Shape quantization and recognition with randomized trees
Neural Computation
Twist Based Acquisition and Tracking of Animal and Human Kinematics
International Journal of Computer Vision
Lucas-Kanade 20 Years On: A Unifying Framework
International Journal of Computer Vision
Performance animation from low-dimensional control signals
ACM SIGGRAPH 2005 Papers
Keypoint Recognition Using Randomized Trees
IEEE Transactions on Pattern Analysis and Machine Intelligence
A survey of advances in vision-based human motion capture and analysis
Computer Vision and Image Understanding - Special issue on modeling people: Vision-based understanding of a person's shape, appearance, movement, and behaviour
Action capture with accelerometers
Proceedings of the 2008 ACM SIGGRAPH/Eurographics Symposium on Computer Animation
Single view motion tracking by depth and silhouette information
SCIA'07 Proceedings of the 15th Scandinavian conference on Image analysis
Realtime human motion control with a small number of inertial sensors
I3D '11 Symposium on Interactive 3D Graphics and Games
Motion reconstruction using sparse accelerometer data
ACM Transactions on Graphics (TOG)
Real-time human pose recognition in parts from single depth images
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Accurate 3D pose estimation from a single depth image
ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
A data-driven approach for real-time full body pose reconstruction from a depth camera
ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
Efficient regression of general-activity human poses from depth images
ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
Creature features: online motion puppetry for non-human characters
Proceedings of the 12th ACM SIGGRAPH/Eurographics Symposium on Computer Animation
Dynamic 2D/3D registration for the Kinect
ACM SIGGRAPH 2013 Courses
ACM Transactions on Graphics (TOG)
On-set performance capture of multiple actors with a stereo camera
ACM Transactions on Graphics (TOG)
Hi-index | 0.00 |
We present a fast, automatic method for accurately capturing full-body 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-of-the-art accuracy in our comparison against alternative systems such as Kinect [2012].