Fast person re-identification based on dissimilarity representations

Satta, Riccardo; Fumera, Giorgio; Roli, Fabio

doi:10.1016/j.patrec.2012.03.026

Cited by 51 publications

(45 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Importantly, our method is more flexible since the feature importance is attribute-driven, thus it is not limited to specific gallery. A more recent work in [13] starts to explore prototype relevance for improving processing time in re-identification problem. In contrast, we systematically investigate salient feature importance mining for improving matching accuracy.…”

Section: Introductionmentioning

confidence: 99%

Person Re-identification: What Features Are Important?

Liu¹,

Gong²,

Loy³

et al. 2012

Lecture Notes in Computer Science

249

195

View full text Add to dashboard Cite

Abstract. State-of-the-art person re-identification methods seek robust person matching through combining various feature types. Often, these features are implicitly assigned with a single vector of global weights, which are assumed to be universally good for all individuals, independent to their different appearances. In this study, we show that certain features play more important role than others under different circumstances. Consequently, we propose a novel unsupervised approach for learning a bottom-up feature importance, so features extracted from different individuals are weighted adaptively driven by their unique and inherent appearance attributes. Extensive experiments on two public datasets demonstrate that attribute-sensitive feature importance facilitates more accurate person matching when it is fused together with global weights obtained using existing methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Person Re-identification: What Features Are Important?

Liu¹,

Gong²,

Loy³

et al. 2012

Lecture Notes in Computer Science

249

195

View full text Add to dashboard Cite

show abstract

“…However, an alternative matching framework is presented in [39]. In this framework, individuals are represented by means of a vector of dissimilarity values with a set of stored prototypes.…”

Section: Techniques For Person Re-identificationmentioning

confidence: 99%

Using latent features for short-term person re-identification with RGB-D cameras

Oliver

Albiol

et al. 2015

Pattern Anal Applic

View full text Add to dashboard Cite

This paper presents a system for people re-identification in uncontrolled scenarios using RGB-depth cameras. Compared to conventional RGB cameras, the use of depth information greatly simplifies the tasks of segmentation and tracking. In a previous work, we proposed a similar architecture where people were characterized using colorbased descriptors that we named bodyprints. In this work, we propose the use of latent feature models to extract more relevant information from the bodyprint descriptors by reducing their dimensionality. Latent features can also cope with missing data in case of occlusions. Different probabilistic latent feature models, such as Probabilistic Principal Component Analysis and Factor Analysis, are compared in the paper. The main difference between the models is how the observation noise is handled in each case. Re-identification experiments have been conducted in a real store where people behaved naturally. The results show that the use of the latent features significantly improves the re-identification rates compared to state-of-the-art works.

show abstract

“…The measure of dist (·, ·) is the Hausdorff distance d H [15], [6]. Given two set Q and S, d H is defined as the distance among the minimum distances between all pairs of elements from Q and S. The dist() is defined as the similarity measure of m pairs of parts.…”

Section: K-nn Classifiermentioning

confidence: 99%

“…In our case the images are partitioned into six sub parts and the mixture of color and texture based features are extracted from each part. The partition based distance measure strategy helps to attain robustness to pose variations and experimentally validated in [6]. The result of the similarity measure of the probe is given by the list of the most similar feature vector of the gallery images ordered by increasing dissimilarity.…”

Section: K-nn Classifiermentioning

confidence: 99%

“…The requirement of labeled gallery images to discover gallery specific feature importance are described in [3]. The prototype strategy for re-identification problem is introduced in [6] by defining a set of prototypes for each body part and representing them with dissimilarity vectors. A matching strategy is followed between the probe and gallery images with respect to the dissimilarity.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Person Re-identification Using Clustering Ensemble Prototypes

Nanda

Kumar

2015

Computer Vision - ACCV 2014 Workshops

View full text Add to dashboard Cite

Abstract. This paper presents an appearance-based model to deal with the person re-identification problem. Usually in a crowded scene, it is observed that, the appearances of most people are similar with regard to the combination of attire. In such situation it is a difficult task to distinguish an individual from a group of alike looking individuals and yields an ambiguity in recognition for re-identification. The proper organization of the individuals based on the appearance characteristics leads to recognize the target individual by comparing with a particular group of similar looking individuals. To reconstruct a group of individual according to their appearance is a crucial task for person re-identification. In this work we focus on unsupervised based clustering ensemble approach for discovering prototypes where each prototype represents similar set of gallery image instances. The formation of each prototype depends upon the appearance characteristics of gallery instances. The estimation of k-NN classifier is employed to specify a prototype to a given probe image. The similarity measure computation is performed between the probe and a subset of gallery images, that shares the same prototype with the probe and thus reduces the number of comparisons. Re-identification performance on benchmark datasets are presented using cumulative matching characteristic (CMC) curves.

show abstract

Fast person re-identification based on dissimilarity representations

Cited by 51 publications

References 20 publications

Person Re-identification: What Features Are Important?

Person Re-identification: What Features Are Important?

Using latent features for short-term person re-identification with RGB-D cameras

Person Re-identification Using Clustering Ensemble Prototypes

Contact Info

Product

Resources

About