Evaluating a dancer's performance using kinect-based skeleton tracking

Alexiadis, Dimitrios S.; Kelly, Philip; Daras, Petros; O’Connor, Noel E.; Boubekeur, Tamy; Moussa, Maher Ben

doi:10.1145/2072298.2072412

Cited by 156 publications

(104 citation statements)

References 2 publications

Supporting

Mentioning

101

Contrasting

Order By: Relevance

“…As a low-cost and widely available approach to human motion sensing, the Kinect and the associated open source libraries have enabled researchers to target a range of next generation novel multimedia applications [3,17]. However, the Kinect is not without its own limitations.…”

Section: Introductionmentioning

confidence: 99%

Kinect vs. Low-cost Inertial Sensing for Gesture Recognition

Gowing

Ahmadi

Destelle

et al. 2014

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. In this paper, we investigate efficient recognition of human gestures / movements from multimedia and multimodal data, including the Microsoft Kinect and translational and rotational acceleration and velocity from wearable inertial sensors. We firstly present a system that automatically classifies a large range of activities (17 different gestures) using a random forest decision tree. Our system can achieve near real time recognition by appropriately selecting the sensors that led to the greatest contributing factor for a particular task. Features extracted from multimodal sensor data were used to train and evaluate a customized classifier. This novel technique is capable of successfully classifying various gestures with up to 91 % overall accuracy on a publicly available data set. Secondly we investigate a wide range of different motion capture modalities and compare their results in terms of gesture recognition accuracy using our proposed approach. We conclude that gesture recognition can be effectively performed by considering an approach that overcomes many of the limitations associated with the Kinect and potentially paves the way for low-cost gesture recognition in unconstrained environments.

show abstract

Section: Introductionmentioning

confidence: 99%

Kinect vs. Low-cost Inertial Sensing for Gesture Recognition

Gowing

Ahmadi

Destelle

et al. 2014

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…This interface will be called as a plugin in Unity3D. As what are needed in WBFS, we create DepthGenerator to read the depth image, UserGenerator to detect or delete image, GestureGenerator to call functions about body skeleton data and Hands Generator to call functions about hand point tracking [7]. We use callback function to read data from generators.…”

Section: B Openni Interfacementioning

confidence: 99%

WBFS: An Interactive Virtual Simulation Landscape System Based on Kinect

Peng¹,

He²,

Huang³

2015

Proceedings of the 2015 International Conference on Modeling, Simulation and Applied Mathematics

View full text Add to dashboard Cite

Abstract-Using gesture to implement 3D navigation still exists many problems to be solved. This paper introduces a solution about gesture interaction in 3D virtual scenes. In order to protect the intangible culture heritage of Dai Ethnic, a nationality of China, we designed and developed the interactive virtual simulation landscape system "Within the Bamboo Forest (WBFS)", where anyone can enjoy a virtual experience of travelling in a village of Dai Ethnic with a free tourist guide. At the respects of technology, we used a Kinect sensor as the bottom hardware layer to collect depth data, OpenNI and NITE plugins as the middle layer to analyze user's gestures, Unity3D Game Engine as the system top layer to integrate art resources and develop interfaces. This solution mainly achieves three aspects of interacting with Kinect sensor, they are sliding main-menu selection, roaming in 3D scenes and clicking 3D objects and elements in scenes.

show abstract

“…To engage a larger percentage of the research fraternity in solving these real time problems, many popular multinational research organizations are coming up with innovative challenges. For example, Huawei 3DLife/ EMC2 challenge [1] provides a platform for demonstrations of online human computer interactive systems and thus encourages the research community to solve the problems faced by the industry or improvise the already acquired solutions to move closer to the desired output. With the recent advent of internet, e-learning program has emerged as one of the most popular internet accessory, which helps a certain human being to acquire different skills online with the help of internet, which wouldn't have been possible for the user to learn in person otherwise.…”

Section: Introductionmentioning

confidence: 99%

“…Essid et al presented a new idea of multi modal dance collection based approach that facilitates the interaction between human beings in virtually framed environment [4]. As a response to the Huawei 3DLife challenge, Alexiadis et al proposed a Kinect based approach for creating an online dance evaluating software, which measures the worth of a performance with respect to a standard one and generates feedback for further improvement [1].…”

Section: Introductionmentioning

confidence: 99%

Human skeleton matching for e-learning of dance using a probabilistic neural network

Saha

Lahiri

Konar

et al. 2016

2016 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Abstract-With the growing interest in the domain of human computer interaction (HCI) these days, budding research professionals are coming up with novel ideas of developing more versatile and flexible modes of communication between a man and a machine. Using the attributes of internet, the scientists have been able to create a web based social platform for learning any desired art by the subject himself/herself, and this particular procedure is termed as electronic learning or e-learning. In this paper, we propose a novel application of gesture dependent elearning of dance. This e-learning procedure may provide help to many dance enthusiasts who cannot learn the art because of the scarcity of resources despite having great zeal. The paper mainly deals with recognition of different dance gestures of a trained user such that after detecting the discrepancies between the gestures shown and actually performed by a novice; the user can rectify his faults. The elementary knowledge of geometry has been employed to introduce the concept of planes in the feature extraction stage. Actually, five planes have been constructed to signify major body parts while keeping the synchronous parts in one unit. Then four distances and four angular features have been obtained to provide entire positional information of the different body joints. Finally, using a probabilistic neural network the dance gestures have been classified after training the said network with sufficient amount of data recorded from numerous subjects to maintain generality.

show abstract

Evaluating a dancer's performance using kinect-based skeleton tracking

Cited by 156 publications

References 2 publications

Kinect vs. Low-cost Inertial Sensing for Gesture Recognition

Kinect vs. Low-cost Inertial Sensing for Gesture Recognition

WBFS: An Interactive Virtual Simulation Landscape System Based on Kinect

Human skeleton matching for e-learning of dance using a probabilistic neural network

Contact Info

Product

Resources

About