Simultaneous visual-appearance-level and spatial-temporal-level dictionary learning for video-based person re-identification

Zhu, Xiaoke; Jing, Xiao‐Yuan; Ma, Fei; Cheng, Li; Ren, Yilin

doi:10.1007/s00521-018-3529-7

Cited by 12 publications

(6 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The visual-appearance-level and spatial-temporal-level dictionary learning (VSDL) [26] method uses a visual appearance level dictionary and a spatiotemporal level dictionary to obtain the coding coefficients of each walking cycle, and judges the dictionary through the representation coefficient discriminant term to achieve tracking. The feature attention block [27] is designed to focus on different local areas, summarize the local areas, and integrate them into the neural network to achieve re-ID for people.…”

Section: Tracking Methodsmentioning

confidence: 99%

A Novel Vehicle Tracking ID Switches Algorithm for Driving Recording Sensors

Zhao

Zhou

et al. 2020

Sensors

View full text Add to dashboard Cite

The main task for real-time vehicle tracking is establishing associations with objects in consecutive frames. After occlusion occurs between vehicles during the tracking process, the vehicle is given a new ID when it is tracked again. In this study, a novel method to track vehicles between video frames was constructed. This method was applied on driving recorder sensors. The neural network model was trained by YOLO v3 and the system collects video of vehicles on the road using a driving data recorder (DDR). We used the modified Deep SORT algorithm with a Kalman filter to predict the position of the vehicles and to calculate the Mahalanobis, cosine, and Euclidean distances. Appearance metrics were incorporated into the cosine distances. The experiments proved that our algorithm can effectively reduce the number of ID switches by 29.95% on the model trained on the BDD100K dataset, and it can reduce the number of ID switches by 32.16% on the model trained on the COCO dataset.

show abstract

Section: Tracking Methodsmentioning

confidence: 99%

A Novel Vehicle Tracking ID Switches Algorithm for Driving Recording Sensors

Zhao

Zhou

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…The work [25] proposed a novel few-shot deep learning approahch to video-based person REID, to learn comparable representations that are discriminative and view-invariant. The research [26] designed a visual-appearance-level and spatial-temporal-level dictionary learning approach for video-based person REID task.…”

Section: Related Work a Image Based Person Re-identificationmentioning

confidence: 99%

Part-Based Enhanced Super Resolution Network for Low-Resolution Person Re-Identification

Tian

Miao

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Person re-identification (REID) is an important task in video surveillance and forensics applications. Many previous works often build models on the assumption that they have same resolution cross different camera views, while it is divorced from reality. To increase the adaptability of person REID models, this paper focuses on the low-resolution person REID task to relax the impractical assumption when traditional low-resolution person REID models are under pixel-to-pixel supervision in low and high resolution pedestrian image pairs. In addition, they are easily influenced by the global background, illumination or pose variations across camera views. Therefore, we propose a Part-based Enhanced Super Resolution (PESR) network by employing a part division strategy and an enhanced generative adversarial network to boost the unpaired pedestrian image super resolution process. Specifically, the part-based super resolution network transforms low resolution image in probe into high resolution without any pixel-to-pixel supervision and the part-based synthetic feature extractor module can learn discriminative pedestrian feature representation for the generated high resolution images, which employ a part feature connection loss as constraint to conduct matching for person re-identification. Furthermore, evaluations on four public person REID datasets demonstrate the advantages of our method over the state-of-the-art ones. INDEX TERMS Low-resolution person re-identification, enhanced super resolution, part based, realistic discriminator.

show abstract

“…Then, we use Alternating Direction Method of Multipliers (ADMM) to optimize Eqn. (15). According to ADMM, the Eqn.…”

Section: B Optimizationmentioning

confidence: 99%

“…Specifically, DBDL complete classification task by approaching a non-parametric Bayesian perspective and JEDL do it according to deliver a linear sparse codes autoextractor and a multi-class classifier by simultaneously minimizing the sparse reconstruction, discriminative sparse-code, code approximation, and classification errors. Zhu et al [13]- [15] proposed several dictionary learning methods for image to video person re-identification, including a semisupervised cross-view projection-based dictionary learning (SCPDL) approach and a joint feature projection matrix and heterogeneous dictionary pair learning (PHDL) approach.…”

Section: Introductionmentioning

confidence: 99%

Class-Specific Sparse Principal Component Analysis for Visual Classification

et al. 2020

View full text Add to dashboard Cite

Extensive research has demonstrated that dictionary learning is active in improving the performance of the representation based classification. However, dictionary learning suffers from lacking an effective dictionary structure that can well tradeoff the reducing reconstruction error and enhancing the representative information. In this paper, we focus on designing capable dictionary learning architecture for the visual classification task with few-shot training samples. First, we propose a class-specific sparse PCA approach to extend the conventional dictionary learning to dictionary pair learning for visual classification. The orthogonal synthesis dictionary ensures fewer reconstruction errors with fixed dictionary size while the sparse analysis dictionary guarantees the representative features. Second, we develop the Alternating Direction Method of Multipliers algorithm to optimize the analysis dictionary to improve computational efficiency. Extensive experiments conducted on multiple image datasets demonstrate that the proposed class-specific PCA method performs favorably against the state-of-art methods on eight widely used image datasets.

show abstract

Simultaneous visual-appearance-level and spatial-temporal-level dictionary learning for video-based person re-identification

Cited by 12 publications

References 40 publications

A Novel Vehicle Tracking ID Switches Algorithm for Driving Recording Sensors

A Novel Vehicle Tracking ID Switches Algorithm for Driving Recording Sensors

Part-Based Enhanced Super Resolution Network for Low-Resolution Person Re-Identification

Class-Specific Sparse Principal Component Analysis for Visual Classification

Contact Info

Product

Resources

About