Gait-based Person Re-identification: A Survey
TL;DR: A survey of the work done in gait analysis for re-identification in the past decade, looking at the main approaches, datasets, and evaluation methodologies is presented and a taxonomic analysis of the current state of the art is provided.
Abstract: The way people walk is a strong correlate of their identity. Several studies have shown that both humans and machines can recognize individuals just by their gait, given that proper measurements of the observed motion patterns are available. For surveillance applications, gait is also attractive, because it does not require active collaboration from users and is hard to fake. However, the acquisition of good-quality measures of a person’s motion patterns in unconstrained environments, (e.g., in person re-identification applications) has proved very challenging in practice. Existing technology (video cameras) suffer from changes in viewpoint, daylight, clothing, accessories, and other variations in the person’s appearance. Novel three-dimensional sensors are bringing new promises to the field, but still many research issues are open. This article presents a survey of the work done in gait analysis for re-identification in the past decade, looking at the main approaches, datasets, and evaluation methodologies. We identify several relevant dimensions of the problem and provide a taxonomic analysis of the current state of the art. Finally, we discuss the levels of performance achievable with the current technology and give a perspective of the most challenging and promising directions of research for the future.
Citations
More filters
01 Jan 1984
TL;DR: The phase relations typical of the Johansson pattern are therefore still present when the film is inverted and run backward, leading to the perception of biological motions though these motions are very strange as discussed by the authors.
Abstract: In a film produced by Johansson, a group of moving spots, corresponding to lights attached to the main joints of a walker or a runner, gives instantly a vivid impression of a person walking or running. Even when this film was inverted and run backward, some sort of human movement was still perceived. It was perceived more frequently as an upright image of a person moving forward in a very strange manner than as an inverted image of a person moving backward. Such strangeness seemed to arise from the fact that the actor's arms were perceived as legs and vice versa. The phase relations typical of the Johansson pattern are therefore still present when the film is inverted and run backward, leading to the perception of biological motions though these motions are very strange.
256 citations
14 Jun 2020
TL;DR: RF-ReID as mentioned in this paper harnesses radio frequency (RF) signals for long-term person ReID, which can be used to extract more persistent human-identifying features like body size and shape.
Abstract: Person Re-Identification (ReID) aims to recognize a person-of-interest across different places and times. Existing ReID methods rely on images or videos collected using RGB cameras. They extract appearance features like clothes, shoes, hair, etc. Such features, however, can change drastically from one day to the next, leading to inability to identify people over extended time periods. In this paper, we introduce RF-ReID, a novel approach that harnesses radio frequency (RF) signals for longterm person ReID. RF signals traverse clothes and reflect off the human body; thus they can be used to extract more persistent human-identifying features like body size and shape. We evaluate the performance of RF-ReID on longitudinal datasets that span days and weeks, where the person may wear different clothes across days. Our experiments demonstrate that RF-ReID outperforms state-of-the-art RGB-based ReID approaches for long term person ReID. Our results also reveal two interesting features: First since RF signals work in the presence of occlusions and poor lighting, RF-ReID allows for person ReID in such scenarios. Second, unlike photos and videos which reveal personal and private information, RF signals are more privacy-preserving, and hence can help extend person ReID to privacy-concerned domains, like healthcare.
49 citations
TL;DR: The description of the architectures used is presented which follows the most required analyses in these systems and future trends are discussed which charts a path into the upcoming research directions.
45 citations
TL;DR: This survey paper includes brief discussion about feature representation learning and deep metric learning with novel loss functions, and thoroughly review datasets with performance analysis on existing datasets.
41 citations
TL;DR: The proposed gait recognition method showed higher accuracy compared to obtained results of other methods result for CASIA-(B) and OU-MVLP and form the best results for the OU-ISIR dataset.
