Model-based 3D tracking of an articulated hand

By B. Stenger, Paulo R. S. Mendonça, Roberto Cipolla. Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001, 2001

343 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Human-Computer Interaction

View Paper: https://www.semanticscholar.org/paper/a29558766194bee91c498bccbec57acad63a3826

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Human-Computer Interaction

Citations in the corpus

Motion Capture of Hands in Action Using Discriminative Salient Points (2012, methodology): “Other approaches rely on stochastic optimization techniques such as Kalman filter [14] and particle filter [15].”
Shape context and chamfer matching in cluttered scenes (2003, methodology): “We useshapematchingto locatea handin an imageand estimateasetof shapeparametersof a3D handmodel [16].”
Analysis of Hand Segmentation in the Wild (2018, methodology): “, using global hand template [29, 24, 28], and (3) motion-based detection; using ego-motion of the camera and assuming hands (foreground) and the background have different motion [27, 9, 8].”
Efficient model-based 3D tracking of hand articulations using Kinect (2011, methodology): “Model-based approaches [5, 7, 15, 16, 18, 23, 24] generate model hypotheses and evaluate them on the available visual observations.”
A REVIEW OF VISION BASED HAND GESTURES RECOGNITION (2009, background): “Model based approaches attempt to infer the pose of the palm and the joint angles [18, 19].”
Estimating 3D hand pose from a cluttered image (2003, background): “Computer vision systems that estimate 3D hand pose typically do it in the context of tracking [8, 16, 19, 20, 24].”
Superpixel-Based Hand Gesture Recognition With Kinect Depth Camera (2015, methodology): “In comparison, model-based method [20] is better suited to reallife interaction, but a dark background is usually assumed so that the hand gesture can be segmented reliably.”
Real time hand pose estimation using depth sensors (2011, methodology): “[15] apply model-based tracking using an articulated hand model and estimate the pose with an unscented Kalman filter.”
Real-Time Hand Gesture Detection and Recognition Using Bag-of-Features and Support Vector Machine Techniques (2011, neutral): “Many approaches that used the 3-D hand model-based technique [26], [35]–[37] depend on the 3-D kinematic hand model with considerable DOF and calculate the hand parameters by comparison between the input frames and the 2-D appearance projected by the 3-D hand model.”
Capturing Hands in Action Using Discriminative Salient Points and Physics Simulation (2015, background): “Several filtering approaches have been presented (Bray et al, 2007; MacCormick and Isard, 2000; Stenger et al, 2001; Wu et al, 2001), while also belief-propagation proved to be suitable for articulated objects (Hamer et al, 2009, 2010; Sudderth et al, 2004).”
A Survey on Human Motion Analysis from Depth Data (2013, methodology): “Other methods rely on filtering techniques like Kalman filter [122] or particle filter [123].”
Sign Language Recognition (2011, methodology): “[94] presented a model-based hand tracking system that used quadrics to build the underlying 3D model from which contours (handling occlusion) were generated that could be compared to edges in the image.”
Pixel-Level Hand Detection in Ego-centric Videos (2013, positive): “Global appearance-based models detect hands using a global hand template, where dense or sparse hand templates are generated from a database 2D images [25] or 2D projections of a 3D hand model [18, 24, 15].”
Full DOF tracking of a hand interacting with an object by modeling occlusions and physical constraints (2011, methodology): “The assembly of appropriate homogeneous transformations of these two geometric primitives yields a hand model similar to that of [25].”
Accurate, Robust, and Flexible Real-time Hand Tracking (2015, neutral): “[24, 35]), again resulting in limited accuracy.”
Disentangling Latent Hands for Image Synthesis and Pose Estimation (2018, background): “Early methods could recognize only a restricted set of poses [1, 36] or used simplified hand representations instead of full 3D skeletons [26, 37].”