Filters








11,470 Hits in 4.6 sec

Metric Regression Forests for Human Pose Estimation

Gerard Pons-Moll, Jonathan Taylor, Jamie Shotton, Aaron Hertzmann, Andrew Fitzgibbon
2013 Procedings of the British Machine Vision Conference 2013  
We present a new method for inferring dense data to model correspondences, focusing on the application of human pose estimation from depth images.  ...  Recent work proposed the use of regression forests to quickly predict correspondences between depth pixels and points on a 3D human mesh model.  ...  PONS-MOLL ET AL.: METRIC REGRESSION FORESTS FOR HUMAN POSE ESTIMATION  ... 
doi:10.5244/c.27.4 dblp:conf/bmvc/Pons-MollTSHF13 fatcat:pomrycz6tzex5m4zuwolyykrku

Metric Regression Forests for Correspondence Estimation

Gerard Pons-Moll, Jonathan Taylor, Jamie Shotton, Aaron Hertzmann, Andrew Fitzgibbon
2015 International Journal of Computer Vision  
We present a new method for inferring dense 1 data to model correspondences, focusing on the application 2 of human pose estimation from depth images.  ...  Recent work 3 proposed the use of regression forests to quickly predict cor-4 respondences between depth pixels and points on a 3D human 5 mesh model.  ...  For human pose estimation we parametrize a model using 606 a skeleton.  ... 
doi:10.1007/s11263-015-0818-9 fatcat:yj5djeipfvdydiz3mo4m45yclq

Latent Regression Forest: Structured Estimation of 3D Articulated Hand Posture

Danhang Tang, Hyung Jin Chang, Alykhan Tejani, Tae-Kyun Kim
2014 2014 IEEE Conference on Computer Vision and Pattern Recognition  
In this paper we present the Latent Regression Forest (LRF), a novel framework for real-time, 3D hand pose estimation from a single depth image.  ...  (ii) A new forest-based, discriminative framework for structured search in images, as well as an error regression step to avoid error accumulation.  ...  Many works for human body pose estimation use large synthetic datasets in training and use either pixel-wise classification [15] , or joint regression techniques [5, 18, 13, 16] for pose estimation.  ... 
doi:10.1109/cvpr.2014.490 dblp:conf/cvpr/TangCTK14 fatcat:hvpzrgh23baf7fq3gfdyxkx4lu

Hand Pose Regression via a Classification-Guided Approach [chapter]

Hongwei Yang, Juyong Zhang
2017 Lecture Notes in Computer Science  
Hand pose estimation from single depth image has achieved great progress in recent years, however, up-to-data methods are still not satisfying the application requirements like in human-computer interaction  ...  Then, an effective and efficient multiway cascaded random forest regressor is used to estimate the hand joints' 3D positions.  ...  We thank Zishun Liu for his helpful suggestions on this paper. This work was supported by the National Key R&D Program of China  ... 
doi:10.1007/978-3-319-54187-7_30 fatcat:4oaxuvsor5f7jackjqxf3kr4ra

Easy Minimax Estimation with Random Forests for Human Pose Estimation [chapter]

P. Daphne Tsatsoulis, David Forsyth
2015 Lecture Notes in Computer Science  
The output of this regression forest is then combined in a novel way. Instead of averaging the output of each tree in the forest we use minimax to calculate optimal weights for the trees.  ...  Unlike the state-of-the-art, our method does not search for individual body parts or poselets. Instead, a regression forest is used to predict a body configuration in body-space.  ...  Introduction In this paper, we address the problem of human pose estimation from a single RGB image.  ... 
doi:10.1007/978-3-319-16178-5_47 fatcat:olsg2iajyjd25l26f2lme3mo4i

Multi-Finger 3D Landmark Detection using Bi-Directional Hierarchical Regression

Jaesung Choi, Minkyu Lee, Sangyoun Lee
2016 Journal of International Society for Simulation Surgery  
PurposeZZIn this paper we proposed bi-directional hierarchical regression for accurate human finger landmark detection with only using depth information.  ...  After initialization, 16 landmarks were estimated using cascaded regression methods. To improve accuracy and stability, we proposed bi-directional hierarchical structure.  ...  In this paper, the regression based approach is used for estimating 3D multi-finger landmarks. Cascaded regression approaches (3, 4) already used for hand pose estimation.  ... 
doi:10.18204/jissis.2016.3.1.009 fatcat:a4hyxxpegfa2bpzxdo7bglpue4

The Vitruvian manifold: Inferring dense correspondences for one-shot human pose estimation

J. Taylor, J. Shotton, T. Sharp, A. Fitzgibbon
2012 2012 IEEE Conference on Computer Vision and Pattern Recognition  
For complex models such as humans, previous work has required a good initialization, or an alternating minimization between correspondence and pose.  ...  In this paper we investigate one-shot pose estimation: can we directly infer correspondences using a regression function trained to be invariant to body size and shape, and then optimize the model pose  ...  The authors would like to acknowledge Mat Cook, Ross Girshick, and Christian Plagemann for their help, and the anonymous reviewers for their constructive feedback.  ... 
doi:10.1109/cvpr.2012.6247664 dblp:conf/cvpr/TaylorSSF12 fatcat:grxnbircpbf2bnaey7awls7tdq

Efficient regression of general-activity human poses from depth images

Ross Girshick, Jamie Shotton, Pushmeet Kohli, Antonio Criminisi, Andrew Fitzgibbon
2011 2011 International Conference on Computer Vision  
We present a new approach to general-activity human pose estimation from depth images, building on Hough forests.  ...  Experimental results demonstrate that our method produces state of the art results on several data sets including the challenging MSRC-5000 pose estimation test set, at a speed of about 200 frames per  ...  We thank Toby Sharp, Mat Cook, John Winn, and Duncan Robertson for their help and interesting discussions.  ... 
doi:10.1109/iccv.2011.6126270 dblp:conf/iccv/GirshickSKCF11 fatcat:yuh7acrkfvh5loltw5tnxt7fqu

