Learning For Person Re-identification Research Articles

Semi-supervised LDA and Multi-distance Metric Learning for Person Re-identification

The problem of person re-identification has attracted a lot of attention in the field of machine vision. In practice, the non-overlapping sample images change drastically and the sample size is small, which makes the metric model overfitting phenomenon. In this paper, based on the k-NN and the sample normality property, we propose a resampling linear discriminant analysis (LDA) algorithm to suppress the local constraints caused by small samples, then train it to obtain the person re-identification metric learning model. A semi-supervised LDA algorithm with semi-supervised characteristics is developed by optimizing the inter-class scatter for weighting. A joint distance metric-based approach is also proposed to learn both the Mahalanobis distance and Euclidean distance. The improved algorithm is tested on the VIPeR and CUHK01 datasets, and the results indicate that, despite the change in the total number of training samples, the algorithm in this paper shows high recognition accuracy.

A joint structure of multi-distance based metric learning for person re-identification

Person re-identification problem is a valuable computer vision task, which aims at matching pedestrian images of different cameras in a non-overlapping surveillance network. Existing metric learning based methods address this problem by learning a robust distance function. These methods learn a mapping subspace by forcing the distance of the positive pair much smaller than the negative pair by a strict constraint. The metric model is over-fitting to the training dataset. Due to drastic appearance variations, the handcrafted features are weak of representation for person re-identification. To address these problems, we propose a joint distance measure based approach, which learns a Mahalanobis distance and a Euclidean distance with a novel feature jointly. The novel feature is represented with a dictionary representation based method which considers pedestrian images of different camera views with the same dictionary. The joint distance combine the Mahalanobis distance based on metric learning method with the Euclidean distance based on the novel feature to measure the similarity between matching pairs. Extensive experiments are conducted on the publicly available bench marking datasets VIPeR and CUHK01. The identification results show that the proposed method reaches a good performance than the comparison methods.

HOB-net: high-order block network via deep metric learning for person re-identification

HOB-net: high-order block network via deep metric learning for person re-identification

Transductive semi-supervised metric learning for person re-identification

Semi-supervised learning is important and has become more widespread because obtaining labeled data is expensive and labor-intensive. In this paper, we focus on the challenging semi-supervised person Re-identification (ReID) task, which is a metric learning problem based on the assumption that unlabeled data is open-set. To address this problem, we propose the Transductive Semi-Supervised Metric Learning (TSSML) framework. In TSSML, we propose a graph-based transductive hard mining method for deeply mining hard triplets in unlabeled data and a degree-based relationship confidence scoring method for further reducing incorrect triplets. Moreover, we investigate the feature consistency loss (FCL) and adopt the curriculum learning strategy to improve the representation learning for semi-supervised ReID. Extensive experiments have been conducted on three large-scale ReID datasets and demonstrate the effectiveness of our TSSML framework.

Semisupervised Consistent Projection Metric Learning for Person Reidentification.

Person reidentification is a hot topic in the computer vision field. Many efforts have been paid on modeling a discriminative distance metric. However, existing metric-learning-based methods are a lack of generalization. In this article, the poor generalization of the metric model is argued as the biased estimation problem that the independent identical distribution hypothesis is not valid. The verification experimental result shows that there is a sharp difference between the training and test samples in the metric subspace. A semisupervised consistent projection metric-learning method is proposed to ease the biased estimation problem by learning a consistent constrained metric subspace in which the identified pairs are forced to follow the distribution of the positive training pairs. First, a semisupervised method is proposed to generate potential matching pairs from the k -nearest neighbors of test samples. The potential matching pairs are used to estimate the distances' distribution center of the positive test pairs. Second, the metric subspace is improved by forcing this estimation to be close to the center of the positive training pairs. Finally, extensive experiments are conducted on five datasets and the results demonstrate that the proposed method reaches the best performance, especially on the rank-1 identification rate.

Camera viewpoint learning for person reidentification

Camera viewpoint has a great influence on reidentification (re-ID) for its diversity. However, there are few methods in response to it, which limits the development of the re-ID community. We analyze the influence of camera viewpoint on re-ID to obtain both visualization and quantitative results, indicating the potential to solve this problem. On this basis, we propose mean and variance loss function (MVL) and camera ID classifier (CIC). MVL reduces the gap among the mean and variance of the feature vectors of images acquired by different cameras, so that the distribution of image feature vectors under different cameras is similar. CIC filters out the images, which have the same camera id with the query to avoid recognition interference. The experiments are conducted on Market1501 and DukeMTMC-reID datasets. We show that MVL and CIC can mitigate the negative impact of the camera viewpoint for re-ID and further improve the accuracy of re-ID. In the Market1501 dataset, rank-1 [mean average precision score (mAP)] accuracy is improved from 88.1 (71.1) % to 90.0 (73.9) % for ResNet-50. In the DukeMTMC-reID dataset, rank-1 (mAP) accuracy is improved from 77.0 (58.9) % to 83.9 (64.1) % for ResNet-50.

