account Eq. 35 follows that Eqs. 24 and 25 are proved. □
Rights and permissions
About this article
Cite this article
Doretto, G., Sebastian, T., Tu, P. et al. Appearance-based person reidentification in camera networks: problem overview and current approaches. J Ambient Intell Human Comput 2, 127–151 (2011). https://doi.org/10.1007/s12652-010-0034-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12652-010-0034-y