Sparse feature extraction for activity detection using low-resolution IR streams

Yordanka Karayaneva, Sara Sharifzadeh, Yanguo Jing, Kevin Chetty, Bo Tan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we propose an ultra-low-resolution infrared (IR) images based activity recognition method which is suitable for monitoring in elderly care-house 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 of the pixels in vectorised sequences of several IR frames, which results in a high dimensional feature space and an "n<; <; p" 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.
Original languageEnglish
Title of host publication2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA)
PublisherIEEE
ISBN (Electronic)9781728145501
DOIs
Publication statusPublished - 17 Feb 2020
Event2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA) - Boca Raton, United States
Duration: 16 Dec 201919 Dec 2019
https://www.icmla-conference.org/icmla19/

Conference

Conference2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA)
Abbreviated titleICMLA
Country/TerritoryUnited States
CityBoca Raton
Period16/12/1919/12/19
Internet address

Fingerprint

Dive into the research topics of 'Sparse feature extraction for activity detection using low-resolution IR streams'. Together they form a unique fingerprint.

Cite this