A hierarchical privacy-preserving IoT architecture for vision-based hand rehabilitation assessment.

The healthcare industry requires the integration of digital technologies, such as Artificial Intelligence (AI) and the Internet of Things (IoT), to their full potential, particularly during this challenging time and the recent outbreak of the COVID-19 pandemic, which resulted in the disruptions in healthcare delivery, service operations, and shortage of healthcare personnel. However, every opportunity has barriers and bumps, and when it comes to IoT healthcare, data privacy is one of the main growing issues. Despite the recent advances in the development of IoT healthcare architectures, most of them are invasive for the data subjects. In this context, the broad applications of AI in the IoT domain have also been hindered by emerging strict legal and ethical requirements to protect individual privacy. Camera-based solutions that monitor human subjects in everyday settings, e.g., for Online Range of Motion (ROM) detection, are making this problem even worse. One actively practiced branch of such solutions is telerehabilitation, which provides remote solutions for the physically impaired to regain their strength and get back to their normal daily routines. The process usually involves transmitting video/images from the patient performing rehabilitation exercises and applying Machine Learning (ML) techniques to extract meaningful information to help therapists devise further treatment plans. Thereby, real-time measurement and assessment of rehabilitation exercises in a reliable, accurate, and Privacy-Preserving manner is imperative. To address the privacy issue of existing solutions, this paper proposes a holistic Privacy-Preserving (PP) hierarchical IoT solution that simultaneously addresses the utilization of AI-driven IoT and the demands for data protection. Furthermore, the efficiency of the proposed architecture is demonstrated by a novel machine learning-based system that allows immediate assessment and extraction of ROM as the critical information for analyzing the progress of patients.

Stability of Kinect for range of motion analysis in static stretching exercises.

Physical rehabilitation aims people with physical impairments to enhance and restore their functional ability. The Microsoft Kinect v1 and v2 technologies apply depth information and machine vision techniques to generate 3D coordinates of a set of anatomical landmarks on the human body regarded as Kinect joints. Trigonometry relationship between Kinect joints can be used to extract body Range of Motion (ROM). The purpose of this study was to evaluate stability of Kinect for ROM measurement during static stretching exercises. According to the literature, the stability of Kinect in static exercises has been reported to a limited extent. 13 healthy men participated in this study and performed 5 exercises in 2 different distances from the cameras. Exercises were recorded by Kinect v1 and Kinect v2, concurrently. The stability of Kinect was also evaluated for 5 ROMs including: elbow flexion, shoulder abduction, wrist pronation, wrist flexion, and wrist ulnar deviation. Maximum and average joint displacement errors were used for stability analysis. Results showed that Kinect v2 is more stable compared to Kinect v1. Kinect v2 joints showed displacement error of more than 15 mm for wrist. For the other joints, Kinect showed an average displacement error of less than 10 mm.

Correction: Intrinsic Image Decomposition via Structure-Preserving Image Smoothing and Material Recognition.

[This corrects the article DOI: 10.1371/journal.pone.0166772.].

Intrinsic Image Decomposition via Structure-Preserving Image Smoothing and Material Recognition.

Decoupling shading and reflectance from complex scene-images is a long-standing problem in computer vision. We introduce a framework for decomposing an image into the product of an illumination component and a reflectance component. Due to the ill-posed nature of the problem, prior information on shading and reflectance is mandatory. The proposed method adopts the premise that pixels in a region with similar chromaticity values should have the same reflectance. This assumption was used to minimize the l2 norm of the local per-pixel reflectance gradients to extract the shading and reflectance components. To obtain smooth chromatic regions, texture was treated in a new style. Texture was removed in the first step of the algorithm and the smooth image was processed for intrinsic decomposition. In the final step, texture details were added to the intrinsic components based on the material of each pixel. In addition, user-assistance was used to further refine the results. The qualitative and quantitative evaluation on the MIT intrinsic dataset indicated that the quality of intrinsic image decomposition was improved in comparison with previous methods.