An Adaptive Multi-Projection Metric Learning for Person Re-Identification Across Non-Overlapping Cameras

Person re-identification is one of the most important and challenging problems in video analytics systems; it aims to match people across non-overlapping camera views. For person re-identification, metric learning is introduced to improve the performance by providing a metric adapted for cross-view matching. The essence of metric learning is to search for an optimal projection matrix to project the original features into a new feature space. However, most existing metric learning methods overlook the inconsistency of feature distributions in multiple cameras. In this paper, we propose a multi-projection metric learning (MPML) method to overcome the inconsistency among multiple cameras in person re-identification. Our solution is to jointly learn multiple projection matrices using paired samples from different cameras to project features from different cameras into a common feature space. To make our method adaptive to newly added cameras without affecting the learned projection matrices, we further propose an adaptive MPML method, which can learn new camera projection matrices without having to update any of the obtained projection matrices. The proposed methods are evaluated on four major person re-identification data sets, with comprehensive experiments showing the effectiveness of the proposed methods and notable improvements over the state-of-the–art approaches.

Centralized embedding hypersphere feature learning for person re-identification

ABSTRACTDeep metric learning has become a general method for person re-identification (ReID) recently. Existing methods train ReID model with various loss functions to learn feature representation and identify pedestrian. However, the interaction between person features and classification vectors in the training process is rarely concerned. Distribution of pedestrian features will greatly affect convergence of the model and the pedestrian similarity computing in the test phase. In this paper, we formulate improved softmax function to learn pedestrian features and classification vectors. Our method applies pedestrian feature representation to be scattered across the coordinate space and embedding hypersphere to solve the classification problem. Then, we propose an end-to-end convolutional neural network (CNN) framework with improved softmax function to improve the performance of pedestrian features. Finally, experiments are performed on four challenging datasets. The results demonstrate that our work is competitive compared to the state-of-the-art.

Deep feature learning with mixed distance maximization for person Re-identification

In despite of several advanced approaches, deep learning for person re-identification is still regarded as a challenging task due to local optima in the objective function of the deep networks in addition to various changes of poses and viewpoints etc. We introduced a novel neural network learning, or deep feature learning with mixed distance maximization, to solve the local optima problem in person re-identification. A local objective function is first defined to maximize the intra-distance among a triplet for person re-identification. Also, a global objective function is proposed to consider distances among triplets. Based on two objective functions, a main objective function is introduced to make full use of the information of triplets. This main objective function is defined based on the combination of two distances, called a mixed distance. This mixed distance can prevent that the triplets become close to each other and the matched pairs in each triplets become apart in deep learning with the relative distance comparison. We test our deep method with the mixed distance maximization on several datasets. Experimental results demonstrate that deep feature learning with the mixed distance maximization have promising discriminative capability in comparison with other ones.

Discriminative Structural Metric Learning for Person Reidentification in Visual Internet of Things

Recently, visual Internet of Things (VIoT) has been deployed in many critical missions that are related to society security, such as anti-terrorism, abnormal event detection, crisis monitoring surveillance, etc. In this paper, we focus on a key fundamental problem in VIoT, person reidentification, which aims to correlate people with appropriate labels. The same person captured by various visual sensors in VIoT appears different significantly. To effectively measure the similarity between image pairs, we propose a novel method named discriminative structural metric learning (DSML), which utilizes intraregion metric, weak extra-region metric and extra-region metric to fully mine the structural information of pedestrian in a local way. According to DSML, we obtain a vector where each element is a local similarity score between two subregions. In order to aggregate the local similarity scores into a global one, we further propose a novel aggregating similarity score method named discriminative subregion aggregating (DSA). The DSA could learn the discriminative subregion by assigning different weights for each subregion. The experimental results demonstrate that the proposed method achieves better performance than the state-of-the-art methods.

Joint deep semantic embedding and metric learning for person re-identification

We focus on the person re-identification (re-id) task, whose goal is to automatically re-identify individual persons from multiple non-overlapping cameras or the same camera across time. While most existing works rely on exploring properties of the visual data, we consider taking advantage of both visual and textual representations. Given images and natural language descriptions of the persons in the probe, the re-id system is required to rank all the samples in the gallery set. We embed the visual representations and textual descriptions in a unified space, in which we map similar examples close to each other and map dissimilar examples farther apart. Our premise is that, in general, strong semantic correlations exist between different persons. The space casts a person in gallery set as a combination of the persons in probe set. The model is trained in an end-to-end fashion. We conduct extensive experiments on the challenging i-LIDS, PRID-2011, CUHK03 and Market-1501 datasets, and confirm that the proposed model achieves state-of-the-art performances.

Multi-Level Common Space Learning for Person Re-Identification

Matching people in different cameras, commonly referred to as person re-identification, is a challenging task. The challenges come from the drastic appearance variation across different camera views caused by changes in pose, lighting condition, occlusion, background, and so on. Instead of matching images in the original feature space, many existing methods learn distance metrics or feature transformations to improve the matching accuracy. For example, data from different camera views can be projected onto their common space to mitigate the feature gap caused by view discrepancy. However, a single-step mapping may not be sufficient to close this gap as the view difference can be significant between different cameras. To overcome this limitation, we propose a multi-level common space learning framework, which can gradually minimize the data discrepancy between different views in an iterative manner. At each intermediate level, synthetic data are generated using the automatically discovered grouping information, and these synthetic data can be viewed as a transitional state between the original camera views. The matching is performed by mapping the probe and gallery onto their common space in multiple steps. We evaluate the proposed method on two widely used person re-identification data sets. The results show that the proposed multi-level scheme significantly outperforms single-level mapping. In addition, competitive results are achieved as compared with over 20 state-of-the-art techniques.

