Gait Recognition Based on Deep Learning: A Survey

Santos, Claudio Filipi Gonçalves dos; Oliveira, Diego de Souza; Passos, Leandro Aparecido; Pires, Rafael G.; Santos, Dimas Oliveira; Valem, Lucas Pascotti; Moreira, Thierry Pinheiro; Santana, Marcos Cleison Silva; Roder, Mateus; Papa, João Paulo; Colombo, Danilo

doi:10.1145/3490235

Cited by 45 publications

(10 citation statements)

References 136 publications

(177 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As introduced in [44], LSTM is a type of Recurrent Neural Network (RNN) designed to provide improved results for problems which involve long sequences of data [45]. The main difference between LSTM and RNN is the construction of the LSTM which contains three components.…”

Section: Classificationmentioning

confidence: 99%

“…The main difference between LSTM and RNN is the construction of the LSTM which contains three components. An LSTM cell contains a forget gate which controls how much information is retained, an input gate which updates the values contained in the hidden states, and an output gate which updates the cells output value [45]. For the given task of person identification, the LSTM model is an appropriate model because of the time-series nature of the data involved and the ability of LSTM to learn temporal dependencies between data samples [46].…”

Section: Classificationmentioning

confidence: 99%

See 1 more Smart Citation

Gait Identification Using Limb Joint Movement and Deep Machine Learning

et al. 2022

View full text Add to dashboard Cite

Person identification is a key problem in the security domain and may be used to automatically identify criminals or missing persons. The traditional face matching approaches adopted by the police and security services across the world have recently been shown to produce a high rate of false positive identification. Alternatively, gait-based person identification has shown to be a convenient method particularly as it can be performed at a distance, without the cooperation of the subject, and is a biometric trait which cannot be easily disguised. In this work, we propose a gait-based person identification approach which uses limb joint motion data and deep machine learning models to identify the individuals. Distinct statistical features are identified and extracted from limb movement using a fixed width sliding window to train a Long Short-Term Memory model. The proposed solution outperforms the existing methods producing 98.87% accuracy when evaluated over unseen samples. In addition, we propose a simple two-stage filtering approach to increase the prediction accuracy up to 100% when identifying individuals from larger sequences of samples. This finding may improve the current solutions in controlled environments such as airports. In the future, this approach may help to overcome the problem of occlusion in gait-based identification, as unlike the existing works, it does not require information regarding the entire body. The study also presents a primary dataset comprising limb joint movement acquired from a diverse range of participants during casual walking captured through two digital goniometers.

show abstract

Section: Classificationmentioning

confidence: 99%

Section: Classificationmentioning

confidence: 99%

Gait Identification Using Limb Joint Movement and Deep Machine Learning

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The first author of this work has also worked in other research areas, such as biopsy cancer classification [47] and biometry identification by gait recognition [48], [49]. Table VII shows other papers the author proposed, however, they are not related directly to the main problem of the thesis.…”

Section: B Other Publications As First Authormentioning

confidence: 99%

Avoiding Overfitting: new algorithms to improve generalization in Convolutional Neural Networks

Santos

Papa

2022

Anais Estendidos Do XXXV Conference on Graphics, Patterns and Images (SIBGRAPI Estendido 2022)

View full text Add to dashboard Cite

Deep Learning has achieved state-of-the-art results in several domains, such as im- age processing, natural language processing, and audio processing. To accomplish such results, it uses neural networks with several processing layers along with a massive amount of labeled information. One particular family of Deep Learning is the Convolutional Neural Networks (CNNs), which work using convolutional layers de- rived from the digital signal processing area, being very helpful to detect relevant features in unstructured data, such as audio and pictures. One way to improve results on CNN is to use regularization algorithms, which aim to make the training process harder but generate models that generalize better for inference when used in applications. The present work contributes to the area of regularization methods for CNNs, proposing more methods for use in different image processing tasks. This thesis presents a collection of works developed by the author during the research period, which were published or submitted until the present time, presenting: (i) a survey, listing recent regularization works and highlighting the solutions and problems of the area; (ii) a neuron dropping method to use in the tensors generated during CNNs training; (iii) a variation of the mentioned method, changing the dropping rules, targeting different features of the tensor; and (iv) a label regularization algorithm used in different image processing problems.

show abstract

“…We refer to the recent survey of dos Santos et al. [37] on the application of deep learning for gait recognition. The authors review several deep learning methods, including the well‐known CNNs and RNNs, but also Deep Belief Networks (DBNs), Capsule Networks (CNs), AutoEncoders (AEs), and Generative Adversarial Networks (GANs).…”

Section: Related Workmentioning

confidence: 99%

Discriminative training of spiking neural networks organised in columns for stream‐based biometric authentication

et al. 2022

View full text Add to dashboard Cite

Stream-based biometric authentication using a novel approach based on spiking neural networks (SNNs) is addressed. SNNs have proven advantages regarding energy consumption and they are a perfect match with some proposed neuromorphic hardware chips, which can lead to a broader adoption of user device applications of artificial intelligence technologies. One of the challenges when using SNNs is the discriminative training of the network since it is not straightforward to apply the well-known error backpropagation (EBP), massively used in traditional artificial neural networks (ANNs). A network structure based on neuron columns is proposed, resembling cortical columns in the human cortex, and a new derivation of error backpropagation for the spiking neural networks that integrate the lateral inhibition in these structures. The potential of the proposed approach is tested in the task of inertial gait authentication, where gait is quantified as signals from Inertial Measurement Units (IMU), and the authors' approach to state-of-the-art ANNs is compared. In the experiments, SNNs provide competitive results, obtaining a difference of around 1% in half total error rate when compared to state-of-the-art ANNs in the context of IMU-based gait authentication.This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

Gait Recognition Based on Deep Learning: A Survey

Cited by 45 publications

References 136 publications

Gait Identification Using Limb Joint Movement and Deep Machine Learning

Gait Identification Using Limb Joint Movement and Deep Machine Learning

Avoiding Overfitting: new algorithms to improve generalization in Convolutional Neural Networks

Discriminative training of spiking neural networks organised in columns for stream‐based biometric authentication

Contact Info

Product

Resources

About