Gait Recognition from a Single Image Using a Phase-Aware Gait Cycle Reconstruction Network

Xu, Chi; Makihara, Yasushi; Li, Xiang; Yagi, Yasushi; Lu, Jianfeng

doi:10.1007/978-3-030-58529-7_23

Cited by 19 publications

(15 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Gait-based retrieval researches [42,38,39,3,2,33,9,8,61] directly use gait sequence/cycle for identity matching, which is also cloth-independent, but they are different from our work and cannot be directly applied into image-based cloth-changing ReID. We clarify the differences between two tasks in detail in the above table: our study focuses on image-based cloth-changing ReID where large viewpoint variations, occlusion, and complex environments will make gait recognition failed.…”

Section: Gait Recognitionmentioning

confidence: 81%

“…As we have discussed in details in the main manuscripts, directly using gait sequences/masks for identity matching is not optimal for cloth-changing ReID problem, especially in the image-based ReID scenarios. Experimentally, we compare the proposed GI-ReID with two popular pure gait recognition works, GaitSet [3] and PA-GCR [61]. GaitSet needs a set/sequence of person masks as input, but recently-released cloth-changing ReID datasets are image datasets that lack of continuous frames for the same person.…”

Section: More Experimental Analysis Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and Regularization

Jin¹,

He²,

Zheng³

et al. 2021

Preprint

View full text Add to dashboard Cite

Cloth-Changing person re-identification (CC-ReID) aims at matching the same person across different locations over a long-duration, e.g., over days, and therefore inevitably meets challenge of changing clothing. In this paper, we focus on handling well the CC-ReID problem under a more challenging setting, i.e., just from a single image, which enables high-efficiency and latency-free pedestrian identify for real-time surveillance applications. Specifically, we introduce Gait recognition as an auxiliary task to drive the Image ReID model to learn clothagnostic representations by leveraging personal unique and cloth-independent gait information, we name this framework as GI-ReID. GI-ReID adopts a two-stream architecture that consists of a image ReID-Stream and an auxiliary gait recognition stream (Gait-Stream). The Gait-Stream, that is discarded in the inference for high computational efficiency, acts as a regulator to encourage the ReID-Stream to capture cloth-invariant biometric motion features during the training. To get temporal continuous motion cues from a single image, we design a Gait Sequence Prediction (GSP) module for Gait-Stream to enrich gait information. Finally, a high-level semantics consistency over two streams is enforced for effective knowledge regularization. Experiments on multiple image-based Cloth-Changing ReID benchmarks, e.g., LTCC, PRCC, Real28, and VC-Clothes, demonstrate that GI-ReID performs favorably against the state-of-the-arts. Codes are available at https://github.com/jinx-USTC/GI-ReID

show abstract

Section: Gait Recognitionmentioning

confidence: 81%

Section: More Experimental Analysis Resultsmentioning

confidence: 99%

Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and Regularization

Jin¹,

He²,

Zheng³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…In decades, many methods have been proposed to tackle the problem of low frame rates for gait recognition. Basically, these methods can be divided into three different categories, including temporal interpolation and super-resolution-based methods, metric learning-based methods, and directly gait feature reconstruction-based methods (Xu et al, 2020). For methods in the first category, temporal reconstruction and super-resolution techniques are imported to address the problem of low frame rates.…”

Section: Related Work Low Frame-rate Gait Recognitionmentioning

confidence: 99%

“…However, these proposed methods can only guarantee the optimality of reconstruction quality rather than recognition accuracy, which is the most important for gait recognition. In order to ensure the reconstruction quality and recognition accuracy simultaneously, a unified framework of a phase-aware gait cycle reconstruction network (PA-GCRNet) is created in Xu et al (2020). Taking the phase of a single input silhouette into account, a full gait cycle of a silhouette sequence with corresponding phases is first reconstructed by PA-GCRNet.…”

Section: Related Work Low Frame-rate Gait Recognitionmentioning

confidence: 99%

“…In recent decades, many methods have been proposed for gait recognition to address the problem of low frame rates. For example, in Makihara, Mori & Yagi (2010), Akae, Makihara & Yagi (2011), Akae et al (2012), Xu et al (2020), the problem of low frame rates is handled using temporal reconstruction and super-resolution methods. In Guan, Li & Choudhury (2013), gait features are directly formulated from the input low frame-rate sequences via metric learning methods.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Gait recognition using a few gait frames

Yao

Kusakunniran

et al. 2021

PeerJ Computer Science

View full text Add to dashboard Cite

Gait has been deemed as an alternative biometric in video-based surveillance applications, since it can be used to recognize individuals from a far distance without their interaction and cooperation. Recently, many gait recognition methods have been proposed, aiming at reducing the influence caused by exterior factors. However, most of these methods are developed based on sufficient input gait frames, and their recognition performance will sharply decrease if the frame number drops. In the real-world scenario, it is impossible to always obtain a sufficient number of gait frames for each subject due to many reasons, e.g., occlusion and illumination. Therefore, it is necessary to improve the gait recognition performance when the available gait frames are limited. This paper starts with three different strategies, aiming at producing more input frames and eliminating the generalization error cause by insufficient input data. Meanwhile, a two-branch network is also proposed in this paper to formulate robust gait representations from the original and new generated input gait frames. According to our experiments, under the limited gait frames being used, it was verified that the proposed method can achieve a reliable performance for gait recognition.

show abstract

Gender Classification from Gait Energy and Posture Images Using Multi-stage Network

Leung,

Chan

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Gait Recognition from a Single Image Using a Phase-Aware Gait Cycle Reconstruction Network

Cited by 19 publications

References 43 publications

Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and Regularization

Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and Regularization

Gait recognition using a few gait frames

Gender Classification from Gait Energy and Posture Images Using Multi-stage Network

Contact Info

Product

Resources

About