Centralized and Clustered Features for Person Re-Identification

Lü, Jian; He, Yaozhen; Liu, Tong; Chen, Xu

doi:10.1109/lsp.2019.2913020

Cited by 15 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For MOT Challenge task, in order to evaluate the performance of our scene-aware method, we conduct 4 groups of comparative experiments on the MOT20 (Lu et al, 2019) dataset, which is the latest benchmark on MOT Challenge. This dataset contains 8 challenging video sequences captured in unconstrained scenes.…”

Section: Datasets and Metricsmentioning

confidence: 99%

“…With the development of object detection algorithms Ayoun et al, 2010;Li et al, 2017;Zheng et al, 2019) and the innovation of reidentification technology Lu et al, 2019;Zhang et al, 2019;Farenzena et al, 2010;Choe et al 2019), tracking-by-detection has become one of the mainstream approaches for video analysis problems. It has been widely studied and has produced remarkable results in recent decades, demonstrating significant application value in vehicle navigation, intelligent monitoring, human-computer interaction, crowd counting, and other fields.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Video Object Counting With Scene-Aware Multi-Object Tracking

Cai

Cheng³

et al. 2023

Journal of Database Management

View full text Add to dashboard Cite

The critical challenge of video object counting is to avoid counting the same object multiple times in different frames. By comparing the appearance and motion feature information of the detection results, the authors use the multi-object tracking method to assign an independent ID number to each object. From the time the ID tag is obtained until the end of the video, each object is counted only once. However, even minor amounts of image noise can cause irreversible changes in feature information, resulting in severe tracking drifts. This paper introduces the concept of scene awareness and addresses unreasonable ID assignment caused by unreliable feature matching in the context of region division. Through the macro analysis of the scene, the authors define the region (called the transition region) where the number of objects can increase or decrease and require that all ID assignments for new objects and ID deletions for existing objects take place only in the transition region. Because the actual number of objects in the non-transition region is constant, they rematch unmatched objects with existing IDs in the region (called ID relocation) because changes in object ID are caused by feature matching failure. In this paper, the authors create algorithms for dynamically generating transition regions, detecting object increases and decreases, and relocating object IDs. Experimental results show that the method effectively improves the accuracy of video object counting.

show abstract

Section: Datasets and Metricsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Video Object Counting With Scene-Aware Multi-Object Tracking

Cai

Cheng³

et al. 2023

Journal of Database Management

View full text Add to dashboard Cite

show abstract

“…Index Terms-Person re-identification, Generated data, Sparse pseudo label I. Introduction P ERSON re-identification (re-ID) is an important research topic in the field of computer vision, it aims to identify the same person in the view of non-overlapping cameras [1], [2], [3], [4], [5]. Peron re-ID is a challenging task due to variations of poses, occlusions, illuminations, viewpoints, and background clutters in training datasets [6], [7], [8], [9], [10].…”

Section: Generated Data With Sparse Regularized Multi-pseudo Label Fo...mentioning

confidence: 99%

Generated Data With Sparse Regularized Multi-Pseudo Label for Person Re-Identification

Huang

Yang

et al. 2020

IEEE Signal Process. Lett.

View full text Add to dashboard Cite

“…Clustering-based unsupervised ReID [7], [10], [37] alternatively generate pseudo-labels with clustering and training a ReID model with them. This stream requires neither manual annotations nor detected trajectory, which is more flexible in real-world application meanwhile achieving decent accuracy, Ding et al [7] proposed a dispersion-based clustering framework that progressively merges similar clusters based on a dispersion criterion and learns representations with cluster labels.…”

mentioning

confidence: 99%

Multi-View Label Prediction for Unsupervised Learning Person Re-Identification

Yin

Wang

Ding

et al. 2021

IEEE Signal Process. Lett.

View full text Add to dashboard Cite

Person re-identification (ReID) aims to match pedestrian images across disjoint cameras. Existing supervised ReID methods utilize deep networks and train them with identitylabeled images, which suffer from limited annotations. Recently, clustering-based unsupervised ReID attracts more and more attention. It first clusters unlabeled images and assigns cluster index to the pseudo-identity-labels, then trains a ReID model with the pseudo-identity-labels. However, considering the slight inter-class variations and significant intra-class variations, pseudo-identitylabels learned from clustering algorithms are usually noisy and coarse. To alleviate the problems above, besides clustering pseudoidentity-labels, we propose to learn pseudo-patch-labels, which brings two advantages: (1) Patch naturally alleviates the effect of backgrounds, occlusions, and carryings since they usually occupy small parts in images, thus overcome noisy labels. (2) It is plausible that patches from different pedestrians belong to the same pseudoidentity-label. For example, pedestrians have a high probability of wearing either the same shoes or pants but a low possibility of wearing both. The experiments demonstrate our proposed method achieves the best performance by a large margin on both imageand video-based datasets.

show abstract

Centralized and Clustered Features for Person Re-Identification

Cited by 15 publications

References 10 publications

Video Object Counting With Scene-Aware Multi-Object Tracking

Video Object Counting With Scene-Aware Multi-Object Tracking

Generated Data With Sparse Regularized Multi-Pseudo Label for Person Re-Identification

Multi-View Label Prediction for Unsupervised Learning Person Re-Identification

Contact Info

Product

Resources

About