A study on leg posture recognition from Indian classical dance using Kinect sensor

Abstract

This paper proposes a simple yet a novel technique to recognize leg postures in Indian classical dance by making use of a Kinect sensor. The sensor device has the ability to track the skeleton of the subject with the help of a visible camera and an IR camera coupled to an IR laser and diffraction grating. Twenty five leg postures from 'Odissi', an Indian Classical dance have been used for the evaluation our proposed algorithm. This methodology extracts eight features, which in turn can be categorized under three levels of symmetry viz. the vertical symmetry, the horizontal symmetry and the angular symmetry. Finally a similarity function is devised which is the basis of the leg posture recognition technique. This method provides better human computer interaction and also aims at spreading the dance form for e-learning purpose. The proposed algorithm can be applied for any dance form for leg posture recognition purposes. It gives 86.75% accuracy with five subjects.Index Terms-angular symmetry, human computer interaction, horizontal symmetry, leg posture, similarity function, vertical symmetry.

Indian Classical Dance Classification with Adaboost Multiclass Classifier on Multifeature Fusion

“…It shows the same result as above, making MCMLAB as the classifier for dance pose recognition with Haar, LBP, ZM, Hu moments, and SS giving satisfactory outcomes in robust comparisons. Figure 19 shows the percentage recognition obtained from methods in [20,21,23,24] along with the proposed early and late feature fusion models. The recognition percentage is averaged over the entire dataset.…”

“…For each dance pose video, a oneto-one matching on both node and edge feature is calculated. Recognition rate is calculated using (24). Multiclass SVM is the most trusted classifier for character recognition.…”

“…The other works proposed also used SVM classifier with simple image processing models on images of dancers for pose estimation which can be found in [21][22][23]. In [24], authors used Kinect sensor to capture leg poses in Indian classical dance forms and classification is initiated with SVM classifier for a set of 40 poses. Kinect sensor produces skeleton data of the human body pose and fails to reproduce data related to fingers which are important in classifying a dance pose.…”

Gesture Recognition of Dance using Chain Code and Hidden Markov Model

“…However, the amount of research on the introduction of the type of dance is still very limited. Introduction of the type of dance that has been recognized in many previous studies, among others: the classical dance of Indians [6], traditional dance Kazakh [5], traditional dance Greek [1], dance Bharatanatyam [6] and dance [7].…”

Recognition and Classification of Various Dance Forms by Using SVM Classifier

“…There is major investigation is carried out in [2] about shapes and large pixel size of image which is taken into account by using a algorithm of segmented interactive classifier and in this present proposed work used this technology for accurate and sharp identification images in the sets. The new superior computer vision model [3] is yield with aim to help for e-learning and self learning. This model is suitable for only [4] are taken into an account by principle "object extracting" challenge.…”