A Unified Approach for Patient Activity Recognition in Healthcare Using Depth Camera

Abstract

Context-awareness is an essential part of pervasive computing. Video-based human activity recognition (HAR) has arisen as an imperative module to detect user's situation for involuntary facility delivery in context-aware domains. The activity recognition systems are frequently employed for protective and practical health care. Most of the existing works utilize RGB (red, green, and blue) cameras which present confidentiality and security concerns in the health-care domain. The existing approaches also do not sustain their performance results under the presence of a depth camera. Moreover, the accuracy of an HAR system relies on the extraction and selection of the prominent features from the feature space. To address these limitations, in this research, we first employ a depth camera to resolve the confidentiality and security concerns, and propose an unsupervised segmentation algorithm that can accurately segment the human body from the video frame. Then, we propose a new feature selection technique that has the ability to excerpt and select the best features from the feature space. Our proposed feature selection method focuses on the selection of confined features from the series of images and discriminate their category based on reversion (i.e., regression) value. The proposed method extracts and selects the best features through the benefits of forward selection and backward regression algorithms. Finally, we have trained and tested our proposed system by employing hidden Markov model (HMM) to label the activities. The proposed approach presents a significant performance against the existing works using depth camera.

Multi-Camera-Based Human Activity Recognition for Human–Robot Collaboration in Construction

“…For instance, Putra et al [ 54 ] achieved significant success in HAR by utilizing multi-view sequences of raw images and obtaining an impressive 90.3% accuracy. Similarly, Siddiqi et al [ 55 ] proposed an innovative Maximum Entropy Markov Model (MEMM) incorporating depth cameras, which led to an outstanding recognition accuracy of 96.3%. While these results are commendable, it is worth noting that depth cameras represent a recent technological advancement that provides 3D data, enabling them to capture additional spatial information.…”

An Efficient Feature Selection Method for Video-Based Activity Recognition Systems

“…en, these extracted features are utilized as the input for the classifier. However, this approach fails to show the significant performance in depth activities such as clapping and boxing that cannot be differentiated in RGB cameras [25].…”

Audio- and Video-Based Human Activity Recognition Systems in Healthcare

“…Our results show that privacy and security issues are barely considered, both in audio and video-based HAR, with only few research works that ensure the involvement of all stakeholders in order to increase the privacy and security level of the proposed HAR approach. Even though these works propose concrete steps to ensure a certain level of privacy such as employing privacy-by-context methods [45], written and verbal consent [15] or depth cameras and silhouettes [18], [21], [17], the effectiveness of these methods is not verified in real settings, and policies and legal issues are not sufficiently considered. Addressing the privacy and confidentiality related concerns of study participants by providing them with instructions to remove sensitive audio recordings from their devices, as in [15], may not be sufficient.…”

“…In video-based HAR, privacy and security are mostly addressed by technical approaches, e.g. by employing depth cameras and silhouettes [17], [18], [21]. In a privacy-bycontext setting, users are able to decide how, when and by whom they are watched [45], and may have their visual…”