Spatial Pyramid-Based Statistical Features for Person Re-Identification: A Comprehensive Evaluation

Si, Jianlou; Zhang, Honggang; Li, Chunguang; Guo, Jun

doi:10.1109/tsmc.2016.2645660

Cited by 16 publications

(6 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous works on person ReID focus on either constructing informative features, or finding a discriminative distance metric. According to the used representation forms in matching stage, we roughly divide the existing methods into two groups: feature vector based methods, e.g., [10,4,19,37,41,17,12,45,35]; and feature set or feature sequence based methods, e.g., [69,60,59,57,36,18,1,38].…”

Section: Related Workmentioning

confidence: 99%

Dual Attention Matching Network for Context-Aware Feature Sequence Based Person Re-identification

Zhang

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

Self Cite

467

200

View full text Add to dashboard Cite

Typical person re-identification (ReID) methods usually describe each pedestrian with a single feature vector and match them in a task-specific metric space. However, the methods based on a single feature vector are not sufficient enough to overcome visual ambiguity, which frequently occurs in real scenario. In this paper, we propose a novel endto-end trainable framework, called Dual ATtention Matching network (DuATM), to learn context-aware feature sequences and perform attentive sequence comparison simultaneously. The core component of our DuATM framework is a dual attention mechanism, in which both intrasequence and inter-sequence attention strategies are used for feature refinement and feature-pair alignment, respectively. Thus, detailed visual cues contained in the intermediate feature sequences can be automatically exploited and properly compared. We train the proposed DuATM network as a siamese network via a triplet loss assisted with a decorrelation loss and a cross-entropy loss. We conduct extensive experiments on both image and video based ReID benchmark datasets. Experimental results demonstrate the significant advantages of our approach compared to the state-of-the-art methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Dual Attention Matching Network for Context-Aware Feature Sequence Based Person Re-identification

Zhang

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

Self Cite

467

200

View full text Add to dashboard Cite

show abstract

“…In [11] saliency matching was proposed based on patch matching in a unified structural RankSVM learning framework for person re-identification. In [12] a spatial pyramid-based statistical feature extraction framework as a unified pipeline was proposed for extracting and combining multiple statistical features for person Re-identification. In this task, five types of spatial pyramid-based statistical features, including spatial pyramid-based color histogram (spHist), spatial pyramid-based histogram of oriented gradient (spHOG) spatial pyramid-based local binary pattern (spLBP), spatial pyramid-based color names (spCNs), spatial pyramid based covariance feature (spCov), and combine them via multiple kernel local Fisher discriminant analysis (mkLFDA) were extracted from images.…”

Section: Related Workmentioning

confidence: 99%

Histogram of the node strength and histogram of the edge weight: two new features for RGB-D person re-identification

Imani

Soltanizadeh

2018

Sci. China Inf. Sci.

View full text Add to dashboard Cite

Person re-identification is a classical task for any multi-camera surveillance system. Most of the existing researches on re-identification are based on features extracted from RGB images. However, there are many deficiencies in RGB image processing, some of which are requiring a lot of illumination and high computation. In this paper, novel features are proposed for RGB-D person re-identification. First, the complex network approach in texture recognition is modified and its threshold function is changed for using in depth images extracted by RGB-D sensors. Then, two novel measurements named the histogram of the edge weight (HEW) and the histogram of the node strength (HNS) are introduced on complex networks. Our features fit both single-shot and multi-shot person re-identification. In the single-shot case, the HNS is extracted from only one frame while for the multi-shot case it is extracted from both one frame and multi-frames. These proposed measurements are called histogram of the spatial node strength (HSNS) and histogram of the temporal node strength (HTNS) respectively. Subsequently, these measurements are combined with skeleton features using score-level fusion. The method is evaluated using two benchmark databases and the results show that ours outperforms some state-of-the-art methods.

show abstract

“…where k ≥ 1 is a preset parameter. The σ 0 defined in (6) roughly encodes the density information in the local neighborhood of x 0 . The advantages of using a smooth kernel function with a density-adaptive parameter are at least twofold: a) the smoothness of the kernel function preserves the ambiguity of the potential candidates in the ranking list; and b) the local density-adaptive parameter endows the kernel function with an individually sample-specific scaling.…”

Section: A Density-adaptive Kernel Functionmentioning

confidence: 99%

“…In the existing works, majority of efforts have been cast into extracting robust and discriminative visual representation. It has been verified that the local features, i.e., color or oriented gradient histogram [2], [3], [4], [5], [6] are effective for person ReID, and combining multiple types of features, i.e., color, texture, and spatial structure, is useful to find more informative matchings [7], [8], [9], [10], [11], [12], [13], [14], [15], [16]. On the other hand, supervised metric R. Guo learning methods-which learn a discriminative distance metric (or equivalently a low-dimensional subspace), in which the samples of same person are closer, could help the task of finding informative matchings [17], [18], [19], [20], [21], [22], [23].…”

Section: Introductionmentioning

confidence: 95%

Density-Adaptive Kernel based Re-Ranking for Person Re-Identification

Guo

et al. 2018

2018 24th International Conference on Pattern Recognition (ICPR)

Self Cite

View full text Add to dashboard Cite

Person Re-Identification (ReID) refers to the task of verifying the identity of a pedestrian observed from nonoverlapping views of surveillance cameras networks. Recently, it has been validated that re-ranking could bring remarkable performance improvements for a person ReID system. However, the current re-ranking approaches either require feedbacks from users or suffer from burdensome computation cost. In this paper, we propose to exploit a density-adaptive smooth kernel technique to perform efficient and effective re-ranking. Specifically, we adopt a smooth kernel function to formulate the neighboring relationship amongst data samples with a density-adaptive parameter. Based on the new formulation, we present two simple yet effective re-ranking methods, termed inverse Density-Adaptive Kernel based Re-ranking (inv-DAKR) and bidirectional Density-Adaptive Kernel based Re-ranking (bi-DAKR), in which the local density information around each gallery sample is elegantly exploited. Moreover, we extend the proposed inv-DAKR and bi-DAKR to incorporate the available extra probe samples and demonstrate that the extra probe samples are able to improve the local neighborhood and thus further refine the ranking result. Extensive experiments are conducted on six benchmark datasets, including PRID450s, VIPeR, CUHK03, GRID, Market-1501 and Mars. Experimental results demonstrate that our proposals are effective and efficient.

show abstract

Spatial Pyramid-Based Statistical Features for Person Re-Identification: A Comprehensive Evaluation

Cited by 16 publications

References 57 publications

Dual Attention Matching Network for Context-Aware Feature Sequence Based Person Re-identification

Dual Attention Matching Network for Context-Aware Feature Sequence Based Person Re-identification

Histogram of the node strength and histogram of the edge weight: two new features for RGB-D person re-identification

Density-Adaptive Kernel based Re-Ranking for Person Re-Identification

Contact Info

Product

Resources

About