Yoga Pose Monitoring System using Deep Learning

Abstract

Activity recognition is the process of continuously monitoring a person’s activity and movement. Human posture recognition can be utilized to assemble a self-guidance practice framework that permits individuals to learn and rehearse yoga postures accurately without help from anyone else. Using Deep learning algorithms, an approach has been taken to accurately detect and recognize various yoga poses. The chosen dataset consists of a total of 85 videos with 6 yoga postures performed by 15 participants. Initially, keypoints of the user are extracted using the Mediapipe library. A combination of convolutional neural network (CNN) and long short-term memory (LSTM) has been used for Yoga pose recognition through real-time monitored videos as a deep learning model. CNN layer is used for extraction of features from the keypoints and it is followed by LSTM that understands the occurrence of sequence of frames for predictions to be made. Then, the poses are classified as correct or incorrect. If a correct pose is identified, the system will give the user feedback through text/speech.

Soil moisture content and fertility status of soil through intercropping of medicinal crops in guava orchard of Northern India

“…However, soil P content was recorded maximum under the growing of mentha crop (T4) and lower in guava sole system (T 7 ) at both depths. More or less, similar findings on beneficial effect of intercropping in increasing phosphorus availability in the soil have been reported by Swain and Patro (2007) and Kumar et al (2009). The available K status of soil was recorded highest when medicinal crops were grown under guava based intercropping as compared to guava sole.…”

“…Significantly maximum available N was recorded in T 4 , which was followed by T 6 and the lowest available nitrogen was found in T 7 . The results of enhanced N content of soil by intercropping in mango orchard have been reported by Swain and Patro (2007). Moreover, the nitrogen content of each block of intercropped declined with the soil depth which might be due to lower leaching losses as reported by Sharma and Choudhury (2002).…”

“…intercropping of medicinal crops under fruit orchard may be due to the addition of litter leaf of cover crops and root biomass promoting soil aggregation and improving structure which leads to increased pore space and ultimately decrease in bulk density (Singh et al 2012). Swain and Patro (2007) also reported a decrease in the bulk density of soil studying the effects of different intercropping in mango orchards.…”

Real Time Yoga Pose Detection Using Deeplearning: A Review

“…During the classification performance, warrior 2 exhibited the highest overall accuracy of 98.43%. Dehabrata Swain et al again used the hybrid CNN+ LSTM [8] system to classify, predict and assess the images. They used the time distributed system along CNN using 16 filters and a window size of 3.…”