Computational framework with novel features for classification of foot postures in Indian classical dance
About: This article is published in Intelligent Decision Technologies.The article was published on 2020-01-01. It has received 8 citations till now. The article focuses on the topics: Dance.
Citations
More filters
01 Mar 2021
TL;DR: A system that recognizes a yoga posture from an image or a frame of a video has been developed with the help of deep learning techniques like convolutional neural networks (CNN) and transfer learning.
Abstract: Yoga is a healthy practice that originated from India, to rejuvenate a man in his physical, mental, and spiritual wellness. Moving with the brisk technology advancements, there is a vast opportunity for computational probing in all social domains. But still, the utilization of artificial intelligence and machine learning techniques for applying to an interdisciplinary domain like yoga is quite challenging. In this work, a system that recognizes a yoga posture from an image or a frame of a video has been developed with the help of deep learning techniques like convolutional neural networks (CNN) and transfer learning. We have considered images of 10 different asanas for training the model as well as evaluating the prediction accuracy. The prediction model backed with transfer learning shows promising results with 85% prediction accuracy and this system can be considered as an initial step to build an automated yoga image and video analysis tool.
22 citations
Posted Content•
TL;DR: This paper is an attempt to review research work reported in the literature, categorize and group significant research work completed in a span of 1967–2020 in the field of automating dance, and identify six major categories corresponding to the use of computers in dance automation.
Abstract: Dance is an art and when technology meets this kind of art, it's a novel attempt in itself. Several researchers have attempted to automate several aspects of dance, right from dance notation to choreography. Furthermore, we have encountered several applications of dance automation like e-learning, heritage preservation, etc. Despite several attempts by researchers for more than two decades in various styles of dance all round the world, we found a review paper that portrays the research status in this area dating to 1990 \cite{politis1990computers}. Hence, we decide to come up with a comprehensive review article that showcases several aspects of dance automation.
This paper is an attempt to review research work reported in the literature, categorize and group all research work completed so far in the field of automating dance. We have explicitly identified six major categories corresponding to the use of computers in dance automation namely dance representation, dance capturing, dance semantics, dance generation, dance processing approaches and applications of dance automation systems. We classified several research papers under these categories according to their research approach and functionality. With the help of proposed categories and subcategories one can easily determine the state of research and the new avenues left for exploration in the field of dance automation.
7 citations
Cites methods from "Computational framework with novel ..."
...A classification system was developed by Shailesh & Judy [64] to classify the foot position (Stanas) of South Indian Classical Dance using a deep neural network and a Naive Bayes classifier....
[...]
TL;DR: In this paper, the authors have attempted to automate several aspects of dance, right from dance notation to choreography, and they have shown that dance is an art and when technology meets this kind of art, it is a novel attempt in itself.
Abstract: Dance is an art and when technology meets this kind of art, it is a novel attempt in itself. Many researchers have attempted to automate several aspects of dance, right from dance notation to chore...
5 citations
TL;DR: In this article , the Hidden Markov Model (HMM) and Long Short-Term Memory (LSTM) are used to recognize the dance sequence in Indian classical dance, em Bharatanatyam.
Abstract: Understanding the underlying semantics of performing arts like dance is a challenging task. Analysis of dance is useful to preserve cultural heritage, make video recommendation systems, and build tutoring systems. To create such a dance analysis application, three aspects of dance analysis must be addressed: (1) segment the dance video to find representative action elements, (2) recognize the detected action elements, and (3) recognize sequences formed by combining action elements according to specific rules. This paper attempts to address the three fundamental problems of dance analysis raised above, with a focus on Indian Classical Dance, em Bharatanatyam. Since dance is driven by music, we use both musical and motion information to extract action elements. The action elements are then recognized using machine learning and deep learning techniques. Finally, the Hidden Markov Model (HMM) and Long Short-Term Memory (LSTM) are used to recognize the dance sequence.
2 citations
TL;DR: A comprehensive view of approaches proposed in the various fields of computerized dance modeling that aid in cultural heritage preservation is presented in this paper , where the authors have developed various approaches to automate the dance, identify the gesture, poses and stance (Pose Recognition), recognize the dance forms, dance movement classification, etc.
Abstract: ‘Cultural heritage conservation’ encompasses all actions and measures taken towards the life of cultural heritage while strengthening the long-term preservation of its messages and values. It has acquired significant heedfulness in recent years due to its wide applications in the potential research fields of image analysis, machine intelligence, computer vision, and pattern recognition. Cultural heritage preservation comprises both tangible and intangible resources. A significant part of intangible resources constitutes performing art such as dance or music. The era of digitization made way for the digitized form of heritage artifacts, which helps preserve knowledge. Many researchers have developed various approaches to automate the dance, identify the gesture, poses, and stance (Pose Recognition), recognize the dance forms, dance movement classification, etc., with impressive achievements. We present a comprehensive view of approaches proposed in the various fields of computerized dance modeling that aid in cultural heritage preservation.
