Use of Low-Resolution Infrared Pixel Array for Passive Human Motion Movement and Recognition

Karayaneva, Yordanka; Baker, Samuel White; Tan, Bo; Jing, Yanguo

doi:10.14236/ewic/hci2018.143

Cited by 17 publications

(13 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Around the same time, Basu and Rowe [2] showed that the same camera can be used to detect multiple people and track their motions as well as estimate the directions of movement. In a similar field, Tao et al [4] and Karayaneva et al [5] also proposed hand-crafted features that could be used in recognizing actions. A common denominator of all these works is the fact that they rely on handcrafted features in order to carry out the tasks.…”

Section: Action Recognition Based On Tpamentioning

confidence: 99%

Action Prediction Using Extremely Low-Resolution Thermopile Sensor Array For Elderly Monitoring

Morawski

Lie

Chiang

2021

2021 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

Accident anticipation for monitoring the elderly is an important topic given the global issue of the rapidly aging population. In this work, we propose a novel approach to elderly accident prevention by using a low-resolution (32x32 pixels) infrared camera -thermopile sensor array (TPA) -for the action prediction task. Such a kind of sensor ensures that the monitoring system is cost-effective, does not interfere with daily life of the user, and most importantly fully preserves their privacy which makes it suitable for use in hospitals, nursing homes and private residences. As the majority of accidents involving the elderly occurs when a person attempts to exit the bed unassisted, we concentrate our efforts on predicting that an elderly person will attempt to get off the bed without asking for help. Our system raises an alarm in such a case and informs the caregiver so that they can intervene and offer assistance. Our designed deeplearning model can predict that the elderly patient monitored has the intention to get off the bed by 8.12 seconds at an accuracy of 96.51% (based on our own dataset collected), on average according to experiments, before the action onset is observed.

show abstract

Section: Action Recognition Based On Tpamentioning

confidence: 99%

Action Prediction Using Extremely Low-Resolution Thermopile Sensor Array For Elderly Monitoring

Morawski

Lie

Chiang

2021

2021 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

show abstract

“…The ultra low-resolution IR images were used in some works. Researchers have applied SVM, RF and KNN on low-resolution raw pixels data and achieved 84.2% overall accuracy [12]. In [34], a Y/N fall detection strategy was developed based on a KNN framework using spatio-temporal pixel level statistics.…”

Section: B Learning-based Featuresmentioning

confidence: 99%

“…A comparison of the recognition accuracy is performed between each of the SDA and SPCA techniques and their corresponding non-sparse feature extraction methods, Reduced Rank LDA (RRLDA) [10] and Principal Component Analysis (PCA). Reviewing the existing pilot studies [9], [11], [12] on low resolution images for activity monitoring in healthcare projects however, no detailed analysis of the features of this new type of data based on sparse techniques and their tolerance to noise was found.…”

Section: Introductionmentioning

confidence: 99%

Sparse Feature Extraction for Activity Detection Using Low-Resolution IR Streams

Karayaneva

Sharifzadeh

Jing

et al. 2019

2019 18th IEEE International Conference on Machine Learning and Applications (ICMLA)

Self Cite

View full text Add to dashboard Cite

In this paper, we propose an ultra-lowresolution 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 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.

show abstract

“…Thus, IR devices represent an attractive solution to be deployed in care homes and hospitals. Current studies reveal significant recognition rates (>90%) for activities including standing, sitting, walking, falling, and others [13], [14], [15]. Contrarily to their advantages, IR devices suffer from a relatively low detection distance.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Doppler Radar Based Activity Recognition for e-Healthcare

Karayaneva

Sharifzadeh

et al. 2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

Passive radio frequency (RF) sensing and monitoring of human daily activities in elderly care homes is an emerging topic. Micro-Doppler radars are an appealing solution considering their nonintrusiveness, deep penetration, and high-distance range. Unsupervised activity recognition using Doppler radar data has not received attention, in spite of its importance in case of unlabelled or poorly labelled activities in real scenarios. This study proposes two unsupervised feature extraction methods for the purpose of human activity monitoring using Doppler-streams. These include a local Discrete Cosine Transform (DCT)-based feature extraction method and a local entropy-based feature extraction method. In addition, a novel application of Convolutional Variational Autoencoder (CVAE) feature extraction is employed for the first time for Doppler radar data. The three feature extraction architectures are compared with the previously used Convolutional Autoencoder (CAE) and linear feature extraction based on Principal Component Analysis (PCA) and 2DPCA. Unsupervised clustering is performed using K-Means and K-Medoids. The results show the superiority of DCT-based method, entropy-based method, and CVAE features compared to CAE, PCA, and 2DPCA, with more than 5%-20% average accuracy. In regards to computation time, the two proposed methods are noticeably much faster than the existing CVAE. Furthermore, for high-dimensional data visualisation, three manifold learning techniques are considered. The methods are compared for the projection of raw data as well as the encoded CVAE features. All three methods show an improved visualisation ability when applied to the encoded CVAE features.

show abstract

Use of Low-Resolution Infrared Pixel Array for Passive Human Motion Movement and Recognition

Cited by 17 publications

References 8 publications

Action Prediction Using Extremely Low-Resolution Thermopile Sensor Array For Elderly Monitoring

Action Prediction Using Extremely Low-Resolution Thermopile Sensor Array For Elderly Monitoring

Sparse Feature Extraction for Activity Detection Using Low-Resolution IR Streams

Unsupervised Doppler Radar Based Activity Recognition for e-Healthcare

Contact Info

Product

Resources

About