Personnel tracking on construction sites using video cameras
Advanced Engineering Informatics
Silhouette representation and matching for 3D pose discrimination - A comparative study
Image and Vision Computing
Dual gait generative models for human motion estimation from a single camera
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics - Special issue on gait analysis
Marker-based human motion capture in multiview sequences
EURASIP Journal on Advances in Signal Processing
Multiple people tracking and pose estimation with occlusion estimation
Computer Vision and Image Understanding
Estimating human pose from occluded images
ACCV'09 Proceedings of the 9th Asian conference on Computer Vision - Volume Part I
Discriminative human full-body pose estimation from wearable inertial sensor data
3DPH'09 Proceedings of the 2009 international conference on Modelling the Physiological Human
Fast Human Pose Detection Using Randomized Hierarchical Cascades of Rejectors
International Journal of Computer Vision
Real-time human pose recognition in parts from single depth images
Communications of the ACM
Two-layer dual gait generative models for human motion estimation from a single camera
Image and Vision Computing
An adaptable system for RGB-D based human body detection and pose estimation
Journal of Visual Communication and Image Representation
Computer Vision and Image Understanding
| Hi-index | 0.02 |
We address the problem of estimating human body pose from a single image with cluttered background. We train multiple local linear regressors for estimating the 3D pose from a feature vector of gradient orientation histograms. Each linear regressor is capable of selecting relevant components of the feature vector depending on pose by training it on a pose cluster which is a subset of the training samples with similar pose. For discriminating the pose clusters, we use kernel Support Vector Machines (SVM) with pose-dependent feature selection. We achieve feature selection for kernel SVMs by estimating scale parameters of RBF kernel through minimization of the radius/margin bound, which is an upper bound of the expected generalization error, with efficient gradient descent. Human detection is also possible with these SVMs. Quantitative experiments show the effectiveness of pose-dependent feature selection to both human detection and pose estimation.