Search

In person reidentification (PReID) tasks, challenges such as occlusion and small object sizes frequently arise. High-precision object detection methods can accurately locate small objects, while attention mechanisms help focus on the strong feature regions of objects. These approaches mitigate the mismatches caused by occlusion and small objects to some extent. This paper proposes a PReID method based on object detection and attention mechanisms (ODAMs) to achieve enhanced object matching accuracy. In the proposed ODAM-based PReID system, You Only Look Once version 7 (YOLOv7) was utilized as the detection algorithm, and a size attention mechanism was integrated into the backbone network to further improve the detection accuracy of the model. To conduct feature extraction, ResNet-50 was employed as the base network and augmented with residual attention mechanisms (RAMs) for PReID. This network emphasizes the key local information of the target object, enabling the extraction of more effective features. Extensive experimental results demonstrate that the proposed method achieves a mean average precision (mAP) value of 90.1% and a Rank-1 accuracy of 97.2% on the Market-1501 dataset, as well as an mAP of 82.3% and a Rank-1 accuracy of 91.4% on the DukeMTMC-reID dataset. The proposed PReID method offers significant practical value for intelligent surveillance systems. By integrating multiscale attention and RAMs, this method enhances both its object detection accuracy and its feature extraction robustness, enabling a more efficient individual identification process in complex scenes. These improvements are crucial for enhancing the real-time performance and accuracy of video surveillance systems, thus providing effective technical support for intelligent monitoring and security applications. [ABSTRACT FROM AUTHOR]

Copyright of Afyon Kocatepe University Journal of Science & Engineering / Afyon Kocatepe Üniversitesi Fen Ve Mühendislik Bilimleri Dergisi is the property of Afyon Kocatepe University, Faculty of Science & Literature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Identifying pedestrians in video sequences captured by non-overlapping multi-cameras is referred to as video-based Person Re-identification. The successive video frames in video clips embrace motion patterns of pedestrians and represent a person's appearance from varying angles with different body poses and, thus, provide critical features to counter occlusion, pose variation, viewpoint change, etc. This article proposes a novel person reidentification methodology, which incorporates a 3D Inception-based Person Re-identification model, which embraces four three-dimensional (3D) Inception modules with 3D convolution and pooling layers. The receptive fields of neurons are well expanded through 3D inception modules in both temporal and spatial dimensions. Due to this, the model learns discriminatory appearance along with pedestrians' long-term and short-term motion patterns without any motion approximation module. Further, the model is trained with a unified loss function integrating center loss with usual identification loss to reduce intra-class difference while increasing inter-class difference. Further, the proposed method incorporates an attribute recognition model to identify discriminatory attributes in the video frames. The Spatio-temporal and attribute features are then utilized by a reranking method, which generates the k-most similar video clips for the given input. The effectiveness of the proposed method is validated by performing extensive experiments over three realistic surveillance video datasets; MARS, DukeMTMC-VideoReID, and iLIDS. [ABSTRACT FROM AUTHOR]

Person reidentification (re-ID) is an important topic in computer vision. This paper studies an unsupervised approach to re-ID, which does not require any labeled information and is thus possible to deploy in real-world scenarios. State-of-the-art unsupervised re-ID methods usually use a memory bank to store the instance feature vectors, generate pseudolabels with a clustering algorithm, and compare the query instances to the centroid of the clusters for contrastive learning. However, because hard negative or noisy samples exist, the centroid generated by unsupervised learning may not be a perfect prototype. Forcing the wrong images to get closer to the centroid would result in accumulated errors and deteriorated overfitting. To solve this problem, we propose a quantitative random selection strategy to form the cluster feature representation. Specifically, in each iteration, the cluster algorithm executes on instance-level feature vectors to generate pseudolabels. Then, we shuffle all the instance vectors belonging to the same cluster and select samples within the same cluster in a certain proportion to form the cluster-level memory. During network training, the query instances are used to update the cluster-level memory for contrastive learning. Extensive experiments show that our proposed method produces state-of-the-art performance in unsupervised person re-ID tasks. [ABSTRACT FROM AUTHOR]

Efficient contact tracing is a crucial step in preventing the spread of COVID-19. However, the current methods rely heavily on manual investigation and truthful reporting by high-risk individuals. Mobile applications and Bluetooth-based contact tracing methods have also been adopted, but privacy concerns and reliance on personal data have limited their effectiveness. To address these challenges, in this paper, a geospatial big data method that combines person reidentification and geospatial information for contact tracing is proposed. The proposed real-time person reidentification model can identify individuals across multiple surveillance cameras, and the surveillance data is fused with geographic information and mapped onto a 3D geospatial model to track movement trajectories. After real-world verification, the proposed method achieves a first accuracy rate of 91.56%, a first-five accuracy rate of 97.70%, and a mean average precision of 78.03% with an inference speed of 13 ms per image. Importantly, the proposed method does not rely on personal information, mobile phones, or wearable devices, avoiding the limitations of existing contact tracing schemes and providing significant implications for public health in the post-COVID-19 era.

