The humanID gait challenge problem: data sets, performance, and analysis

By Sudeep Sarkar, P. Jonathon Phillips, Zongyi Joe Liu, Isidro Robledo Vega, Patrick Grother, Kevin W. Bowyer. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005

1,255 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/bb6b14397f69bbfbc52cbd1a04bc6302a8b938d7

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

A Critical Review of Action Recognition Benchmarks (2013, background): “We further limit the discussion to benchmarks designed to measure performance on general action recognition tasks, rather than speciﬁc applications (e.g., violence detection in [8] or gait recognition [31]).”
Gait Recognition Using a View Transformation Model in the Frequency Domain (2006, methodology): “[6] proposed direct matching of silhouette image sequences as a baseline algorithm.”
HumanEva: Synchronized Video and Motion Capture Dataset and Baseline Algorithm for Evaluation of Articulated Human Motion (2010, background): “…that similar efforts have been made in related areas including the development of datasets for face detection (Phillips et al. 2000, 2002), human gait identification (Gross and Shi 2001; Sarkar et al. 2005), dense stereo vision (Scharstein and Szeliski 2002) and optical flow (Baker et al. 2007).”
Depth Information in Human Gait Analysis: An Experimental Study on Gender Recognition (2012, methodology): “We can find in the literature several approaches for gait classification [3,5,15,6,9].”
Unobtrusive User-Authentication on Mobile Phones Using Biometric Gait Recognition (2010, background): “In the machine vision approaches [8], [9], [10], [11], the system will typically consist of several digital or analog cameras with suitable optics for acquiring the gait data.”
GEINet: View-invariant gait recognition using a convolutional neural network (2016, methodology): “Some publicly available gait databases, such as the USF gait database [38], SOTON gait database [40], CASIA Figure 1: The structure of GEINet.”
Pattern Recognition (2018, neutral): “For eﬃcient gait recognition, we consider the same three datasets as [5] , namely CASIA-B [36] , OU-ISIR [37] and USF [38] .”
What Else Does Your Biometric Data Reveal? A Survey on Soft Biometrics (2016, methodology): “02 years on the USF database [174] consisting of 1870 gait sequences from 122 subjects (85 male and 37 female subjects of age between 19 and 59 years old).”
A Study on Gait-Based Gender Classification (2009, background): “As in gait recognition [33], there are still many challenges in gaitbased-gender classification.”
Robust view transformation model for gait recognition (2011, background): “Gait is a potential behavior biometric used to recognize and analyze person at distance [1], but the deviation of gait representation in practical visual surveillance scenario often gets out of control due to the viewing angle variation, large intraclass variations.”
GaitPart: Temporal Part-Based Model for Gait Recognition (2020, background): “Most state-of-art works have taken spatial feature extraction and temporal modeling as the focus[16, 23, 7, 3, 26, 2, 1].”
HumanEva: Synchronized Video and Motion Capture Dataset for Evaluation of Articulated Human Motion (2006, background): “It is worth noting that similar eﬀorts have been made in related areas including the development of datasets for face detection [23, 24], human gait identiﬁcation [31] and dense stereo vision [32].”
Machine Recognition of Human Activities: A Survey (2008, background): “Currently, the most promising example of behavio r l biometric is human gait [10].”
The OU-ISIR Gait Database Comprising the Large Population Dataset and Performance Evaluation of Gait Recognition (2012, methodology): “The USF dataset [18] is one of the most widely used gait datasets and is composed of a gallery and 12 probe sequences captured outdoors under different walking conditions including factors such as view, shoes, surface, baggage, and time.”
Learning Race from Face: A Survey (2014, background): “USF, short for the University of South Florida (USF) Human ID 3D database [194], sponsored by the US defense advanced research projects agency”
Motion history image: its variants and applications (2012, methodology): “[63,170] (2006) [64] (2003) DB: USF HumanID Gait DB [126] RR: overall ∼71% (rank 5); F: Frequency & phase estimation; C: PCA+MDA (Multiple Discriminant Analysis)”
Biometric Gait Authentication Using Accelerometer Sensor (2006, background): “Furthermore, recent studies with a larger sample size (more than 100 subjects in the database) confirm gait as having discriminating power from which individuals can be identified [20], [21], [22], [23].”