Human Body Recognition
Ankita Mishra, Kapil Verma, Baljender Kaur, Anurag Shrivastava
Department of Computer Science and Engineering,
Babu Banarasi Das Northern Institute of Technology, Lucknow
ABSTRACT
The human activity monitoring system helps to differentiate a person's physical actions such as walking, clapping, shaking hands etc. Activity awareness is the foundation for the development of many potential applications for health, wellness and sports. HAR has a variety of uses because of its impact on health. Helps users improve quality of life in areas such as aged care, daily logging, personal fitness software. Personal Performance Recognition is a field for identifying basic human activity and is currently being used in various fields where important information about an individual's ability to work and lifestyle.
As the famous saying goes "Exercise not only changes our body it changes our mind, our mood, and our attitude". Fitness is a practice today. Everyone wants to be fit, to be beautiful, and to be healthy. But during this epidemic, not everyone can hire a coach or go to the gym. Another option is wearable devices that not everyone can afford. This paper proposed an AI trainer model. The proposed model used by anyone regardless of age and health status. The AI model uses Personal Status Evaluation. It is a popular method and determines the location and posture of the human body. This technique creates important points in the human body and is based on the fact that it creates a virtual skeletal structure in the 2D dimension. Featured is a live video taken from a person's webcam and the output captures location marks or key points in the human body. The AI trainer specifies the calculation and timing of the settings that a person must perform. It also specifies errors and feedback if any. This paper provides a way to use the stop rate that works on the CPU to get the correct points. Based on points touch and other curls (biceps) are calculated. This paper proposes a method that uses OpenCV to use a stand-alone model.
Keywords: Pose Estimation, Real Time Body Detection, movement Classification, BlazePose Model, Activity Recognition.