A Framework for Evaluating the Effect of View Angle, Clothing and Carrying Condition on Gait Recognition

By Shiqi Yu, Daoliang Tan, Tien-Ping Tan. International Conference on Pattern Recognition, 2006

1,264 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Biomedical Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/0268d1744377ffbff48b014f513ea3e5e4a4dab1

How researchers see this paper

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

In Artificial Intelligence

In Biomedical Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Gait recognition using Gait Entropy Image (2009, methodology): “3), and a direct template matching based method in [15].”
The OU-ISIR Gait Database Comprising the Large Population Dataset and Performance Evaluation of Gait Recognition (2012, methodology): “The CASIA database, Dataset B [19] consists of multiview (11 views) walking sequences and includes variations in the view angle, clothing, and carrying conditions.”
Pattern Recognition (2018, positive): “For eﬃcient gait recognition, we consider the same three datasets as [5] , namely CASIA-B [36] , OU-ISIR [37] and USF [38] .”
Motion history image: its variants and applications (2012, neutral): “[26,25] (2008) DB: CASIA gait database—all [167] RR: overall ∼90.”
A Comprehensive Study on Cross-View Gait Based Human Identification with Deep CNNs (2017, methodology): “We greatly advance the record scores on the CASIA- B [6], OU-ISIR [28] and USF [29] datasets, showing that our method works pretty well and can generalize for thousands of categories and complex backgrounds .”
A model-based gait recognition method with body pose and human prior knowledge (2020, methodology): “We chose CASIA B Gait Dataset [32] since it contains the original color video frames.”
Multi-view large population gait dataset and its performance evaluation for cross-view gait recognition (2018, background): “As the database with a wide range of view angle, there exist Soton multimodal [23] (not released to the public), CASIA database B [21], CMU Mobo [24], AVA [25], WOSG [26], KY 4D [27], and OU-ISIR Treadmill Dataset C [28] (not released to the public).”
iLGaCo: Incremental Learning of Gait Covariate Factors (2020, methodology): “a small learning rate and a balanced set of samples. Finally, in the fourth stage, the memory is updated to include new samples. 4. Experiments 4.1. Dataset In our experiments, we use CASIA-B dataset [45], which contains 124 subjects recorded from 11 different view angles and three different walking”
Gaitgraph: Graph Convolutional Network for Skeleton-Based Gait Recognition (2021, methodology): “In this part, we compare GaitGraph to other SOTA meth-ods in public gait dataset CASIA-B [19].”
Gait Recognition via Effective Global-Local Feature Representation and Local Temporal Aggregation (2020, methodology): “The CASIA-B dataset [24] is the largest crossview gait database.”
Human Identification Using Temporal Information Preserving Gait Template (2012, methodology): “Example images from the three benchmark databases used in our evaluation experiments [8], [26], [27].”
GEINet: View-invariant gait recognition using a convolutional neural network (2016, background): “gait database [46], OU-ISIR Treadmill dataset [26], and TUMGAID [10], contain several covariate conditions, such as view angle, clothing, and carrying conditions.”
Robust arbitrary view gait recognition based on parametric 3D human body reconstruction and virtual posture synthesis (2016, methodology): “…decade, several gait databases larger than 100 people defined as large datasets in gait field have been published, e.g., USF HumanID [2], CASIA [3], SOTON [4] and WOSG [5], and studies have shown that personal identification could be achieved where the individual and environmental factors are…”
Gait recognition without subject cooperation (2010, methodology): “To evaluate the effectiveness of our proposed approach, extensive experiments are carried out on two comprehensive benchmarking databases: the CASIA database (Yu et al., 2006) and the Southampton Human ID at a distance gait database (SOTON database) (Shutler et al., 2002).”
Robust view transformation model for gait recognition (2011, background): “We also consider some results from [3, 5], although they are not belong to the factorization based VTM.”
GaitPart: Temporal Part-Based Model for Gait Recognition (2020, methodology): “2) In CASIA-B[17], the batch size is set to (8, 16) following the manner introduced in Sec3.”
A Study on Gait-Based Gender Classification (2009, methodology): “Database (Dataset B) [20] were shown on a computer screen at a rate of 25 frames per second, the same rate at which the video were recorded.”
GaitSet: Regarding Gait as a Set for Cross-View Gait Recognition (2018, methodology): “However, gait recognition suffers from exterior factors such as the subject’s walking speed, dressing and carrying Figure 1: From top-left to bottom-right are silhouettes of a completed period of a subject in CASIA-B gait dataset. condition, and the camera’s viewpoint and frame rate.”
What Else Does Your Biometric Data Reveal? A Survey on Soft Biometrics (2016, methodology): “Specifically, this work employed Adaboost and SVMs to classify human GEIs along with facial features that were related by canonical correlation analysis (CCA) on the CASIA Gait Database (Dataset B) [127] consisting of”