Realtime human motion control with a small number of inertial sensors

Liu, Huajun; Wei, Xiaolin; Chai, Jinxiang; Ha, Inwoo; Rhee, Taehyun

doi:10.1145/1944745.1944768

Cited by 88 publications

(101 citation statements)

References 27 publications

Supporting

Mentioning

101

Contrasting

Order By: Relevance

“…Our work is also relevant to recent efforts in realtime full-body motion capture using only a few sensors [Chai and Hodgins 2005;Slyper and Hodgins 2008;Liu et al 2011;Tautges et al 2011]. Reconstructing human poses from a small number of sensors is often an ill-posed problem.…”

Section: Related Workmentioning

confidence: 96%

“…One good way to reduce the ambiguity is to utilize prior knowledge embedded in prerecorded motion data. A number of researchers have explored how to utilize prerecorded motion capture data to reduce the reconstruction ambiguity from low-dimensional control signals obtained from a sparse number of markers [Chai and Hodgins 2005] or inertial sensors [Slyper and Hodgins 2008;Liu et al 2011;Tautges et al 2011]. Our work is different because we focus on markerless motion capture using a single depth camera.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Accurate realtime full-body motion capture using a single depth camera

Wei¹,

Zhang²,

Chai³

2012

ACM Trans. Graph.

Self Cite

196

150

View full text Add to dashboard Cite

Figure 1: Our system automatically and accurately reconstructs 3D skeletal poses in real time using monocular depth data obtained from a single camera. (top) reference image data; (bottom) the reconstructed poses overlaying depth data. AbstractWe present a fast, automatic method for accurately capturing fullbody motion data using a single depth camera. At the core of our system lies a realtime registration process that accurately reconstructs 3D human poses from single monocular depth images, even in the case of significant occlusions. The idea is to formulate the registration problem in a Maximum A Posteriori (MAP) framework and iteratively register a 3D articulated human body model with monocular depth cues via linear system solvers. We integrate depth data, silhouette information, full-body geometry, temporal pose priors, and occlusion reasoning into a unified MAP estimation framework. Our 3D tracking process, however, requires manual initialization and recovery from failures. We address this challenge by combining 3D tracking with 3D pose detection. This combination not only automates the whole process but also significantly improves the robustness and accuracy of the system. Our whole algorithm is highly parallel and is therefore easily implemented on a GPU. We demonstrate the power of our approach by capturing a wide range of human movements in real time and achieve state-ofthe-art accuracy in our comparison against alternative systems such as Kinect [2012].

show abstract

Section: Related Workmentioning

confidence: 96%

Section: Related Workmentioning

confidence: 99%

Accurate realtime full-body motion capture using a single depth camera

Wei¹,

Zhang²,

Chai³

2012

ACM Trans. Graph.

Self Cite

196

150

View full text Add to dashboard Cite

show abstract

“…Since human motion is highly non-linear, learning statistical dynamic models as a motion prior can produce movements that better satisfy the required constraints [9]. Such a motion prior concept is applied to real-time pose reconstruction by generating higher quality movements [25]. When adapting this idea to accelerometer-based systems, an online lazy neighbourhood graph is used to minimize false positive samples in the local subspace [38].…”

Section: Pose Reconstructionmentioning

confidence: 99%

Filtered pose graph for efficient kinect pose reconstruction

Plantard

Shum

Multon

2016

Multimed Tools Appl

View full text Add to dashboard Cite

Being marker-free and calibration free, Microsoft Kinect is nowadays widely used in many motion-based applications, such as user training for complex industrial tasks and ergonomics pose evaluation. The major problem of Kinect is the placement requirement to obtain accurate poses, as well as its weakness against occlusions. To improve the robustness of Kinect in interactive motion-based applications, real-time data-driven pose reconstruction has been proposed. The idea is to utilize a database of accurately captured human poses as a prior to optimize the Kinect recognized ones, in order to estimate the true poses performed by the user. The key research problem is to identify the most relevant poses in the database for accurate and efficient reconstruction. In this paper, we propose a new pose reconstruction method based on modelling the pose database with a structure called Filtered Pose Graph, which indicates the intrinsic correspondence between poses. Such a graph not only speeds up the database poses selection process, but also improves the relevance of the selected poses for higher quality reconstruction. We apply the proposed method in a challenging environment of industrial context that involves sub-optimal Kinect placement and a large amount of occlusion. Experimental results show that our real-time system reconstructs Kinect poses more accurately than existing methods.

show abstract

“…However, many of these systems su↵er from tracking errors due to marker occlusions. Inertial Measurement Units (IMUs) o↵er an accurate MoCap alternative [9,3] and have been developed into commercially successful systems, such as XSens [11], however they are still prone to drift in accuracy over time, a common limitation of inertial sensing. IMUs are low power, light weight, o↵er high sample rates and do not su↵er from occlusions, but they are susceptible to orientation and position errors if not corrected over time.…”

Section: Motion Capturementioning

confidence: 99%

A Multimodal Gamified Platform for Real-Time User Feedback in Sports Performance

Monaghan

Honohan

Ahmadi

et al. 2016

Proceedings of the 24th ACM International Conference on Multimedia

View full text Add to dashboard Cite

In this paper we introduce a novel platform that utilises multi-modal low-cost motion capture technology for the delivery of real-time visual feedback for sports performance. This platform supports the expansion to multi-modal interfaces that utilise haptic and audio feedback, which scales e↵ectively with motor task complexity. We demonstrate an implementation of our platform within the field of sports performance. The platform includes low-cost motion capture through a fusion technique, combining a Microsoft Kinect V2 with two wrist inertial sensors, which make use of the accelerometer and gyroscope sensors, alongside a game-based Graphical User Interface (GUI) for instruction, visual feedback and gamified score tracking.

show abstract

Realtime human motion control with a small number of inertial sensors

Cited by 88 publications

References 27 publications

Accurate realtime full-body motion capture using a single depth camera

Accurate realtime full-body motion capture using a single depth camera

Filtered pose graph for efficient kinect pose reconstruction

A Multimodal Gamified Platform for Real-Time User Feedback in Sports Performance

Contact Info

Product

Resources

About