ABSTRACT
A patient recovering from a stroke, injury, or physical pain needs continuous physiotherapy and rehabilitation to achieve a quick and complete recovery. It is often difficult for elderly people to visit clinics to undertake exercises. Finding physiotherapists and relevant treatments becomes more difficult, particularly in an epidemic condition like covid-19. AI-driven at-home physiotherapy exercise monitoring and assessment systems can be the straightforward feasible solution in this regard. Accurate recognition of particular exercises, exercise assessments, providing feedback, etc. are parts of the whole system, which a machine typically learns through a data-heavy training process. A key issue in this regard is the lack of specific training data for physiotherapy exercises. There exist only a few datasets in the literature that are designed for physiotherapy exercises;most of them however are based on multiple body sensors or Kinect device. Sensor devices are quite costly, and their availability is not guaranteed everywhere. In contrast, video data can be a better alternative, where video can be acquired easily from an available smartphone camera or desktop/laptop webcam. Addressing this issue, we present a new video-based physiotherapy exercise database containing 1237 video clips of 14 physiotherapy exercises that were carefully elicited from an extensively conducted survey from multiple physiotherapists. Exercises were recorded with 28 male and female subjects within various lighting conditions, camera angles, and camera jitters to simulate the real-world setting. Several machine learning algorithms were utilized to carry out an experimental study on the dataset, and the results are provided for future reference. © 2022 IEEE.
ABSTRACT
In addressing the worldwide Covid-19 pandemic situation, the process of flattening the curve for coronavirus cases will be difficult if the citizens do not take action to prevent the spread of the virus. One of the most important practices in these outbreaks is to ensure a safe distance between people in public. This paper presents the detection of people with social distance monitoring as a precautionary measure in reducing physical contact between people. This study focuses on detecting people in areas of interest using the MobileNet Single Shot Multibox Detector (SSD) object tracking model and OpenCV library for image processing. The distance will be computed between the persons detected in the captured footage and then compared to a fixed pixels' values. The distance is measured between the central points and the overlapping boundary between persons in the segmented tracking area. With the detection of unsafe distances between people, alerts or warnings can be issued to keep the distance safe. In addition to social distance measure, another key feature of the system is detecting the presence of people in restricted areas, which can also be used to trigger warnings. Some analysis has been performed to test the effectiveness of the program for both purposes. From the results obtained, the distance tracking system achieved between 56.5% to 68% accuracy for testing performed on outdoor and challenging input videos, while 100% accuracy was achieved for the controlled environment on indoor testing. Whereas for the safety violation alert feature based on segmented ROI, it was found to have achieved better accuracy, i.e. between 95.8% to 100% for all tested input videos. © 2020 IEEE.