TY - GEN
T1 - Sparse Feature Extraction for Activity Detection Using Low-Resolution IR Streams
AU - Karayaneva, Yordanka
AU - Sharifzadeh, Sara
AU - Jing, Yanguo
AU - Cherry, Kevin
AU - Tan, Bo
N1 - © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
PY - 2019
Y1 - 2019
N2 - In this paper, we propose an ultra-low resolution infrared (IR) images based activity recognition method which is suitable for monitoring in elderly carehouse and modern smart home. The focus is on the analysis of sequences of IR frames, including single subject doing daily activities. The pixels are considered as independent variables because of the lacking of spatial dependencies between pixels in the ultra-low resolution image. Therefore, our analysis is based on the temporal variation ofthe pixels in vectorised sequences of several IR frames, which results in a high dimensional feature space and an ”np” problem. Two different sparse analysis strategies are used and compared: Sparse Discriminant Analysis (SDA) and Sparse Principal Component Analysis (SPCA). The extracted sparse features are tested with four widely used classifiers: Support Vector Machines (SVM), Random Forests (RF), K-Nearest Neighbours (KNN) and Logistic Regression (LR). To prove the availability of the sparse features, we also compare the classification results of the noisy data based sparse features and non-sparse based features respectively. The comparison shows the superiority of sparse methods in terms of noise tolerance and accuracy.
AB - In this paper, we propose an ultra-low resolution infrared (IR) images based activity recognition method which is suitable for monitoring in elderly carehouse and modern smart home. The focus is on the analysis of sequences of IR frames, including single subject doing daily activities. The pixels are considered as independent variables because of the lacking of spatial dependencies between pixels in the ultra-low resolution image. Therefore, our analysis is based on the temporal variation ofthe pixels in vectorised sequences of several IR frames, which results in a high dimensional feature space and an ”np” problem. Two different sparse analysis strategies are used and compared: Sparse Discriminant Analysis (SDA) and Sparse Principal Component Analysis (SPCA). The extracted sparse features are tested with four widely used classifiers: Support Vector Machines (SVM), Random Forests (RF), K-Nearest Neighbours (KNN) and Logistic Regression (LR). To prove the availability of the sparse features, we also compare the classification results of the noisy data based sparse features and non-sparse based features respectively. The comparison shows the superiority of sparse methods in terms of noise tolerance and accuracy.
KW - infrared data
KW - sparse feature extraction
KW - healthcare applications
U2 - 10.1109/ICMLA.2019.00296
DO - 10.1109/ICMLA.2019.00296
M3 - Other contribution
SN - 978-1-7281-4551-8
PB - IEEE
ER -