Person reidentification (re-ID) has been receiving increasing attention in recent years due to its importance for both science and society. Machine learning (particularly Deep Learning (DL)) has become the main re-ID tool that has allowed to achieve unprecedented accuracy levels on benchmark datasets. However, there is a known problem of poor generalization in respect of DL models. That is, models that are trained to achieve high accuracy on one dataset perform poorly on other ones and require re-training. In order to address this issue, we present a model without trainable parameters. This, in turn, results in a great potential for high generalization. This approach combines a fully analytical feature extraction and similarity ranking scheme with DL-based human parsing wherein human parsing is used to obtain the initial subregion classification. We show that such combination, to a high extent, eliminates the drawbacks of existing analytical methods. In addition, we use interpretable color and texture features that have human-readable similarity measures associated with them. In order to verify the proposed method we conduct experiments on Market1501 and CUHK03 datasets, thus achieving a competitive rank-1 accuracy comparable with that of DL models. Most importantly, we show that our method achieves 63.9% and 93.5% rank-1 cross-domain accuracy when applied to transfer learning tasks, while also being completely re-ID dataset agnostic. We also achieve a cross-domain mean average precision (mAP) that is higher than that of DL models in some experiments. Finally, we discuss the potential ways of adding new features to further improve the model. We also show the advantages of interpretable features for the purposes of constructing human-generated queries from verbal descriptions in order to conduct searches without a query image. [ABSTRACT FROM AUTHOR]

Deep learning has shown significant successes in person reidentification (re-id) tasks. However, most existing works focus on discriminative feature learning and impose complex neural networks, suffering from low inference efficiency. In fact, feature extraction time is also crucial for real-world applications and lightweight models are needed. Prevailing pruning methods usually pay attention to compact classification models. However, these methods are suboptimal for compacting re-id models, which usually produce continuous features and are sensitive to network pruning. The key point of pruning re-id models is how to retain the original filter distribution in continuous features as much as possible. In this work, we propose a blockwise adjacent filter decaying method to fill this gap. Specifically, given a trained model, we first evaluate the redundancy of filters based on the adjacency relationships to preserve the original filter distribution. Second, previous layerwise pruning methods ignore that discriminative information is enhanced block-by-block. Therefore, we propose a blockwise filter pruning strategy to better utilize the block relations in the pretrained model. Third, we propose a novel filter decaying policy to progressively reduce the scale of redundant filters. Different from conventional soft filter pruning that directly sets the filter values as zeros, the proposed filter decaying can keep the pretrained knowledge as much as possible. We evaluate our method on three popular person reidentification datasets, that is: 1) Market-1501; 2) DukeMTMC-reID; and 3) MSMT17_V1. The proposed method shows superior performance to the existing state-of-the-art pruning methods. After pruning over 91.9% parameters on DukeMTMC-reID, the Rank-1 accuracy only drops 3.7%, demonstrating its effectiveness for compacting person reidentification. [ABSTRACT FROM AUTHOR]

Currently, deep learning is the mainstream method to solve the problem of person reidentification. With the rapid development of neural networks in recent years, a number of neural network frameworks have emerged for it, so it is becoming more important to explore a simple and efficient baseline algorithm. In fact, the performance of the same module varies greatly in different positions of the network architecture. After exploring how modules can play a maximum role in the network and studying and summarizing existing algorithms, we designed an adaptive multiple loss baseline (AML) with a simple structure but powerful functions. In this network, we use an adaptive mining sample loss (AMS) and other modules, which can mine more information from input samples at the same time. Based on triplet loss, AMS loss can optimize the distance between the input sample and its positive and negative samples and protect structural information within the sample. During the experiment, we conducted several group tests and confirmed the high performance of AML baseline via the results. AML baseline has outstanding performance in three commonly used datasets. The two indicators of AML baseline on CUHK-03 are 25.7% and 26.8% higher than BagTricks. [ABSTRACT FROM AUTHOR]

Person reidentification (P-Reid) is an emerging research domain in the field of information retrieval that has gained exponential growth due to its wide range of applications in pedestrian tracking and crime prevention. The primary goal of P-Reid is to recognize a person based on previous appearance in multiview surveillance videos. The mainstream approaches apply fully supervised learning techniques that have poor scalability when deployed in complex real-world scenes, due to the overfitting problem, caused by the lack of sufficient annotated data. Further, optimization of these models for unlabeled data in real-time surveillance is a challenging task. To tackle these issues, an intelligent framework (LR-Net) is proposed, consisting of three tiers including fine-tuning (FT), siamese network (SN), and fusion strategy (FS). In the first tier, a deep learning model is fine-tuned for P-Reid that can handle both labeled and unlabeled data. Next, with the assistance of transfer learning, an SN is proposed that has a strong discriminative capability in terms of similarity between a pair of images. Finally, a learning-to-rank strategy is applied to optimize the learning capability of the SN, in which a triplet network extracts spatial-temporal patterns from unlabeled samples. In addition, a bayesian fusion model (BFM) is introduced to integrate the spatiotemporal and visual features, which yields 4.4%, 9.3%, and 0.8% improvement in the matching score over Market-1501, DukeMCMT-reID, and CUHK03 data sets, respectively. The conducted experiments and ablation study on the benchmark data sets empirically validate the proposed system, which obtains a high Rank-1 score as compared with the state-of-the-art (SOTA) methods. [ABSTRACT FROM AUTHOR]