2 citations
References
More filters
TL;DR: The field of semantic segmentation as pertaining to deep convolutional neural networks is reviewed and comprehensive coverage of the top approaches is provided and the strengths, weaknesses and major challenges are summarized.
Abstract: During the long history of computer vision, one of the grand challenges has been semantic segmentation which is the ability to segment an unknown image into different parts and objects (e.g., beach, ocean, sun, dog, swimmer). Furthermore, segmentation is even deeper than object recognition because recognition is not necessary for segmentation. Specifically, humans can perform image segmentation without even knowing what the objects are (for example, in satellite imagery or medical X-ray scans, there may be several objects which are unknown, but they can still be segmented within the image typically for further investigation). Performing segmentation without knowing the exact identity of all objects in the scene is an important part of our visual understanding process which can give us a powerful model to understand the world and also be used to improve or augment existing computer vision techniques. Herein this work, we review the field of semantic segmentation as pertaining to deep convolutional neural networks. We provide comprehensive coverage of the top approaches and summarize the strengths, weaknesses and major challenges.
451 citations
22 Oct 2017
TL;DR: BlitzNet as discussed by the authors proposes a deep architecture that jointly performs object detection and semantic segmentation in one forward pass, allowing real-time computations, and it achieves state-of-the-art performance.
Abstract: Real-time scene understanding has become crucial in many applications such as autonomous driving. In this paper, we propose a deep architecture, called BlitzNet, that jointly performs object detection and semantic segmentation in one forward pass, allowing real-time computations. Besides the computational gain of having a single network to perform several tasks, we show that object detection and semantic segmentation benefit from each other in terms of accuracy. Experimental results for VOC and COCO datasets show state-of-the-art performance for object detection and segmentation among real time systems.
156 citations
Posted Content•
TL;DR: A deep architecture is proposed, called BlitzNet, that jointly performs object detection and semantic segmentation in one forward pass, allowing real-time computations and shows state-of-the-art performance forobject detection and segmentation among real time systems.
Abstract: Real-time scene understanding has become crucial in many applications such as autonomous driving. In this paper, we propose a deep architecture, called BlitzNet, that jointly performs object detection and semantic segmentation in one forward pass, allowing real-time computations. Besides the computational gain of having a single network to perform several tasks, we show that object detection and semantic segmentation benefit from each other in terms of accuracy. Experimental results for VOC and COCO datasets show state-of-the-art performance for object detection and segmentation among real time systems.
95 citations
05 Jun 2013
TL;DR: This work proposes gesture recognition algorithm for Indian Classical Dance Style using Kinect sensor, which gives a high recognition rate of 86.8% using SVM.
Abstract: This work proposes gesture recognition algorithm for Indian Classical Dance Style using Kinect sensor. This device generates the skeleton of human body from which twenty different junction 3-dimensional coordinates are obtained. Here we require only eleven coordinates for the proposed work. Basically six joints coordinates about right and left hands and five upper body joint coordinates are processed. A unique system of feature extraction have been used to distinguish between `Anger', `Fear', `Happiness', `Sadness' and `Relaxation'. This system checks whether the emotion is positive or negative with its intensity information. A total of twenty three features have been extracted based on the distance between different parts of the upper human body, the velocity and acceleration generated along with the angle between different joints. The proposed algorithm gives a high recognition rate of 86.8% using SVM.
46 citations
09 Jan 2012
TL;DR: A sparse representation based dictionary learning technique is used to address dance classification as a new problem in computer vision and to present a new action descriptor to represent a dance video which overcomes the problem of the “Bags-of-Words” model.
Abstract: In this paper, we address an interesting application of computer vision technique, namely classification of Indian Classical Dance (ICD). With the best of our knowledge, the problem has not been addressed so far in computer vision domain. To deal with this problem, we use a sparse representation based dictionary learning technique. First, we represent each frame of a dance video by a pose descriptor based on histogram of oriented optical flow (HOOF), in a hierarchical manner. The pose basis is learned using an on-line dictionary learning technique. Finally each video is represented sparsely as a dance descriptor by pooling pose descriptor of all the frames. In this work, dance videos are classified using support vector machine (SVM) with intersection kernel. Our contribution here are two folds. First, to address dance classification as a new problem in computer vision and second, to present a new action descriptor to represent a dance video which overcomes the problem of the “Bags-of-Words” model. We have tested our algorithm on our own ICD dataset created from the videos collected from YouTube. An accuracy of 86.67% is achieved on this dataset. Since we have proposed a new action descriptor too, we have tested our algorithm on well known KTH dataset. The performance of the system is comparable to the state-of-the-art.
39 citations