A Survey of Computer Vision-Based Human Motion Capture

Moeslund, Thomas B.; Granum, Erik

doi:10.1006/cviu.2000.0897

Cited by 1,422 publications

(688 citation statements)

References 116 publications

Supporting

Mentioning

642

Contrasting

Unclassified

Order By: Relevance

“…MoCap is a well-studied and broad research area that has been explored in multiple different research fields including computer vision, computer graphics and even body sensor networks [15,12,19,14]. The various different approaches are numerous and include approaches based on mechanical, inertial, magnetic, acoustic and visual sensing etc.…”

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

“…Contributions include those from Deutscher et al [1], Mikić et al [10], and Sidenbladh et al [13]. For a comprehensive survey of the whole area of visual motion capture up to the year 2000, see work by Moeslund [12]. This paper demonstrates the feasibility of tracking human pose during complex movements of multiple people in a multi-camera studio environment, with strong emphasis on efficiency.…”

Section: Introductionmentioning

confidence: 90%

Simultaneous Pose Estimation of Multiple People using Multiple-View Cues with Hierarchical Sampling

Mitchelson¹,

Hilton²

2003

Procedings of the British Machine Vision Conference 2003

View full text Add to dashboard Cite

“…Derpanis in [10] reviewed the vision based hand gestures for human computer interaction. Detailed discussion on the feature set, classification method and the underlying representation of gesture set has been done.…”

Section: Related Workmentioning

confidence: 99%

An Effectual Approach in Biased Shape Matching for Gesture Recognition using LTrP and SIFT Algorithm

Raut¹

2015

IJIRCCE

View full text Add to dashboard Cite

ABSTRACT:Here a new approach for matching partially provided more efficiently and easily using local standard Tetra (LTrP) algorithm to extract size and feature a constant feature transformation (SIFT) for matching points function. The main idea and the major contributors to this work lies in matching textures and recognition and thus provide some special features such as the stability of size, deformation and orientation tolerance and free nature. In the heart of the proposed system is As if new format also allows measuring the local level. Calculated descriptors form an open or closed manner along the spatially non-uniform features. LTrP model proposes to extract the fabric texture image properties Sift then able to implement texture classification and recognition algorithm. Due to the properties of descriptor newly proposed format, and the method used for extraction and matching technology, the proposed approach and takes the form of a partial match more efficiently.

show abstract

A Survey of Computer Vision-Based Human Motion Capture

Cited by 1,422 publications

References 116 publications

Kinect vs. Low-cost Inertial Sensing for Gesture Recognition

Kinect vs. Low-cost Inertial Sensing for Gesture Recognition

Simultaneous Pose Estimation of Multiple People using Multiple-View Cues with Hierarchical Sampling

An Effectual Approach in Biased Shape Matching for Gesture Recognition using LTrP and SIFT Algorithm

Contact Info

Product

Resources

About