Abstract Person reidentification rate has become a challenging research topic in the field of computer vision due to the fact that person appearance is easily affected by lighting, posture and perspective. In order to make full use of the continuity of video data on the time line and the unstructured relationship of features, a video person reidentification algorithm combining the neural ordinary differential equation with the graph convolution network is proposed in this paper. First, a continuous time model is constructed by using the ordinary differential equation (ODE) network so as to capture hidden information between video frames. By simulating the hidden space of the hidden variables with the hidden time series model, the hidden information between frames that may be ignored in the discrete model can be obtained. Then, the features of the generated video frames are given to the graph convolution network to reconstruct them. Finally, weak supervision is used to classify the features. Experiments on PRID2011 datasets show that the proposed algorithm can significantly improve person reidentification performance.

The goal of domain-generalized person reidentification (DG-ReID) is to train a model in the source domain and apply it directly to unknown target domains for specific pedestrian retrieval. Existing methods rely primarily on low-order statistics (such as the mean, standard deviation, or variance), thereby ensuring the stability of the source domain data distribution for model training. However, such methods underperform when the data follow a non-Gaussian distribution, thereby reducing the generalization ability of the model on unseen target domains. To address this issue, this study proposes an instance normalization-based skewness regularity (INSR) framework that uses high-order statistics (skewness and high-order moments) to measure the skewness and regularity of the data distribution. Such measures allow further learning of the morphological features (skewness degree, trait of data near the mean, etc.) of complex data distributions for DG-ReID. Specifically, the proposed framework first extracts the skewness and third-order moments from the source domains, which provide more features (high-order moments, variance, etc.) to characterize the data distribution. Subsequently, a batch normalization-like operation was implemented to project the data into a new feature space with zero mean and unit variance, enhancing model adaption and accuracy. Extensive experiments were conducted on small-scale (VIPeR, PRID, GRID, and i-LIDS) and large-scale (Market-1501, DukeMTMC-reID, CUHK03, MSMT17) public datasets using two different protocols, demonstrating that the proposed INSR framework significantly outperforms other state-of-the-art counterparts for DG-ReID. [ABSTRACT FROM AUTHOR]

Sistem pengawasan berbasis CCTV telah banyak digunakan untuk memantau tempat umum, sehingga keamanan dan kenyamanan lebih terjamin. Salah satu permasalahan pada proses pengawasan adalah mengidentifikasi objek manusia pada kamera CCTV yang berbeda, yang disebut sebagai person reidentification (Re-ID). Re-ID adalah proses untuk mengidentifikasi gambar objek manusia, yang berasal dari dua citra atau lebih yang berada di sudut pandang kamera CCTV berbeda, adalah orang yang sama atau tidak. Pada makalah ini diusulkan metode berbasis fitur visual dari citra objek dengan nama Bag of Visual Feature (BOVF). BOVF bekerja dengan merepresentasikan data sebagai kumpulan fitur lokal yang digunakan dengan mekanisme pengelompokan fitur (feature clustering). Implementasi BOVF menggunakan algoritme pengelompokan fitur Density Based Spatial Clustering of Applications with Noise (DBSCAN) pada proses pelatihan model citra dengan mempelajari fitur Histogram of Oriented Gradient (HOG). Hasil dari penelitian yang menggunakan dataset sebanyak 70 citra frame dari dataset iLIDS-VID ini mendapatkan akurasi terbaik pada R-20 sebesar 88% menggunakan DBSCAN dengan kecepatan proses sebesar 1,85 detik.

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. [ABSTRACT FROM AUTHOR]

The system for re-identifying persons is used to find and verify the persons crossing through different spots using various cameras. Much research has been done to re-identify the person by utilising features with deep-learned or hand-crafted information. Deep learning techniques segregate and analyse the features of their layers in various forms, and the output is complex feature vectors. This paper proposes a distinctive framework called Integrated Level Feature Pattern (ILFP) framework, which integrates local and global features. A new deep learning architecture named modified XceptionNet (m-XceptionNet) is also proposed in this work, which extracts the global features effectively with lesser complexity. The proposed framework gives better performance in Rank1 metric for Market1501 (96.15%), CUHK03 (82.29%) and the newly created NEC01 (96.66%) datasets than the existing works. The mean Average Precision (mAP) calculated using the proposed framework gives 92%, 85% and 98%, respectively, for the same datasets. [ABSTRACT FROM AUTHOR]

Person reidentification (re-ID) has been receiving increasing attention in recent years due to its importance for both science and society. Machine learning (particularly Deep Learning (DL)) has become the main re-ID tool that has allowed to achieve unprecedented accuracy levels on benchmark datasets. However, there is a known problem of poor generalization in respect of DL models. That is, models that are trained to achieve high accuracy on one dataset perform poorly on other ones and require re-training. In order to address this issue, we present a model without trainable parameters. This, in turn, results in a great potential for high generalization. This approach combines a fully analytical feature extraction and similarity ranking scheme with DL-based human parsing wherein human parsing is used to obtain the initial subregion classification. We show that such combination, to a high extent, eliminates the drawbacks of existing analytical methods. In addition, we use interpretable color and texture features that have human-readable similarity measures associated with them. In order to verify the proposed method we conduct experiments on Market1501 and CUHK03 datasets, thus achieving a competitive rank-1 accuracy comparable with that of DL models. Most importantly, we show that our method achieves 63.9% and 93.5% rank-1 cross-domain accuracy when applied to transfer learning tasks, while also being completely re-ID dataset agnostic. We also achieve a cross-domain mean average precision (mAP) that is higher than that of DL models in some experiments. Finally, we discuss the potential ways of adding new features to further improve the model. We also show the advantages of interpretable features for the purposes of constructing human-generated queries from verbal descriptions in order to conduct searches without a query image.

