Search For:

Displaying 1-13 out of 13 total
Efficient Human Pose Estimation from Single Depth Images
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Jamie Shotton,Ross Girshick,Andrew Fitzgibbon,Toby Sharp,Mat Cook,Mark Finocchio,Richard Moore,Pushmeet Kohli,Antonio Criminisi,Alex Kipman,Andrew Blake
Issue Date:December 2013
pp. 2821-2840
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 key to both approaches is the use of a large, realistic, ...
Image Segmentation Using Hardware Forest Classifiers
Found in: 2013 IEEE 21st Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)
By Neil Pittman,Alessandro Forin,Antonio Criminisi,Jamie Shotton,Atabak Mahram
Issue Date:April 2013
pp. 73-80
Image segmentation is the process of partitioning an image into segments or subsets of pixels for purposes of further analysis, such as separating the interesting objects in the foreground from the un-interesting objects in the background. In many image pr...
Efficient regression of general-activity human poses from depth images
Found in: Computer Vision, IEEE International Conference on
By Ross Girshick,Jamie Shotton,Pushmeet Kohli,Antonio Criminisi,Andrew Fitzgibbon
Issue Date:November 2011
pp. 415-422
We present a new approach to general-activity human pose estimation from depth images, building on Hough forests. We extend existing techniques in several ways: real time prediction of multiple 3D joints, explicit learning of voting weights, vote compressi...
KinectFusion: Real-time dense surface mapping and tracking
Found in: 2011 IEEE International Symposium on Mixed and Augmented Reality
By Richard A. Newcombe,Shahram Izadi,Otmar Hilliges,David Molyneaux,David Kim,Andrew J. Davison,Pushmeet Kohi,Jamie Shotton,Steve Hodges,Andrew Fitzgibbon
Issue Date:October 2011
pp. 127-136
We present a system for accurate real-time mapping of complex and arbitrary indoor scenes in variable lighting conditions, using only a moving low-cost depth camera and commodity graphics hardware. We fuse all of the depth data streamed from a Kinect senso...
Facial Deblur Inference Using Subspace Analysis for Recognition of Blurred Faces
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Masashi Nishiyama, Abdenour Hadid, Hidenori Takeshima, Jamie Shotton, Tatsuo Kozakaya, Osamu Yamaguchi
Issue Date:April 2011
pp. 838-845
This paper proposes a novel method for recognizing faces degraded by blur using deblurring of facial images. The main issue is how to infer a Point Spread Function (PSF) representing the process of blur on faces. Inferring a PSF from a single facial image ...
Semantic texton forests for image categorization and segmentation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Jamie Shotton, Matthew Johnson, Roberto Cipolla
Issue Date:June 2008
pp. 1-8
We propose semantic texton forests, efficient and powerful new low-level features. These are ensembles of decision trees that act directly on image pixels, and therefore do not need the expensive computation of filter-bank responses or local descriptors. T...
Multiscale Categorical Object Recognition Using Contour Fragments
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Jamie Shotton, Andrew Blake, Roberto Cipolla
Issue Date:July 2008
pp. 1270-1281
Psychophysical studies [9], [17] show that we can recognize objects using fragments of outline contour alone. This paper proposes a new automatic visual recognition system based only on local contour features, capable of localizing objects in space and sca...
The Layout Consistent Random Field for Recognizing and Segmenting Partially Occluded Objects
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By John Winn, Jamie Shotton
Issue Date:June 2006
pp. 37-44
This paper addresses the problem of detecting and segmenting partially occluded objects of a known category. We first define a part labelling which densely covers the object. Our Layout Consistent Random Field (LayoutCRF) model then imposes asymmetric loca...
Contour-Based Learning for Object Detection
Found in: Computer Vision, IEEE International Conference on
By Jamie Shotton, Andrew Blake, Roberto Cipolla
Issue Date:October 2005
pp. 503-510
We present a novel categorical object detection scheme that uses only local contour-based features. A two-stage, partially supervised learning architecture is proposed: a rudimentary detector is learned from a very small set of segmented images and applied...
Real-Time RGB-D Camera Relocalization via Randomized Ferns for Keyframe Encoding
Found in: IEEE Transactions on Visualization and Computer Graphics
By Ben Glocker,Jamie Shotton,Antonio Criminisi,Shahram Izadi
Issue Date:February 2015
pp. 1
Recovery from tracking failure is essential in any simultaneous localization and tracking system. In this context, we explore an efficient keyframe-based relocalization method based on frame encoding using randomized ferns. The method enables automatic dis...
Scene Coordinate Regression Forests for Camera Relocalization in RGB-D Images
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Jamie Shotton,Ben Glocker,Christopher Zach,Shahram Izadi,Antonio Criminisi,Andrew Fitzgibbon
Issue Date:June 2013
pp. 2930-2937
We address the problem of inferring the pose of an RGB-D camera relative to a known 3D scene, given only a single acquired image. Our approach employs a regression forest that is capable of inferring an estimate of each pixel's correspondence to 3D points ...
GeoF: Geodesic Forests for Learning Coupled Predictors
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Peter Kontschieder,Pushmeet Kohli,Jamie Shotton,Antonio Criminisi
Issue Date:June 2013
pp. 65-72
Conventional decision forest based methods for image labelling tasks like object segmentation make predictions for each variable (pixel) independently [3, 5, 8]. This prevents them from enforcing dependencies between variables and translates into locally i...
Real-time human pose recognition in parts from single depth images
Found in: Communications of the ACM
By Alex Kipman, Andrew Blake, Andrew Fitzgibbon, Jamie Shotton, Mark Finocchio, Mat Cook, Richard Moore, Toby Sharp
Issue Date:January 2013
pp. 116-124
We propose a new method to quickly and accurately predict human pose---the 3D positions of body joints---from a single depth image, without depending on information from preceding frames. Our approach is strongly rooted in current object recognition strate...