• Corpus ID: 15341921

Voxelized Shape and Color Histograms for RGB-D

@inproceedings{Kanezaki2011VoxelizedSA,
  title={Voxelized Shape and Color Histograms for RGB-D},
  author={Asako Kanezaki and Zolt{\'a}n-Csaba M{\'a}rton and Dejan Pangercic and Tatsuya Harada and Yasuo Kuniyoshi and Michael Beetz},
  booktitle={IROS 2011},
  year={2011}
}
Real world environments typically include objects with different perceptual appearances. A household, for example, includes textured, textureless and even partially transparent objects. While perception methods exist that work well on one such class of objects at a time, the perception of various classes of objects in a scene is still a challenge. It is our view that the construction of a descriptor that takes both color and shape into account, thereby fostering high discriminating power, will… 

Figures and Tables from this paper

Object Categorization in Clutter Using Additive Features and Hashing of Part-Graph Descriptors

TLDR
A part-graph-based hashing method for classifying objects in clutter, using an additive feature descriptor, allowing easy addition of new training data without recreating the complete model and taking advantage of the additive nature of the feature to increase efficiency.

Textured/textureless object recognition and pose estimation using RGB-D image

TLDR
A novel global object descriptor, so-called Viewpoint oriented Color-Shape Histogram (VCSH), which combines 3D object’s color and shape features, which is efficiently used in a real-time textured/textureless object recognition and 6D pose estimation system and applied for object localization in a coherent semantic map.

Part-Based Geometric Categorization and Object Reconstruction in Cluttered Table-Top Scenes

TLDR
This work categorizes objects into five geometric shapes: sphere, box, flat, cylindrical, and disk/plate, as these shapes represent the majority of objects found on tables in typical households and reconstruct complete 3D models that include the invisible back-sides of objects as well, in order to facilitate manipulation by domestic service robots.

Contextual object category recognition for RGB-D scene labeling

Tracking-based interactive segmentation of textureless objects

This paper describes a textureless object segmentation approach for autonomous service robots acting in human living environments. The proposed system allows a robot to effectively segment

BRAND: A robust appearance and depth descriptor for RGB-D images

This work introduces a novel descriptor called Binary Robust Appearance and Normals Descriptor (BRAND), that efficiently combines appearance and geometric shape information from RGB-D images, and is

Appearance and Geometry Fusion for Enhanced Dense 3D Alignment

This work proposes a novel RGB-D feature descriptor called Binary Appearance and Shape Elements (BASE) that efficiently combines intensity and shape information to improve the discriminative power

Cumulative object categorization in clutter

In this paper we present an approach based on scene- or part-graphs for geometrically categorizing touching and occluded objects, using additive RGBD feature descriptors and hashing of graph

Object class and instance recognition on rgb-d data

TLDR
A novel approach for combining 3D depth and visual information for object class and object instance recognition is presented and the algorithm was further evaluated during the RoboCup world championship 2012 in Mexico-City and won the first place in the Technical Challenge of the @Home-league.

References

SHOWING 1-10 OF 23 REFERENCES

Hierarchical object geometric categorization and appearance classification for mobile manipulation

TLDR
This paper tackles the problem of recognizing everyday objects that are useful for a personal robotic assistant in fulfilling its tasks, using a hierarchical multi-modal 3D-2D processing and classification system.

Combining depth and color cues for scale- and viewpoint-invariant object segmentation and recognition using Random Forests

  • J. StücklerSven Behnke
  • Computer Science
    2010 IEEE/RSJ International Conference on Intelligent Robots and Systems
  • 2010
TLDR
This paper fuse information from color images with depth from a Time-of-Flight (ToF) camera to improve recognition performance under scale and viewpoint changes and incorporates local 3D shape features into the classifier.

High-speed 3D object recognition using additive features in a linear subspace

TLDR
This paper proposes a method of high-speed 3D object recognition using linear subspace method and 3D features that consider the co-occurrence of shape and colors of an object's surface and shows that this method is appropriate for 3Dobject recognition.

Representing shape with a spatial pyramid kernel

TLDR
This work introduces a descriptor that represents local image shape and its spatial layout, together with a spatial pyramid kernel that is designed so that the shape correspondence between two images can be measured by the distance between their descriptors using the kernel.

Fast object detection for robots in a cluttered indoor environment using integral 3D feature table

TLDR
This work has developed a robot system that collects 3D-scene data in an indoor environment during automatic routine crawling, and also detects objects quickly through a global search of the collected 3D -scene data.

Surface completion for shape and appearance

TLDR
The experiments show that the unified framework, founded upon the techniques of deformable models, local parameterization, and PDE modeling, can provide a robust and elegant solution for content completion of defective, complex point surfaces.

General 3D modelling of novel objects from a single view

TLDR
A method for building models for grasping from a single 3D snapshot of a scene composed of objects of daily use in human living environments using fast shape estimation, probabilistic model fitting and verification methods, and a triangular mesh of the parts that have no other representation to model previously unseen objects of arbitrary shape.

Shape-Colour Histograms for matching 3D video sequences

  • P. HuangA. Hilton
  • Computer Science
    2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops
  • 2009
TLDR
A novel descriptor, Shape-Colour Histograms, is introduced to match objects with similar shape and appearance to match 3D video sequences for animation production and demonstrates the accurate matching of surface shape, appearance and motion at transition points.

How to Combine Color and Shape Information for 3D Object Recognition: Kernels do the Trick

TLDR
A kernel method is presented that allows to combine color and shape information for appearance-based object recognition using results of statistical mechanics of spin glasses combined with Markov random fields via kernel functions.

Fast 3D recognition and pose using the Viewpoint Feature Histogram

TLDR
The Viewpoint Feature Histogram (VFH) is presented, a descriptor for 3D point cloud data that encodes geometry and viewpoint that is robust to large surface noise and missing depth information in order to work reliably on stereo data.