Multiscale features have attracted widespread attention in person reidentification due to their capability to enhance the model information processing. However, the use of multiscale features often leads to model redundancy and low operational efficiency, greatly affecting the practical application of person reidentification. To address the above issue, we propose an efficient and lightweight multiscale network for person reidentification. Specifically, we construct a baseline network for lightweight person reidentification called the multiscale efficient network (MSENet). It comprises three primary stages, with each stage employing the multiscale efficient block, consisting of varying numbers of lightweight efficient convolution blocks. The proposed network efficiently achieves pedestrian image retrieval while maintaining low model complexity. Subsequently, we propose a lightweight pyramid feature fusion module to aggregate multilayer features of the MSENet, enhancing feature diversity and obtaining robust features. Finally, we design a contour branch that focuses on the overall feature extraction of pedestrian images, effectively reducing the interference of background information. Extensive experiments conducted on three popular datasets have demonstrated that the proposed method has excellent recognition accuracy and low model complexity. [ABSTRACT FROM AUTHOR]

Person reidentification (ReID) is a challenging task of finding a target pedestrian in a gallery set collected from multiple nonoverlapping camera views. Recently, state-of-the-art ReID performance has been achieved via an end-to-end trainable deep neural network framework, which integrates convolution feature extraction, similarity learning and reranking into a joint optimization framework. In such a framework, the similarity is learned via an embedding network, the reranking is conducted with a random walk, and the whole framework is optimized with a cross-entropy-based verification loss. Unfortunately, the embedding net is difficult to train well because their two-dimensional outputs mutually interfere each other when using the conventional random walk. In addition, the supervision information has not been fully exploited during the training phase due to the binary nature of the verification loss. In this paper, we propose a novel approach, called group-shuffling dual random walks with label smoothing (GSDRWLS), in which random walks are performed separately on two channels-one for positive verification and one for negative verification-and the binary verification labels are properly modified with an adaptive label smoothing technique before feeding into the verification loss in order to train the overall network effectively and to avoid the overfitting problem. Extensive experiments conducted on three large benchmark datasets, including CUHK03, Market-1501 and DukeMTMC, confirm the superior performance of our proposal.

Person reidentification rate has become a challenging research topic in the field of computer vision due to the fact that person appearance is easily affected by lighting, posture and perspective. In order to make full use of the continuity of video data on the time line and the unstructured relationship of features, a video person reidentification algorithm combining the neural ordinary differential equation with the graph convolution network is proposed in this paper. First, a continuous time model is constructed by using the ordinary differential equation (ODE) network so as to capture hidden information between video frames. By simulating the hidden space of the hidden variables with the hidden time series model, the hidden information between frames that may be ignored in the discrete model can be obtained. Then, the features of the generated video frames are given to the graph convolution network to reconstruct them. Finally, weak supervision is used to classify the features. Experiments on PRID2011 datasets show that the proposed algorithm can significantly improve person reidentification performance. [ABSTRACT FROM AUTHOR]

A mass of information grows explosively in socially networked industries, as extensive data, such as images and texts, is captured by vast sensors. Pedestrians are the main initiators of various activities in socially networked industries, hence, it is very important to quickly obtain relevant information of pedestrians from a large number of images. Person reidentification is an image retrieval technology, which can immediately retrieve target person in abundant images. However, due to the complexity of many important factors especially of changeful poses, occlusion and background clutter, person reidentification still faces extensive challenges. Considering these challenges, robust and distinguishing person representations are hard to be extracted well to identify different people. In this paper, to obtain more discriminative representations, we propose a human body multiple parts parsing (BMPP) architecture, which captures local pixel-level representations from body parts and global representations from whole body simultaneously. Additionally, a straightforward preprocessing method is adopted in this paper to improve the resolution of images in person reidentification benchmarks. To eliminate the negative effects of changeful poses, a simple yet effective representation fusion strategy is used for the original and horizontally flipped images to get final representations. Experimental results indicate that the method proposed in this article attains superior performance to most of state-of-the-art methods on CUHK03 and Market-1501.

