Modeling spatiotemporal patterns of gait anomaly with a CNN-LSTM deep neural network

N Sadeghzadehyazdi, T Batabyal, ST Acton - Expert Systems with …, 2021 - Elsevier
In this work, we propose an end-to-end deep learning model that uses the skeleton data
recorded by Kinect to capture spatiotemporal patterns for gait anomaly recognition. Via …

Learning content and style: Joint action recognition and person identification from human skeletons

H Wang, L Wang - Pattern Recognition, 2018 - Elsevier
Humans are able to simultaneously identify a person and recognize his or her action based
on biological motions. Previous work usually treats action recognition and person …

Continuous detection of human fall using multimodal features from Kinect sensors in scalable environment

TH Tran, TL Le, VN Hoang, H Vu - Computer methods and programs in …, 2017 - Elsevier
Abstract Background and Objectives: Automatic detection of human fall is a key problem in
video surveillance and home monitoring. Existing methods using unimodal data …

Cross-view human action recognition from depth maps using spectral graph sequences

T Kerola, N Inoue, K Shinoda - Computer Vision and Image Understanding, 2017 - Elsevier
We present a method for view-invariant action recognition from depth cameras based on
graph signal processing techniques. Our framework leverages a novel graph representation …

Glidar3dj: a view-invariant gait identification via flash lidar data correction

N Sadeghzadehyazdi, T Batabyal… - … on Image Processing …, 2019 - ieeexplore.ieee.org
Gait recognition is a leading remote-based identification method, suitable for real-world
surveillance and medical applications. Model-based gait recognition methods have been …

GlidarCo: gait recognition by 3D skeleton estimation and biometric feature correction of flash lidar data

N Sadeghzadehyazdi, T Batabyal, NK Dhar… - arxiv preprint arxiv …, 2019 - arxiv.org
Gait recognition using noninvasively acquired data has been attracting an increasing
interest in the last decade. Among various modalities of data sources, it is experimentally …

Using skeleton correction to improve flash lidar-based gait recognition

N Sadeghzadehyazdi, T Batabyal… - Applied Artificial …, 2022 - Taylor & Francis
This paper presents GlidarPoly, an efficacious pipeline of 3D gait recognition for flash lidar
data based on pose estimation and robust correction of erroneous and missing joint …

Joint-angle-based yoga posture recognition for prevention of falls among older people

P Chezhiyan, DP - Data Technologies and Applications, 2019 - emerald.com
Purpose United Nations' World Population Ageing Report states that falls are one of the
most common problems in the elderly around the world. Falls are a leading cause of …

A posture recognition system for assisted self-learning of yoga by cognitive impaired older people for the prevention of falls

K Ponmozhi, P Deepalakshmi - EAI International Conference on Big Data …, 2020 - Springer
Abstract According to United Nation's World Population ageing report, every country is
facing an ageing issue by most of their citizens. It is estimated that 75% of fall injuries occur …

Ugrad: A graph-theoretic framework for classification of activity with complementary graph boundary detection

T Batabyal, ST Acton, A Vaccari - 2016 IEEE International …, 2016 - ieeexplore.ieee.org
Activity recognition and activity boundary detection are two separate long-standing
challenges in the image processing literature. In activity recognition, a predefined set of …