Try Walking in My Shoes, if You Can: Accurate Gait Recognition Through Deep Learning

Giorgi, Giacomo; Martinelli, Fabio; Saracino, Andrea; Sheikhalishahi, Mina

doi:10.1007/978-3-319-66284-8_32

Cited by 27 publications

(21 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They use IDnet dataset with misclassification rates less than 0.15%. Giorgi et al [151] show very high accuracies on a dataset of 175 subjects wearing body inertial sensors. Dehzangi et al [152] design a deep convolutional neural network to extract features from expanded gait cycles and jointly optimize the spatio-temporal features and identification model, although they had only 10 subjects and treated the identification problem as a 10-class classification problem.…”

Section: Deep Learning In Gait Recognitionmentioning

confidence: 99%

A Survey on Gait Recognition

2018

View full text Add to dashboard Cite

Recognizing people by their gait has become more and more popular nowadays due to the following reasons. First, gait recognition can work well remotely. Second, gait recognition can be done from low-resolution videos and with simple instrumentation. Third, gait recognition can be done without the cooperation of individuals. Fourth, gait recognition can work well while other features such as faces and fingerprints are hidden. Finally, gait features are typically difficult to be impersonated. Recent ubiquity of smartphones that capture gait patterns through accelerometers and gyroscope and advances in machine learning have opened new research directions and applications in gait recognition. A timely survey that addresses current advances is missing. In this article, we survey research works in gait recognition. In addition to recognition based on video, we address new modalities, such as recognition based on floor sensors, radars, and accelerometers; new approaches that include machine learning methods; and examine challenges and vulnerabilities in this field. In addition, we propose a set of future research directions. Our review reveals the current state-of-art and can be helpful to both experts and newcomers of gait recognition. Moreover, it lists future works and publicly available databases in gait recognition for researchers.

show abstract

Section: Deep Learning In Gait Recognitionmentioning

confidence: 99%

A Survey on Gait Recognition

2018

View full text Add to dashboard Cite

show abstract

“…Recently, deep learning has gained an extraordinary development and dramatically improved the state-of-the-art researches in many pattern recognition and machine learning tasks such as speech recognition, visual object recognition/detection [35]. Following that trend, many studies have adopted deep leaning techniques for the task of inertial sensor-based gait recognition and achieved new state-of-theart results [9]- [12], [14]- [16], [36].…”

Section: A Gait Recognitionmentioning

confidence: 99%

“…After that, several studies [14], [36] followed this trend by proposing others CNN architectures, and evaluated with different datasets (e.g., [19], [22]). On the other hand, some researches adopted CNN on the fused data of multiple sensors placing in different positions of the human body to improve the accuracy [9], [11]. Instead of directly using gait signals as the input of CNN, Zhao and Zhou [12] transformed gait signals to angle embedded gait dynamic image (AE-GDI), which is invariant to device's rotation or disorientation.…”

Section: A Gait Recognitionmentioning

confidence: 99%

“…To the best of our knowledge, there is no published research that focuses on proposing and analyzing a data augmentation method dedicated to inertial sensor-based gait data. There were only some simple methods, which were included in [9], [14]. In [9], each gait signal was diversified using a value drawn from a uniform distribution in the range of [−0.2, 0.2] to make an augmenting instance.…”

Section: B Data Augmentationmentioning

confidence: 99%

“…Although deep learning techniques have been applied and established new state-of-the-art researches in this field recently [9]- [12], [14]- [16], the scarcity of training data still endures as an obstacle that impedes to build a robust deep gait model [7]. Specifically, training a deep network usually requires a large and diverged dataset which covers a substantial number of data instances possibly occurring in practice [17], [18].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Data Augmentation for Inertial Sensor-Based Gait Deep Neural Network

Tran

Choi

2020

IEEE Access

View full text Add to dashboard Cite

Inertial sensor-based gait has been discovered as an attractive method for user recognition. Recently, with the approaching of deep learning techniques, new state-of-the-art researches have been established. However, the scarcity of training data still endures as an obstacle that impedes to build a robust deep gait model. In this study, we address that problem by proposing a novel approach for inertial sensor-based gait data augmentation. First, two label-preserving transformation algorithms, namely Arbitrary Time Deformation (ATD) and Stochastic Magnitude Perturbation (SMP), are proposed to generate more training data from the real gait data. The ATD algorithm adjusts the timing information of gait data with random values, on the other hand, SMP alters the magnitude arbitrarily, to create variations on the augmenting data. Then, we design a generic gait recognition model using convolutional neural network, in which, the ATD and SMP algorithms are coordinated appropriately to produce augmenting data varied naturally in both time and magnitude as real data. The proposed approach was evaluated on two public datasets, one was collected in unconstrained conditions, and the other had the largest number of participating users. The experiment showed that, under different amounts of training data, using ATD or SMP alone could increase the recognition performance effectively, and their combination even attained higher accuracy. With ATD and SMP, our model achieved competitive performance on both two datasets comparing to state-ofthe-art researches.

show abstract

Comparison of Orientation Invariant Inertial Gait Matching Algorithms on Different Substrate Types

Sawicki

Saeed

2022

New Advances in Dependability of Networks and Systems

View full text Add to dashboard Cite

Try Walking in My Shoes, if You Can: Accurate Gait Recognition Through Deep Learning

Cited by 27 publications

References 18 publications

A Survey on Gait Recognition

A Survey on Gait Recognition

Data Augmentation for Inertial Sensor-Based Gait Deep Neural Network

Comparison of Orientation Invariant Inertial Gait Matching Algorithms on Different Substrate Types

Contact Info

Product

Resources

About