Person reidentification (ReID) refers to the task of verifying the identity of a pedestrian observed from nonoverlapping views in a surveillance camera network. It has recently been validated that reranking can achieve remarkable performance improvements in person ReID systems. However, current reranking approaches either require feedback from users or suffer from burdensome computational costs. In this paper, we propose to exploit a density-adaptive smooth kernel technique to achieve efficient and effective reranking. Specifically, we adopt a smooth kernel function to formulate the neighbor relationships among data samples with a density-adaptive parameter. Based on this new formulation, we present two simple yet effective reranking methods, termed inverse density-adaptive kernel based reranking (inv-DAKR) and bidirectional density-adaptive kernel based reranking (bi-DAKR), in which the local density information in the vicinity of each gallery sample is elegantly exploited. Moreover, we extend the proposed inv-DAKR and bi-DAKR methods to incorporate the available extra probe samples and demonstrate that when and why these extra probe samples are able to improve the local neighborhood and thus further refine the ranking results. Extensive experiments are conducted on six benchmark datasets, including: PRID450s, VIPeR, CUHK03, GRID, Market-1501 and Mars. The experimental results demonstrate that our proposals are effective and efficient. [ABSTRACT FROM AUTHOR]

Person reidentification (Re-ID) is an important task in computer vision and has many applications in video-based surveillance. Recently, the triplet loss has been popular in the deep learning framework for person Re-ID. It is particularly important to note that the selection of hard triplets has significant influence on the performance of the learned deep model. However, the existing triplet losses only focus on some specific forms of hard triplets, thus leading to weaker generalization capability. To address this issue, we propose a novel variant of the triplet loss, named exhaustive hard triplet mining loss (EHTM), which is able to deal with various forms of hard triplets in a comprehensive manner. Moreover, the proposed loss comprises a term to facilitate distinguishing different identities by directly narrowing intraclass distances and indirectly enlarging interclass distances. We also provide an effective training strategy to further enhance model performance. Extensive experiments on several benchmark datasets show that our method outperforms state-of-the-art approaches by a large margin. [ABSTRACT FROM AUTHOR]

Distance metric learning has achieved great success in person re‐identification. Most existing methods that learn metrics from pairwise constraints suffer the problem of imbalanced data. In this study, the authors present a large margin relative distance learning (LMRDL) method which learns the metric from triplet constraints, so that the problem of imbalanced sample pairs can be bypassed. Different from existing triplet‐based methods, LMRDL employs an improved triplet loss that enforces penalisation on the triplets with minimal inter‐class distance, and this leads to a more stringent constraint to guide the learning. To suppress the large variations of pedestrian's appearance in different camera views, the authors propose to learn the metric over the intra‐class subspace. The proposed method is formulated as a logistic metric learning problem with positive semi‐definite constraint, and the authors derive an efficient optimisation scheme to solve it based on the accelerated proximal gradient approach. Experimental results show that the proposed method achieves state‐of‐the‐art performance on three challenging datasets (VIPeR, PRID450S, and GRID).

• The global optimization under temporal-spatial and network consistence constraints. • Integer Programming based reranking on similarity scores matrices. • Tradeoff between the person appearance and temporal-spatial information. • Solving generalized situation by introducing topology information. Recent research of person Re-identification (ReID) most focuses on exploring person appearance feature and distance measure between specific camera pair, and seldom considers complex camera network consistence and physical information as supplemental factors for improving the re-identification performance. In this paper, a re-ranking optimization framework under temporal-spatial information and common network consistency constraints is proposed to compensate the accuracy deterioration caused by appearance only based ReID methods in all pairwise cameras. Firstly, a correction function is introduced for describing the influence factor of temporal-spatial information on similarity scores. Then the amended similarity score strategy is provided to tradeoff between the person appearance and temporal-spatial information. Finally the global optimization problem of the jointing temporal-spatial and common consistence constraints is solved by integer programming algorithm. Furthermore, we try to solve the generalized situation where cameras and persons are more random by introducing topology information according to geometry around the cameras, taking the place of network consistency. The experiment results validate that the proposed framework significantly improves performance compared to the other person re-identification methods on the multi-cameras RAiD dataset and TMin dataset both in simple and generalized camera network. [ABSTRACT FROM AUTHOR]

Existing efforts on person reidentification (re-ID) either ignore the structural interactions among person images or require a highly crafted re-ID structure as a priori information. In contrast, our approach formulates person re-ID as a deep structured prediction problem that outperforms the state-of-the-art methods by utilizing neural-style-transfer-based structure sampling and fully parameterized energy networks. [ABSTRACT FROM AUTHOR]

Video-based person reidentification is a challenging and important task in surveillance-based applications. Toward this, several shallow and deep networks have been proposed. However, the performance of existing shallow networks does not generalize well on large datasets. To improve the generalization ability, we propose a shallow end-to-end network which incorporates two stream convolutional neural networks, discriminative visual attention and recurrent neural network with triplet and softmax loss to learn the spatiotemporal fusion features. To effectively use both spatial and temporal information, we apply spatial, temporal, and spa- tiotemporal pooling. In addition, we contribute a large dataset of airborne videos for person reidentification, named DJI01. It includes various challenging conditions, such as occlusion, illuminationchanges, people with similar clothes, and the same people on different days. We perform elaborate qualitative and quantitative analyses to demonstrate the robust performance of the proposed model. [ABSTRACT FROM AUTHOR]

A multi‐directional salience based similarity evaluation for person re‐identification (re‐id) is presented. After distribution analysis for salience consistency between image pairs, a similarity between matched patches is established by weighted fusion of multi‐directional salience. The weight of saliency in each direction is obtained using metric learning by means of structural support vector machines ranking. The discriminative and accurate performance of re‐id is achieved. Compared with existing salience based person matching framework, the proposed method achieves higher re‐id rate with multi‐directional salience based similarity evaluation.

