Open-World Person Re-Identification With RGBD Camera in Top-View Configuration for Retail Applications

Martini, Massimo; Paolanti, Marina; Frontoni, Emanuele

doi:10.1109/access.2020.2985985

Cited by 20 publications

(4 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Apart from the above works, some Re-ID methods use raw-depth and RGB images combinedly [ 40 , 42 , 47 ]. Moreover, in some approaches [ 48 , 57 ], depth frames are used as body segmentation masks, which play an important role in removing cluttered backgrounds from scenes. Most of the above RGB-depth image-based Re-ID methods are considered deep-learning approaches with score-level or feature-level fusion techniques.…”

Section: Multi-modal Person Re-identificationmentioning

confidence: 99%

Person Re-Identification with RGB–D and RGB–IR Sensors: A Comprehensive Survey

Uddin

Bhuiyan

Bappee

et al. 2023

Sensors

View full text Add to dashboard Cite

Learning about appearance embedding is of great importance for a variety of different computer-vision applications, which has prompted a surge in person re-identification (Re-ID) papers. The aim of these papers has been to identify an individual over a set of non-overlapping cameras. Despite recent advances in RGB–RGB Re-ID approaches with deep-learning architectures, the approach fails to consistently work well when there are low resolutions in dark conditions. The introduction of different sensors (i.e., RGB–D and infrared (IR)) enables the capture of appearances even in dark conditions. Recently, a lot of research has been dedicated to addressing the issue of finding appearance embedding in dark conditions using different advanced camera sensors. In this paper, we give a comprehensive overview of existing Re-ID approaches that utilize the additional information from different sensor-based methods to address the constraints faced by RGB camera-based person Re-ID systems. Although there are a number of survey papers that consider either the RGB–RGB or Visible-IR scenarios, there are none that consider both RGB–D and RGB–IR. In this paper, we present a detailed taxonomy of the existing approaches along with the existing RGB–D and RGB–IR person Re-ID datasets. Then, we summarize the performance of state-of-the-art methods on several representative RGB–D and RGB–IR datasets. Finally, future directions and current issues are considered for improving the different sensor-based person Re-ID systems.

show abstract

Section: Multi-modal Person Re-identificationmentioning

confidence: 99%

Person Re-Identification with RGB–D and RGB–IR Sensors: A Comprehensive Survey

Uddin

Bhuiyan

Bappee

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Figure 5 shows the most popular sensors used in person Re-ID research. Near-infrared (NIR) cameras are primarily used in situations with low lighting, such as dark indoor conditions or at night [17]. RGB-D sensors or Kinects can acquire depth information which can be helpful for 3D reconstruction or depth perception but is used in very particular person Re-ID applications [18,19].…”

Section: Introductionmentioning

confidence: 99%

A Review of Techniques on Gait-Based Person Re-Identification

Rahi¹,

Li²,

Qi³

2023

IJNDI

View full text Add to dashboard Cite

Survey/review study A Review of Techniques on Gait-Based Person Re-Identification Babak Rahi 1,*, Maozhen Li 1, and Man Qi 2 1 Department of Electronics and Computer Engineering, Brunel University London, Uxbridge, Middlesex, UB8 3PH, United Kingdom 2 The School of Engineering, University of Warwick, Coventry CV4 7AL, United Kingdom * Correspondence: babak.h.rahi@hotmail.com Received: 16 October 2022 Accepted: 14 December 2022 Published: Abstract: Person re-identification at a distance across multiple non-overlapping cameras has been an active research area for years. In the past ten years, short-term Person re-identification techniques have made great strides in accuracy using only appearance features in limited environments. However, massive intra-class variations and inter-class confusion limit their ability to be used in practical applications. Moreover, appearance consistency can only be assumed in a short time span from one camera to the other. Since the holistic appearance will change drastically over days and weeks, the technique, as mentioned above, will be ineffective. Practical applications usually require a long-term solution in which the subject's appearance and clothing might have changed after the elapse of a significant period. Facing these problems, soft biometric features such as Gait has stirred much interest in the past years. Nevertheless, even Gait can vary with illness, ageing and emotional states, walking surfaces, shoe types, clothes types, carried objects (by the subject) and even environment clutters. Therefore, Gait is considered as a temporal cue that could provide biometric motion information. On the other hand, the shape of the human body could be viewed as a spatial signal which can produce valuable information. So extracting discriminative features from both spatial and temporal domains would benefit this research. This article examines the main approaches used in gait analysis for re-identification over the past decade. We identify several relevant dimensions of the problem and provide a taxonomic analysis of current research. We conclude by reviewing the performance levels achievable with current technology and providing a perspective on the most challenging and promising research directions.

show abstract

“…Person re-identification (Re-ID) (Ye et al 2021;Luo et al 2019;Liu et al 2016Liu et al , 2019 aims to identify a person-ofinterest across non-overlapping camera networks under different times and locations. It has drawn extensive research attention in recent years, due to its significant role in various practice scenarios, such as object tracking, activity analysis and smart retail etc (Wang 2013;Caba Heilbron et al 2015;Martini, Paolanti, and Frontoni 2020). Along with the success of deep learning, large amount of sophisticated person Re-ID methods have been proposed and achieved promising performances in a fully supervised manner.…”

Section: Introductionmentioning

confidence: 99%

Debiased Batch Normalization via Gaussian Process for Generalizable Person Re-identification

Liu

Huang

et al. 2022

AAAI

View full text Add to dashboard Cite

Generalizable person re-identification aims to learn a model with only several labeled source domains that can perform well on unseen domains. Without access to the unseen domain, the feature statistics of the batch normalization (BN) layer learned from a limited number of source domains is doubtlessly biased for unseen domain. This would mislead the feature representation learning for unseen domain and deteriorate the generalizaiton ability of the model. In this paper, we propose a novel Debiased Batch Normalization via Gaussian Process approach (GDNorm) for generalizable person re-identification, which models the feature statistic estimation from BN layers as a dynamically self-refining Gaussian process to alleviate the bias to unseen domain for improving the generalization. Specifically, we establish a lightweight model with multiple set of domain-specific BN layers to capture the discriminability of individual source domain, and learn the corresponding parameters of the domain-specific BN layers. These parameters of different source domains are employed to deduce a Gaussian process. We randomly sample several paths from this Gaussian process served as the BN estimations of potential new domains outside of existing source domains, which can further optimize these learned parameters from source domains, and estimate more accurate Gaussian process by them in return, tending to real data distribution. Even without a large number of source domains, GDNorm can still provide debiased BN estimation by using the mean path of the Gaussian process, while maintaining low computational cost during testing. Extensive experiments demonstrate that our GDNorm effectively improves the generalization ability of the model on unseen domain.

show abstract

Open-World Person Re-Identification With RGBD Camera in Top-View Configuration for Retail Applications

Cited by 20 publications

References 31 publications

Person Re-Identification with RGB–D and RGB–IR Sensors: A Comprehensive Survey

Person Re-Identification with RGB–D and RGB–IR Sensors: A Comprehensive Survey

A Review of Techniques on Gait-Based Person Re-Identification

Debiased Batch Normalization via Gaussian Process for Generalizable Person Re-identification

Contact Info

Product

Resources

About