Individual recognition using gait energy image

By Ju Han, Bir Bhanu. 2006

1,935 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Human-Computer Interaction

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

In Human-Computer Interaction

Citations in the corpus

Scene Flow to Action Map: A New Representation for RGB-D Based Action Recognition with Convolutional Neural Networks (2017, background): “There are several ways to encode the video sequences into dynamic images [2, 25, 60, 51, 52, 1], but how to encode the scene flow vectors into one dynamic image still needs to be explored.”
Gaitgraph: Graph Convolutional Network for Skeleton-Based Gait Recognition (2021, background): “Early approaches proposed to encode a gait cycle into a single image, i.e., Gait Energy Image (GEI) [12].”
A Comprehensive Study on Cross-View Gait Based Human Identification with Deep CNNs (2017, methodology): “As one common pipeline, appearance-based approaches first obtain human silhouettes from all frames in a video; compute a gait energy image [5] by aligning the silhouettes in the spatial space and averaging them along the temporal dimension; then evaluate the similarities between pairs of GEIs,…”
Pattern Recognition (2018, positive): “Gait energy images (GEI) [29] which are the average silhouettes along the temporal dimension have been proved to be successful for gait recognition.”
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.”
Saliency Weighted Features for Person Re-identification (2014, background): “[17, 25, 29, 33]) exploit human-defined person models that are matched using distance measures”
Recurrent Attention Models for Depth-Based Person Identification (2016, methodology): “stances between skeleton joints [52]. Multi-Shot Identiﬁcation. Table 3 list several multishot methods. (1-2) We use random and human performance as baselines. (3-4) We evaluate the gait energy image [26] and volume [63]. (5-6) These methods use handcrafted skeleton features with an inter-frame voti”
Dissimilarity-based people re-identification and search for intelligent video surveillance (2013, background): “Among the approaches to characterise gait, the recently proposed Gait Energy Image (GEI) [65] has attracted the attention of many researchers.”
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].”
MPCA: Multilinear Principal Component Analysis of Tensor Objects (2008, methodology): “recommended by the authors of [5], and the ETGLDA results shown are obtained with , determined empirically.”
MARS: A Video Benchmark for Large-Scale Person Re-Identification (2016, methodology): “In our experiment, the size of GEI is 80× 30, which is reshaped into a column as the final vector.”
GaitPart: Temporal Part-Based Model for Gait Recognition (2020, methodology): “For the temporal changing characteristics, some of these state-of-art methods do not model temporal features explicitly, which leads to the loss of important invariant features in time series[23, 7, 3, 26].”
Robust view transformation model for gait recognition (2011, methodology): “Besides, Gait Energy Image (GEI) [11] has been constructed as gait feature descriptor based on the previous period estimation.”
A Study on Gait-Based Gender Classification (2009, methodology): “Unlike the segmentation in [3], the borders between the different components lie in the inner part of the GEI because pixel values there are almost the same for males or females.”
Person Re-identification: Past, Present and Future (2016, background): “Its features include HOG3D [106] and the gait energy image (GEI) [107].”
Motion history image: its variants and applications (2012, methodology): “(Year) Employed databases (DB)/Applications Results (RR)/Features (F)/Classifier (C)/ Comments [147] (2006) DB: 10 activities by 9 subjects [62] RR: ∼100%; F: AME, mean motion shape (MSS); C: KNN, NN, NN with class exemplar (ENN), Summation of Absolute Difference, Mahalanobis distance [139] (2007) D”
A model-based gait recognition method with body pose and human prior knowledge (2020, methodology): “GEI+PCA [4] is one simple approach of GEI-based methods, it can achieve good accuracy when there are no obvious variations.”
GaitSet: Regarding Gait as a Set for Cross-View Gait Recognition (2018, methodology): “Further, deep neural networks like 3D-CNN for extracting sequential information are harder to train than those using a single template like Gait Energy Image (GEI) (Han and Bhanu 2006).”
Human Identification Using Temporal Information Preserving Gait Template (2012, methodology): “Motivated by their work, Han and Bhanu [1] proposed the concept of GEI , and constructed the real and synthetic gait templates to improve the accuracy of gait recognition.”
GEINet: View-invariant gait recognition using a convolutional neural network (2016, methodology): “A typical example is gait energy image (GEI) [8], also known as an averaged silhouette [23], which is regarded as a mixture of static and dynamic features.”