Person re-identification (Re-ID) is a fundamental subject in the field of the computer vision technologies. The traditional methods of person Re-ID have difficulty in solving the problems of person illumination, occlusion and attitude change under complex background. Meanwhile, the introduction of deep learning opens a new way of person Re-ID research and becomes a hot spot in this field. This study reviews the traditional methods of person Re-ID, then the authors focus on the related papers about different person Re-ID frameworks on the basis of deep learning, and discusses their advantages and disadvantages. Finally, they propose the direction of further research, especially the prospect of person Re-ID methods based on deep learning.

Sparse representation (SR) has shown great potential in multishot person reidentification. However, conventional SR methods usually encode each probe image individually, which ignores the prior knowledge shared by similar probe images with the same identity. Considering that probe images with the same identity are similar and can be complementary to each other, we propose a joint group sparse representation (JGSR) method to simultaneously encode a set of probe person images with the same identity. Additionally, we consider the fact that prior knowledge is also contained in the set of images with the same identity in the gallery. In JGSR, probe images with the same identity are coded on the same dictionary atoms and shared similar coefficients. Furthermore, the person reidentification performance is also improved by incorporating JGSR with k-means clustering and kernel local Fisher discriminant analysis into a unified framework. Extensive experiments on three publicly available iLIDS-VID, PRID 2011, and SAIVT-SoftBio multishot benchmark datasets were conducted and demonstrated the superior performance of the JGSR method in comparison with current state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Person reidentification is the process of matching individuals from images taken of them at different times and often with different cameras. To perform matching, most methods extract features from the entire image; however, this gives no consideration to the spatial context of the information present in the image. We propose using a convolutional neural network approach based on ResNet-50 to predict the foreground of an image: the parts with the head, torso, and limbs of a person. With this information, we use the LOMO and salient color name feature descriptors to extract features primarily from the foreground areas. In addition, we use a distance metric learning technique (XQDA), to calculate optimally weighted distances between the relevant features. We evaluate on the VIPeR, QMUL GRID, and CUHK03 data sets and compare our results against a linear foreground estimation method, and show competitive or better overall matching performance. © 2018 SPIE and IS&T [DOI: 10.1117/1.JEI.27.5.051215] [ABSTRACT FROM AUTHOR]

Person reidentification matches person observations captured by nonoverlapping cameras at different times and locations. Due to the appearance variations caused by view angle, pose, lighting, background, and occlusion, person reidentification is a challenging task. To improve the accuracy of person reidentification, this paper proposes a metric learning method. The main idea of our method is to learn a low-dimensional metric space, in which the features extracted from different observations of the same person are pulled, and the features extracted from observations of different persons but in the neighborhood of original feature space are pushed. Then all the features are projected to this metric space for matching. Compared with other metric learning methods, our method differentiates negative samples according to their importances in constructing the metric space, and pays more attention to restrain the more confusable negative pairs. Moreover, our method can simultaneously learn a uniform metric space for multiple features that is practical for multifeature fusion, an effective way to improve reidentification performance. Experimental results on three popular data sets show that our method is more robust against appearance changes and it outperforms other state-of-the-art reidentification methods. [ABSTRACT FROM AUTHOR]

Re‐identification enables the tracking of the person taken from different disjoint camera aspects either from online or retrospectively for recognition of his or her visual appearance. Here a new method is proposed for person re‐identification, taking into consideration the pose of the person as the primary factor, with multiple features being extracted from significant portions. Then angle‐based pose priority has applied for matching and identification more robust to viewpoint. Their proposed method helps to reduce the number of images which are redundant in the training phase as well as the number of matching process in the test phase. The strength of the proposed method is demonstrated on three different benchmark databases containing more than 1000 person‐images under variations in illumination, viewpoint and occlusion. The experimental results show that the proposed approach provides a higher recognition rates for all the issues of identification process. Finally, the results prove the superiority of the proposed method over other re‐identification methods both in terms of visual and quantitative comparisons. [ABSTRACT FROM AUTHOR]

At present, in the field of person reidentification (re-id), the commonly used supervised learning algorithms require a large amount of labeled samples, which is not conducive to the model promotion. On the other hand, the accuracy of unsupervised learning algorithms is lower than supervised algorithms due to the lack of discriminant information. To address these issues, we make use of a small amount of labeled samples to add discriminant information in the basic dictionary learning. Moreover, the sparse coefficients of dictionary learning are decomposed into a projection problem of the original features, and the projection matrix is trained by labeled samples, which is transformed into a metric learning problem. It thus integrates the advantages of the two methods through combining dictionary learning and metric learning. After the data are trained, a projection matrix is used to project the unlabeled features into a feature subspace and the labels of the samples are reconstructed. The semisupervised learning problem is then transformed to a supervised learning problem with a graph regu-larization term. Experiments on different public pedestrian datasets, such as VIPeR, PRID, iLIDS, and CUHK01, show that the recognition accuracy of our method is better than some other existing person re-id methods. © The Authors. Published by SPIE under a Creative Commons Attribution 3.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI. [DOI: 10.1117/1.JEI.27.4.043043] [ABSTRACT FROM AUTHOR]

