Depth-encoded hough voting for joint object detection and shape recovery

Authors:
Min Sun;Gary Bradski;Bing-Xin Xu;Silvio Savarese
Affiliations:
Electrical and Computer Engineering, University of Michigan, Ann Arbor;Willow Garage, Menlo Park, CA;Electrical and Computer Engineering, University of Michigan, Ann Arbor;Electrical and Computer Engineering, University of Michigan, Ann Arbor
Venue:
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part V
Year:
2010

Citing 9
Cited 10

Recognizing solid objects by alignment with an image

International Journal of Computer Vision
A Method for Registration of 3-D Shapes

IEEE Transactions on Pattern Analysis and Machine Intelligence - Special issue on interpretation of 3-D scenes—part II
A Sparse Object Category Model for Efficient Learning and Exhaustive Recognition

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Histograms of Oriented Gradients for Human Detection

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Photo tourism: exploring photo collections in 3D

ACM SIGGRAPH 2006 Papers
Groups of Adjacent Contour Segments for Object Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
View Synthesis for Recognizing Unseen Poses of Object Classes

ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part III
Using Multi-view Recognition and Meta-data Annotation to Guide a Robot's Attention

International Journal of Robotics Research
Close-range scene segmentation and reconstruction of 3D point cloud maps for mobile manipulation in domestic environments

IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems

Toward coherent object detection and scene layout understanding

Image and Vision Computing
Object Detection using Geometrical Context Feedback

International Journal of Computer Vision
Viewpoint-aware object detection and continuous pose estimation

Image and Vision Computing
Latent hough transform for object detection

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III
3D2PM - 3d deformable part models

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VI
An introduction to random forests for multi-class object detection

Proceedings of the 15th international conference on Theoretical Foundations of Computer Vision: outdoor and large-scale real-world scene analysis
A proposed PCNN features quality optimization technique for pose-invariant 3D Arabic sign language recognition

Applied Soft Computing
Ensembles of strong learners for multi-cue classification

Pattern Recognition Letters
Model based training, detection and pose estimation of texture-less 3d objects in heavily cluttered scenes

ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part I
Object detection, shape recovery, and 3D modelling by depth-encoded hough voting

Computer Vision and Image Understanding

Quantified Score

Hi-index	0.00

Visualization

Abstract

Detecting objects, estimating their pose and recovering 3D shape information are critical problems in many vision and robotics applications. This paper addresses the above needs by proposing a new method called DEHV - Depth-Encoded Hough Voting detection scheme. Inspired by the Hough voting scheme introduced in [13], DEHV incorporates depth information into the process of learning distributions of image features (patches) representing an object category. DEHV takes advantage of the interplay between the scale of each object patch in the image and its distance (depth) from the corresponding physical patch attached to the 3D object. DEHV jointly detects objects, infers their categories, estimates their pose, and infers/decodes objects depth maps from either a single image (when no depth maps are available in testing) or a single image augmented with depth map (when this is available in testing). Extensive quantitative and qualitative experimental analysis on existing datasets [6,9,22] and a newly proposed 3D table-top object category dataset shows that our DEHV scheme obtains competitive detection and pose estimation results as well as convincing 3D shape reconstruction from just one single uncalibrated image. Finally, we demonstrate that our technique can be successfully employed as a key building block in two application scenarios (highly accurate 6 degrees of freedom (6 DOF) pose estimation and 3D object modeling).