International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 10 Issue: 04 | Apr 2023 2023
p-ISSN: 2395-0072
www.irjet.net
AI Personal Trainer Using Open CV and Media Pipe Kriti Ohri1, Akula Nihal Reddy2, Sri Soumya Pappula3, Penmetcha Bhargava Datta Varma4, Sara Likhith Kumar5, Sonika Goud Yeada6 1 Assistant Professor, Dept. of Computer Science and Engineering, VNR Vignana Jyothi Institute of Engineering and
Technology, Hyderabad, India 2,3,4,5,6 Student, Dept. of Computer Science and Engineering, VNR Vignana Jyothi Institute of Engineering and
Technology, Hyderabad, India ---------------------------------------------------------------------***--------------------------------------------------------------------digital coaches, the term "AI personal trainer" is no longer Abstract - Many individuals are experiencing health a fresh one. issues as a result of insufficient physical activity. Due to social distancing, a large number of workout To begin, let's define an AI personal trainer for those who facilities were closed during the pandemic. As a result, are unfamiliar with it. "AI personal trainers are artificial people began training at home without the guidance intelligence-powered virtual trainers who assist you in of a trainer, which can lead to severe injuries if achieving your fitness goals. The computerized personal exercises are performed incorrectly. Our project aims trainer may provide you with tailored training and diet regimens after gathering a few facts such as body to help users achieve their desired physique by measurements, current fitness level, fitness objectives, and providing a personalized trainer, customized workout more." plan, and diet plan. Furthermore, we facilitate the connection of users with similar workout goals since Nowadays, Every person needs a customized trainer, having a workout partner increases motivation. To which takes time and money to provide. Artificial accomplish this, we employ OpenCV and Media Pipe to Intelligence technology, therefore be used to speed up the detect the user's posture and analyze the pose's angles customizing process by determining the best exercise and geometry in real-time video, while using Flask to regimen for a certain student's demands or preferences. develop the web application's front end.
Therefore, our goal is to create an AI-based trainer that will enable everyone to exercise more effectively in the comfort of their own homes. The aim of this project is to build an AI that will assist you in exercising by calculating the quantity and quality of repetitions using pose estimation. This project is intended to make exercise easier and more fun by correcting the posture of the human body and also by connecting with people having similar workout goals.
Key Words: BlazePose, Media Pipe, Open CV, COCO Data Set, Open Pose.
1. INTRODUCTION The significance of exercise in maintaining good health is well-known. However, it is equally important to exercise in the correct manner. Over-exercising can lead to severe bodily harm such as muscle tears and can hinder muscular hypertrophy. Home-based workouts have gained popularity in recent times due to their convenience and time-saving benefits.
This study presented an objective discussion of the usage of AI technology to select a suitable virtual fitness trainer based on user-submitted attributes.
2. RELATED WORK
During the pandemic, many people realized the importance of maintaining physical fitness and that it was possible to exercise at home. While some individuals cannot afford a gym membership or feel uncomfortable working out in a gym with weights, others have the financial means to hire trainers and join gyms but struggle with inconsistent schedules that hinder their ability to prioritize their health and fitness.
Initially, it started with body posture detection proposed by Jamie Shotton et al., [1] who used the Kinect Camera, which produces 640x480 images at a frame rate of 30 frames per second with a few centimeters of depth resolution. The depth image characteristics show that pixels are being identified. These characteristics work well together in a decision forest to distinguish all trained sections even though individually they merely provide a weak indication of which region of the body the pixel is
At that point, AI personal trainers started to appear. Since there are already so many digital fitness programmers and
© 2023, IRJET
|
Impact Factor value: 7.529
|
ISO 9001:2008 Certified Journal
|
Page 913