Video-based pedestrian reidentification is an emerging task in video surveillance and is closely related to several real-world applications. Its goal is to match pedestrians across multiple nonoverlapping network cameras. Despite the recent effort, the performance of pedestrian reidentification needs further improvement. Hence, we propose a novel two-stream multirate recurrent neural network for video-based pedestrian reidentification with two inherent advantages: First, capturing the static spatial and temporal information; Second,Author: Figure II is not cited in the text. Please cite it at the appropriate place. dealing with motion speed variance. Given video sequences of pedestrians, we start with extracting spatial and motion features using two different deep neural networks. Then, we explore the feature correlation which results in a regularized fusion network integrating the two aforementioned networks. Considering that pedestrians, sometimes even the same pedestrian, move in different speeds across different camera views, we extend our approach by feeding the two networks into a multirate recurrent network to exploit the temporal correlations. Extensive experiments have been conducted on two real-world video-based pedestrian reidentification benchmarks: iLIDS-VID and PRID 2011 datasets. The experimental results confirm the efficacy of the proposed method. Our code will be released upon acceptance. [ABSTRACT FROM AUTHOR]

Person reidentification (Re-ID) aims at establishing global identities for individuals as they move across a camera network. It is a challenging task due to the drastic appearance changes that occur between cameras as a consequence of different pose and illumination conditions. Pairwise matching models yield state-of-the-art results in most of the person Re-ID datasets by capturing nuances that are robust and discriminative for a specific pair of cameras. Nonetheless, pairwise models are not scalable with the number of surveillance cameras. Therefore, elegant solutions combining scalability with high matching rates are crucial for the person Re-ID in real-world scenarios. We tackle this problem proposing a multicamera nonlinear regression model called kernel multiblock partial least squares (kernel MBPLS), a single subspace model for the entire camera network that uses all the labeled information. In this subspace, probe and gallery individual can be successfully matched. Experimental results in three multicamera person Re-ID datasets (WARD, RAiD, and SAIVT-SoftBIO) demonstrate that the kernel MBPLS presents favorable aspects, such as the scalability and robustness with respect to the number of cameras combined with the high matching rates. © 2018 SPIE and IS&r [DOI: 10.1117/1.JEI.27.3.033041] [ABSTRACT FROM AUTHOR]

Deep metric learning is an effective method for person reidentification. In practice, impostor samples generally possess more discriminative information than other negative samples. Specifically, existing triplet- based deep-learning methods cannot effectively remove impostors, because they cannot consider congeners of impostor and it may produce new impostors when removing existing impostors. To utilize discriminative information in triplets and make impostor and its congeners more clustering, we design oversymmetric and over- asymmetric relationships and apply these two constraints to triplet and impostors' congeners to train our deep triplet-group network with original individual images rather than handcrafted features. Extensive experiments with five benchmark datasets demonstrate that our method outperforms the state-of-the-art methods with regards to the rank-N matching accuracy. ©The Authors. Published by SPIE under a Creative Commons Attribution 3.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI. [DOI: 10.1117/1.JEI.27.3.033033] [ABSTRACT FROM AUTHOR]

We propose an effective person reidentification method based on normalized distance aggregation of discriminative features. Our framework is built on the integration of three high-performance discriminative feature extraction models, including local maximal occurrence (LOMO), feature fusion net (FFN), and a concatenation of LOMO and FFN called LOMO -- FFN, through two fast and discriminant metric learning models, i.e., cross-view quadratic discriminant analysis (XQDA) and large-scale similarity learning (LSSL). More specifically, we first represent all the cross-view person images using LOMO, FFN, and LOMO -- FFN, respectively, and then apply each extracted feature representation to train XQDA and LSSL, respectively, to obtain the optimized individual cross-view distance metric. Finally, the cross-view person matching is computed as the sum of the optimized individual cross-view distance metric through the min -- max normalization. Experimental results have shown the effectiveness of the proposed algorithm on three challenging datasets (VIPeR, PRID450s, and CUHK01). © 2018 SPIE and IS&T [DOI: 10.1117/1.JEI.27.2.023006] [ABSTRACT FROM AUTHOR]

Recently, support vector ranking (SVR) has been adopted to address the challenging person reidentification problem. However, the ranking model based on ordinary global features cannot well represent the significant variation of pose and viewpoint across camera views. To address this issue, a novel ranking method that fuses the dense invariant features (DIFs) is proposed in this paper to model the variation of images across camera views. An optimal space for ranking is learned by simultaneously maximizing the margin and minimizing the error on the fused features. The proposed method significantly outperforms the original SVR algorithm due to the invariance of the DIFs, the fusion of the bidirectional features, and the adaptive adjustment of parameters. Experimental results demonstrate that the proposed method is competitive with state-of-the-art methods on two challenging data sets, showing its potential for real-world person reidentification. [ABSTRACT FROM AUTHOR]

