Proceedings ArticleDOI
Using stereo for object recognition
Scott Helmer,David G. Lowe +1 more
- pp 3121-3127
TLDR
This paper proposes a model that utilizes a chamfer-type silhouette classifier which is weighted by a prior on scale, which is robust to missing stereo depth information, and is validated on a set of challenging indoor scenes containing mugs and shoes.Abstract:
There has been significant progress recently in object recognition research, but many of the current approaches still fail for object classes with few distinctive features, and in settings with significant clutter and viewpoint variance. One such setting is visual search in mobile robotics, where tasks such as finding a mug or stapler require robust recognition. The focus of this paper is on integrating stereo vision with appearance based recognition to increase accuracy and efficiency. We propose a model that utilizes a chamfer-type silhouette classifier which is weighted by a prior on scale, which is robust to missing stereo depth information. Our approach is validated on a set of challenging indoor scenes containing mugs and shoes, where we find that priors remove a significant number of false positives, improving the average precision by 0.2 on each dataset. We additionally experiment with an additional classifer by Felzenszwalb et al.[1] to demonstrate the approach's robustness.read more
Citations
More filters
Proceedings ArticleDOI
A large-scale hierarchical multi-view RGB-D object dataset
TL;DR: A large-scale, hierarchical multi-view object dataset collected using anRGB-D camera is introduced and techniques for RGB-D based object recognition and detection are introduced, demonstrating that combining color and depth information substantially improves quality of results.
Proceedings ArticleDOI
Indoor scene segmentation using a structured light sensor
Nathan Silberman,Rob Fergus +1 more
TL;DR: This paper uses a CRF-based model to evaluate a range of different representations for depth information and proposes a novel prior on 3D location, revealing that the combination of depth and intensity images gives dramatic performance gains over intensity images alone.
Proceedings ArticleDOI
SGM-Nets: Semi-Global Matching with Neural Networks
Akihito Seki,Marc Pollefeys +1 more
TL;DR: A novel SGM parameterization, which deploys different penalties depending on either positive or negative disparity changes in order to represent the object structures more discriminatively, is proposed.
Proceedings ArticleDOI
Detection-based object labeling in 3D scenes
TL;DR: This work utilizes sliding window detectors trained from object views to assign class probabilities to pixels in every RGB-D frame, and performs efficient inference on a Markov Random Field over the voxels, combining cues from view-based detection and 3D shape, to label the scene.
References
More filters
Journal ArticleDOI
Distinctive Image Features from Scale-Invariant Keypoints
TL;DR: This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.
Journal ArticleDOI
The Pascal Visual Object Classes (VOC) Challenge
TL;DR: The state-of-the-art in evaluated methods for both classification and detection are reviewed, whether the methods are statistically different, what they are learning from the images, and what the methods find easy or confuse.
Book
Multiple view geometry in computer vision
Richard Hartley,Andrew Zisserman +1 more
TL;DR: In this article, the authors provide comprehensive background material and explain how to apply the methods and implement the algorithms directly in a unified framework, including geometric principles and how to represent objects algebraically so they can be computed and applied.
Distinctive Image Features from Scale-Invariant Keypoints
TL;DR: The Scale-Invariant Feature Transform (or SIFT) algorithm is a highly robust method to extract and consequently match distinctive invariant features from images that can then be used to reliably match objects in diering images.
Multiple View Geometry in Computer Vision.
TL;DR: This book is referred to read because it is an inspiring book to give you more chance to get experiences and also thoughts and it will show the best book collections and completed collections.
Related Papers (5)
Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography
Using spin images for efficient object recognition in cluttered 3D scenes
Andrew E. Johnson,Martial Hebert +1 more