Accelerated low-rank sparse metric learning for person re-identification

Person re-identification is an open and challenging problem in computer vision. A surge of effort has been spent design the best feature representation, and to learn either the transformation of such features across cameras or an optimal matching metric. Metric learning solutions which are currently in vogue in the field generally require a dimensionality reduction pre-processing stage to handle the high-dimensionality of the adopted feature representation. Such an approach is suboptimal and a better solution can be achieved by combining such a step in the metric learning process. Towards this objective, a low-rank matrix which projects the high-dimensional vectors to a low-dimensional manifold with a discriminative Euclidean distance is introduced. The goal is achieved with a stochastic accelerated proximal gradient method. Experiments on two public benchmark datasets show that better performances than state-of-the-art methods are achieved.

Dual Regularized KISS Metric Learning for Person Reidentification

Dual Regularized KISS Metric Learning for Person Reidentification

WITHDRAWN: Cross-scenario transfer metric learning for person re-identification

WITHDRAWN: Cross-scenario transfer metric learning for person re-identification

Semi-supervised Region Metric Learning for Person Re-identification

In large-scale camera networks, label information for person re-identification is usually not available under a large amount of cameras due to expensive human labor efforts. Semi-supervised learning could be employed to train a discriminative classifier by using unlabeled data and unmatched image pairs (negatives) generated from non-overlapping camera views, but existing methods suffer from the problem of imbalanced unlabeled data. In this context, this paper proposes a novel semi-supervised region metric learning method to improve person re-identification performance under imbalanced unlabeled data. Firstly, instead of seeking for matched image pairs (positives) from the unlabeled data, we propose to estimate positive neighbors by label propagation with cross person score distribution alignment. Secondly, multiple positive regions are generated using sets of positive neighbors to learn a discriminative region-to-point metric. Experimental results demonstrate that the superiority of the proposed method over existing unsupervised, semi-supervised and person re-identification methods.

Deep feature learning for person re-identification in a large-scale crowdsourced environment

Finding the same individual across cameras in disjoint views at different locations and times, which is known as person re-identification (re-id), is an important but difficult task in intelligent visual surveillance. However, to build a practical re-id system for large-scale and crowdsourced environments, the existing approaches are largely unsuitable because of their high model complexity. In this paper, we present a deep feature learning framework for automated large-scale person re-id with low computational cost and memory usage. The experimental results show that the proposed framework is comparable to the state-of-the-art methods while having low model complexity.

Unsupervised metric learning for person re-identification by image re-ranking

Person re-identification is an important and challenging problem in video surveillance. Most of the methods are based on supervised distance metrics learning, which have to label samples for distance metrics learning, while it is hardly done in massive cameras. This paper carried out an unsupervised distance metric learning method based on image re-ranking. This method calculates original distance matrix for samples from two cameras using original distance metric function, and re-ranking distance matrix to acquire a better distance function, then new distance rank matrix is calculated. This matrix is used to label positive and negative samples automatically, doing unsupervised distance metric learning, and acquire a better Mahalanobis distance metric function, without the need to manually label samples. Experiments are done on public datasets, and result is evaluated by CMC, which indicates this algorithm could overcome the difficulties of labelling massive samples, with a better re-identification rate than other algorithms.

Unsupervised metric learning for person re-identification by image re-ranking

Unsupervised metric learning for person re-identification by image re-ranking

Equidistance constrained metric learning for person re-identification

Person re-identification (re-id), aiming to search a specific person among a non-overlapping camera network, has attracted plenty of interest in recent years. This task is highly challenging, especially when there exists only single image per person in the database. In this paper, we present an algorithm for learning a Mahalanobis distance for person re-identification. Our method has two distinctive features: (1) to obtain the best separability of the training data, we first minimize the intra-class distances to the most extent by forcing intra-class distances to be zero, and (2) to promote the generalization ability of the learned metric, we then maximize the minimum margin between different classes. Inspired by the simple geometric intuition that a regular simplex maximizes its minimum side length, provided the sum of all side length is fixed, our method, called EquiDistance constrained Metric Learning (EquiDML), applies least-square regression technique to map images of the same person to the same vertex of a regular simplex, and images of different persons to different vertices of a regular simplex. Consequently, under the learned metric, images of the same class are collapsed to a single point, while images of different classes are transformed to be equidistant. This simple motivation is further formulated as a convex optimization problem, solved by the projected gradient descent method and proved to be very effective in person re-identification task. Although it is fairly simple, our method outperforms the state-of-the-art methods on CUHK01, CUHK03, Market1501 and DukeMTMC-reID datasets, and achieves very competitive performance on the widely used VIPeR dataset.