Three-dimensional object recognition
ACM Computing Surveys (CSUR) - Annals of discrete mathematics, 24
Intelligence: the eye, the brain, and the computer
Intelligence: the eye, the brain, and the computer
Surfaces in range image understanding
Surfaces in range image understanding
Introduction to Solid Modeling
Introduction to Solid Modeling
Recognition and Shape Synthesis of 3-D Objects Based on Attributed Hypergraphs
IEEE Transactions on Pattern Analysis and Machine Intelligence
Describing and recognizing 3-D objects using surface properties
Describing and recognizing 3-D objects using surface properties
Computer graphics: principles and practice (2nd ed.)
Computer graphics: principles and practice (2nd ed.)
Report: 1988 NSF range image understanding workshop
Analysis and interpretation of range images
On Three-Dimensional Surface Reconstruction Methods
IEEE Transactions on Pattern Analysis and Machine Intelligence
Human and machine vision: computing perceptual organisation
Human and machine vision: computing perceptual organisation
Mathematics for computer graphics
Mathematics for computer graphics
Model-based object recognition in dense-range images—a review
ACM Computing Surveys (CSUR)
Geometric invariants and object recognition
International Journal of Computer Vision
Image analysis and computer vision: 1992
CVGIP: Image Understanding
A guided tour of computer vision
A guided tour of computer vision
A Mechanism of Automatic 3D Object Modeling
IEEE Transactions on Pattern Analysis and Machine Intelligence
Introduction to Robotics: Mechanics and Control
Introduction to Robotics: Mechanics and Control
Digital Image Processing: A Systems Approach
Digital Image Processing: A Systems Approach
Artificial Intelligence and the Design of Expert Systems
Artificial Intelligence and the Design of Expert Systems
View Variation of Point-Set and Line-Segment Features
IEEE Transactions on Pattern Analysis and Machine Intelligence
| Hi-index | 0.00 |
Object recognition is imperative in industry automation since it empowers robots with the perceptual capability of understanding the three-dimensional(3-D) environment by means of sensory devices. Considering object recognition as a mapping between object models and a partial description of an object, this paper introduces a three-phase filtering method that eliminates candidate models when their differences with the object show up. Throughout the process, a view-insensitive modeling method, namely localized surface parameters, is employed.Surface matching is carried out in the first phase to match modelswith the object by comparing their localized surface descriptions. Amodel is a candidate of the object only if every object surfacematches locally with at least one of the model surfaces. Since thetopological relationship between surfaces specifies the global shapeof the object and models, it is then checked in the next phase withlocal coordinate systems to make sure that a candidate model has theidentical structure as the object.Because the information of an object cannot be complete in a singleviewing direction, the first two conditions can only determine if acandidate has the same portion as the object. The selected model maystill be bigger than the object. To avoid the part-to-wholeconfusion, in the third phase, a back projection from candidatemodels is performed to ensure that no unmatched model features becomevisible when a model is virtually brought to the object‘sorientation.In case multiple models are selected as a result of the insufficientinformation, disambiguating features and their visible directionsare derived to verify the expected feature. In addition to the viewindependent object recognition under even ambiguous situations, thefiltering method has a low computational complexity upper bounded byO(m^2n^2) and lower bounded by O(mn),where m and n are the numbers of model and object features. The three-phase objectrecognition has been exercised with real and synthesized rangeimages. Experiment results are given in the paper.