Interactive Hand Pose Estimation: Boosting accuracy in localizing extended finger joints

Cairong Zhang, Guijin Wang, Hengkai Guo, Xinghao Chen, Fei Qiao, Huazhong Yang
2018 IS&T International Symposium on Electronic Imaging Science and Technology  
Accurate 3D hand pose estimation plays an important role in Human Machine Interaction (HMI).  ...  It first detects which fingers are stretching out, then neighbor pixels of certain joint vote for its new location based on random forests.  ...  Introduction Hand pose estimation plays an important role in Human Machine Interaction (HMI), such as virtual reality (VR), augmented reality (AR) and remote control.  ... 
doi:10.2352/issn.2470-1173.2018.2.vipc-251 fatcat:fgavbuyweffxhjebmalteupb7q

Multi-task Forest for Human Pose Estimation in Depth Images

Joe Lallemand, Olivier Pauly, Loren Schwarz, David Tan, Slobodan Ilic
2013 2013 International Conference on 3D Vision  
Results on this dataset show that our multi-task forest provides improved human pose estimation compared to a pure regression forest approach.  ...  In this paper, we address the problem of human body pose estimation from depth data.  ...  Inspired by the human body pose estimation approach based on regression forests [10] and the manifold learning approach of [21] , we propose to jointly learn generic human body poses and human activity  ... 
doi:10.1109/3dv.2013.43 dblp:conf/3dim/LallemandPSTI13 fatcat:33xuzkdvafebfmp7wz4phqduom

Efficient Human Pose Estimation from Single Depth Images [chapter]

J. Shotton, R. Girshick, A. Fitzgibbon, T. Sharp, M. Cook, M. Finocchio, R. Moore, P. Kohli, A. Criminisi, A. Kipman, A. Blake
2013 Decision Forests for Computer Vision and Medical Image Analysis  
We describe two new approaches to human pose estimation. Both can quickly and accurately predict the 3D positions of body joints from a single depth image, without using any temporal information.  ...  The second approach instead directly regresses the positions of body joints.  ...  Finally thanks to Varun Ganapathi and Christian Plagemann for providing their test data.  ... 
doi:10.1007/978-1-4471-4929-3_13 fatcat:3xpceijgfbb2jevep2memfn6qq

Efficient Human Pose Estimation from Single Depth Images

Jamie Shotton, Ross Girshick, Andrew Fitzgibbon, Toby Sharp, Mat Cook, Mark Finocchio, Richard Moore, Pushmeet Kohli, Antonio Criminisi, Alex Kipman, Andrew Blake
2013 IEEE Transactions on Pattern Analysis and Machine Intelligence  
We describe two new approaches to human pose estimation. Both can quickly and accurately predict the 3D positions of body joints from a single depth image, without using any temporal information.  ...  The second approach instead directly regresses the positions of body joints.  ...  Finally thanks to Varun Ganapathi and Christian Plagemann for providing their test data.  ... 
doi:10.1109/tpami.2012.241 pmid:24136424 fatcat:yin6x7zrmfavnhacufa2pf3heu

Cascaded hand pose regression

Xiao Sun, Yichen Wei, Shuang Liang, Xiaoou Tang, Jian Sun
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
We extends the previous 2D cascaded object pose regression work [9] in two aspects so that it works better for 3D articulated objects.  ...  Comprehensive experiments verify the state-of-the-art accuracy and efficiency of the proposed approach on the challenging 3D hand pose estimation problem, on a public dataset and our new dataset.  ...  Introduction The problem of pose estimation of 3D articulated objects such as human body and hand has been studied for decades.  ... 
doi:10.1109/cvpr.2015.7298683 dblp:conf/cvpr/0001WLT015 fatcat:xjdzlihfh5ckfpfmqjxe6vjtgu

Deep Head Pose: Gaze-Direction Estimation in Multimodal Video

Sankha S. Mukherjee, Neil Martin Robertson
2015 IEEE transactions on multimedia  
In this paper we present a convolutional neural network (CNN)-based model for human head pose estimation in low-resolution multi-modal RGB-D data.  ...  Next we combine the two models (classification and regression) to estimate approximate regression confidence.  ...  They would also like to thank Microsoft for providing access to the Kinect developer program.  ... 
doi:10.1109/tmm.2015.2482819 fatcat:qrz7fhtnynbjbfwt6eqlr4enw4

Scene Coordinate Regression Forests for Camera Relocalization in RGB-D Images

Jamie Shotton, Ben Glocker, Christopher Zach, Shahram Izadi, Antonio Criminisi, Andrew Fitzgibbon
2013 2013 IEEE Conference on Computer Vision and Pattern Recognition  
Our approach employs a regression forest that is capable of inferring an estimate of each pixel's correspondence to 3D points in the scene's world coordinate frame.  ...  This starts with an initial set of hypothesized camera poses, constructed by applying the forest at a small fraction of image pixels.  ...  In each test example, we show the RGB and depth images, and a 3D visualization of the underlying scene with camera frusta overlaid: the ground truth pose (red), our inferred pose using a DA-RGB SCoRe Forest  ... 
doi:10.1109/cvpr.2013.377 dblp:conf/cvpr/ShottonGZICF13 fatcat:qqdiqtdvmjechjmudlpiqlgshe
« Previous Showing results 1 — 15 out of 11,470 results