Abstract: Person re-identification across multiple cameras is an essential task in computer vision applications, particularly tracking the same person in different scenes. Gait recognition, which is the recognition based on the walking style, is mostly used for this purpose due to that human gait has unique characteristics that allow recognizing a person from a distance. However, human recognition via gait technique could be limited with the position of captured images or videos. Hence, this paper proposes a gait recognition approach for person re-identification. The proposed approach starts with estimating the angle of the gait first, and this is then followed with the recognition process, which is performed using convolutional neural networks. Herein, multitask convolutional neural network models and extracted gait energy images (GEIs) are used to estimate the angle and recognize the gait. GEIs are extracted by first detecting the moving objects, using background subtraction techniques. Training and testing phases are applied to the following three recognized datasets: CASIA-(B), OU-ISIR, and OU-MVLP. The proposed method is evaluated for background modeling using the Scene Background Modeling and Initialization (SBI) dataset. The proposed gait recognition method showed an accuracy of more than 98% for almost all datasets. Results of the proposed approach showed higher accuracy compared to obtained results of other methods result for CASIA-(B) and OU-MVLP and form the best results for the OU-ISIR dataset.
41 citations
References
More filters
TL;DR: High generalization ability of support-vector networks utilizing polynomial input transformations is demonstrated and the performance of the support- vector network is compared to various classical learning algorithms that all took part in a benchmark study of Optical Character Recognition.
Abstract: The support-vector network is a new learning machine for two-group classification problems. The machine conceptually implements the following idea: input vectors are non-linearly mapped to a very high-dimension feature space. In this feature space a linear decision surface is constructed. Special properties of the decision surface ensures high generalization ability of the learning machine. The idea behind the support-vector network was previously implemented for the restricted case where the training data can be separated without errors. We here extend this result to non-separable training data.
High generalization ability of support-vector networks utilizing polynomial input transformations is demonstrated. We also compare the performance of the support-vector network to various classical learning algorithms that all took part in a benchmark study of Optical Character Recognition.
37,861 citations
TL;DR: The kinetic-geometric model for visual vector analysis originally developed in the study of perception of motion combinations of the mechanical type was applied to biological motion patterns and the results turned out to be highly positive.
Abstract: This paper reports the first phase of a research program on visual perception of motion patterns characteristic of living organisms in locomotion. Such motion patterns in animals and men are termed here as biological motion. They are characterized by a far higher degree of complexity than the patterns of simple mechanical motions usually studied in our laboratories. In everyday perceptions, the visual information from biological motion and from the corresponding figurative contour patterns (the shape of the body) are intermingled. A method for studying information from the motion pattern per se without interference with the form aspect was devised. In short, the motion of the living body was represented by a few bright spots describing the motions of the main joints. It is found that 10–12 such elements in adequate motion combinations in proximal stimulus evoke a compelling impression of human walking, running, dancing, etc. The kinetic-geometric model for visual vector analysis originally developed in the study of perception of motion combinations of the mechanical type was applied to these biological motion patterns. The validity of this model in the present context was experimentally tested and the results turned out to be highly positive.
4,175 citations
"Gait-based Person Re-identification..." refers background or methods in this paper
...Similarly, John et al. (2013) combined colour, person-height, and gait, and Wang et al. (2016) combined colour with space-time features. From the various strategies of feature fusion, the most widely used are score-level fusion and feature-level fusion (Ross et al. 2006).14 In Liu et al. (2015), both score-level fusion and feature-level fusion were applied to various features extracted from the gait sequence for improving the aggregate performance....
[...]
...In a famous study of biological motion (Johansson 1973), using Moving Light Displays (MLDs), they instrumented the main joints of a human with bright light spots....
[...]
...Similarly, John et al. (2013) combined colour, person-height, and gait, and Wang et al....
[...]
...Similarly, John et al. (2013) combined colour, person-height, and gait, and Wang et al. (2016) combined colour with space-time features....
[...]
21 Jul 2017
TL;DR: Part Affinity Fields (PAFs) as discussed by the authors uses a nonparametric representation to learn to associate body parts with individuals in the image and achieves state-of-the-art performance on the MPII Multi-Person benchmark.