In this article, we revisit two popular convolutional neural networks in person re-identification (re-ID): verification and identification models. The two models have their respective advantages and limitations due to different loss functions. Here, we shed light on how to combine the two models to learn more discriminative pedestrian descriptors. Specifically, we propose a Siamese network that simultaneously computes the identification loss and verification loss. Given a pair of training images, the network predicts the identities of the two input images and whether they belong to the same identity. Our network learns a discriminative embedding and a similarity measurement at the same time, thus taking full usage of the re-ID annotations. Our method can be easily applied on different pretrained networks. Albeit simple, the learned embedding improves the state-of-the-art performance on two public person re-ID benchmarks. Further, we show that our architecture can also be applied to image retrieval. The code is available at https://github.com/layumi/2016_person_re-ID. [ABSTRACT FROM AUTHOR]

Plenty of research has been conducted to obtain the best reidentification performance between a single camera-pairs. None of the current approaches has addressed the reidentification in a camera network by considering the network topology (i.e., the structure of the monitored environment). We introduce a distributed network person reidentification framework which introduces the following contributions. 1) a camera matching cost to measure the reidentification performance between nodes of the network and 2) a derivation of the distance vector algorithm which allows to learn the network topology thus to prioritize and limit the cameras inquired for the matching of the probe. Results on three benchmark datasets show that the network topology can be learned in an unsupervised fashion and network-wise reidentification performance improves. As a side effect, we obtain that the communication bandwidth usage is reduced. [ABSTRACT FROM PUBLISHER]

Person reidentification, which matches person images of the same identity across nonoverlapping camera views, becomes an important component for cross-camera-view activity analysis. Most (if not all) person reidentification algorithms are designed based on appearance features. However, appearance features are not stable across nonoverlapping camera views under dramatic lighting change, and those algorithms assume that two cross-view images of the same person can be well represented either by exploring robust and invariant features or by learning matching distance. Such an assumption ignores the nature that images are captured under different camera views with different camera characteristics and environments, and thus, mostly there exists large discrepancy between the extracted features under different views. To solve this problem, we formulate an asymmetric distance model for learning camera-specific projections to transform the unmatched features of each view into a common space where discriminative features across view space are extracted. A cross-view consistency regularization is further introduced to model the correlation between view-specific feature transformations of different camera views, which reflects their nature relations and plays a significant role in avoiding overfitting. A kernel cross-view discriminant component analysis is also presented. Extensive experiments have been conducted to show that asymmetric distance modeling is important for person reidentification, which matches the concerns on cross-disjoint-view matching, reporting superior performance compared with related distance learning methods on six publically available data sets. [ABSTRACT FROM PUBLISHER]

In this letter, we introduce an adaptive metric learning (AML) method for person reidentification. Different from conventional metric learning approaches, which treat all the negative samples equally, AML adaptively classifies the negative samples into three groups and pays different attention to them. By emphasizing the influence of hard negative samples, AML can better mine the discriminative information between positive and negative samples, and thus generate a more effective metric. Furthermore, we also propose a probe-specific reranking (PSR) algorithm to refine the initial ranking list measured by the learned metric. For each probe, PSR constructs a corresponding hypergraph to capture the neighborhood relationship between the probe and its top 100 ranked gallery images. Then, these images are reranked based on their neighborhood affinity in the hypergraph. Extensive experiments on three challenging datasets demonstrate the superiority of both AML and PSR. [ABSTRACT FROM PUBLISHER]

Person reidentification (re-id) has been widely studied because of its extensive use in video surveillance and forensics applications. It aims to search a specific person among a nonoverlapping camera network, which is highly challenging due to large variations in the cluttered background, human pose, and camera viewpoint. We present a metric learning algorithm for learning a Mahalanobis distance for re-id. Generally speaking, there exist two forces in the conventional metric learning process, one pulling force that pulls points of the same class closer and the other pushing force that pushes points of different classes as far apart as possible. We argue that, when only a limited number of training data are given, forcing interclass distances to be as large as possible may drive the metric to overfit the uninformative part of the images, such as noises and backgrounds. To alleviate overfitting, we propose the ring-push metric learning algorithm. Different from other metric learning methods that only punish too small interclass distances, in the proposed method, both too small and too large inter-class distances are punished. By introducing the generalized logistic function as the loss, we formulate the ringpush metric learning as a convex optimization problem and utilize the projected gradient descent method to solve it. The experimental results on four public datasets demonstrate the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Person reidentification involves recognizing a person across nonoverlapping camera views, with different pose, illumination, and camera characteristics. We propose to tackle this problem by training a deep convolutional network to represent a person’s appearance as a low-dimensional feature vector that is invariant to common appearance variations encountered in the reidentification problem. Specifically, a Siamese network architecture is used to train a feature extraction network using pairs of similar and dissimilar images. We show that the use of a novel multitask learning objective is crucial for regularizing the network parameters in order to prevent overfitting due to the small size of the training data set. We complement the verification task, which is at the heart of reidentification, by training the network to jointly perform verification and identification and to recognize attributes related to the clothing and pose of the person in each image. In addition, we show that our proposed approach performs well even in the challenging cross-data set scenario, which may better reflect real-world expected performance. [ABSTRACT FROM PUBLISHER]