Abstract: We present an approach to efficiently detect the 2D pose of multiple people in an image. The approach uses a nonparametric representation, which we refer to as Part Affinity Fields (PAFs), to learn to associate body parts with individuals in the image. The architecture encodes global context, allowing a greedy bottom-up parsing step that maintains high accuracy while achieving realtime performance, irrespective of the number of people in the image. The architecture is designed to jointly learn part locations and their association via two branches of the same sequential prediction process. Our method placed first in the inaugural COCO 2016 keypoints challenge, and significantly exceeds the previous state-of-the-art result on the MPII Multi-Person benchmark, both in performance and efficiency.
3,958 citations
Posted Content•
TL;DR: This work presents an approach to efficiently detect the 2D pose of multiple people in an image using a nonparametric representation, which it refers to as Part Affinity Fields (PAFs), to learn to associate body parts with individuals in the image.
Abstract: We present an approach to efficiently detect the 2D pose of multiple people in an image. The approach uses a nonparametric representation, which we refer to as Part Affinity Fields (PAFs), to learn to associate body parts with individuals in the image. The architecture encodes global context, allowing a greedy bottom-up parsing step that maintains high accuracy while achieving realtime performance, irrespective of the number of people in the image. The architecture is designed to jointly learn part locations and their association via two branches of the same sequential prediction process. Our method placed first in the inaugural COCO 2016 keypoints challenge, and significantly exceeds the previous state-of-the-art result on the MPII Multi-Person benchmark, both in performance and efficiency.
3,791 citations
"Gait-based Person Re-identification..." refers background or methods in this paper
...Instead, we envisage that recent methods on pose estimation from single 2D images such as OpenPose15 (Cao et al. 2017) will facilitate the application of model-based techniques using standard video technology....
[...]
...In this regard, novel techniques like open-pose (Cao et al. 2017) bestowing real-time pose estimation upon 2D images looks promising for future work....
[...]
07 Dec 2015
TL;DR: A minor contribution, inspired by recent advances in large-scale image search, an unsupervised Bag-of-Words descriptor is proposed that yields competitive accuracy on VIPeR, CUHK03, and Market-1501 datasets, and is scalable on the large- scale 500k dataset.
Abstract: This paper contributes a new high quality dataset for person re-identification, named "Market-1501". Generally, current datasets: 1) are limited in scale, 2) consist of hand-drawn bboxes, which are unavailable under realistic settings, 3) have only one ground truth and one query image for each identity (close environment). To tackle these problems, the proposed Market-1501 dataset is featured in three aspects. First, it contains over 32,000 annotated bboxes, plus a distractor set of over 500K images, making it the largest person re-id dataset to date. Second, images in Market-1501 dataset are produced using the Deformable Part Model (DPM) as pedestrian detector. Third, our dataset is collected in an open system, where each identity has multiple images under each camera. As a minor contribution, inspired by recent advances in large-scale image search, this paper proposes an unsupervised Bag-of-Words descriptor. We view person re-identification as a special task of image search. In experiment, we show that the proposed descriptor yields competitive accuracy on VIPeR, CUHK03, and Market-1501 datasets, and is scalable on the large-scale 500k dataset.
3,564 citations
"Gait-based Person Re-identification..." refers background or methods in this paper
...…individually available for Re-ID (e.g., Viper (Gray et al. 2007), CAVIAR4REID (Cheng et al. 2011), CUHK03 (Li et al. 2014), and Market-1501 (Zheng et al. 2015)), as well as for gait analysis (e.g., TUM-IITKGP Gait Database (Hofmann et al. 2011) and Multi Biometric Tunnel (Seely et al.…...
[...]
...There are many other datasets individually available for Re-ID (e.g., Viper (Gray et al. 2007), CAVIAR4REID (Cheng et al. 2011), CUHK03 (Li et al. 2014), and Market-1501 (Zheng et al. 2015)), as well as for gait analysis (e.g., TUM-IITKGP Gait Database (Hofmann et al. 2011) and Multi Biometric Tunnel (Seely et al. 2008))....
[...]
...2014] and Market1501 [Zheng et al. 2015] as well as for gait analysis, (e....
[...]