Maximum-Likelihood Registration of Range Images with Missing Data

Missing data are common in range images, due to geometric occlusions, limitations in the sensor field of view, poor reflectivity, depth discontinuities, and cast shadows. Using registration to align these data often fails, because points without valid correspondences can be incorrectly matched. This...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on pattern analysis and machine intelligence 2008-01, Vol.30 (1), p.120-130
Main Authors: Sharp, G.C., Lee, S.W., Wehe, D.K.
Format: Article
Language:English
Subjects:
Algorithms
Applied sciences
Artificial Intelligence
Cameras
Casting
Computer science
control theory
systems
Computer Simulation
Convergence
Data Interpretation, Statistical
Discontinuity
Exact sciences and technology
Field of view
Image Enhancement - methods
Image Interpretation, Computer-Assisted - methods
Image sensors
Imaging, Three-Dimensional - methods
Information Storage and Retrieval - methods
Iterative closest point algorithm
Layout
Likelihood Functions
Maximum Likelihood
Maximum likelihood estimation
Missing data
Models, Statistical
Object recognition
Occlusion
Pattern Recognition, Automated - methods
Pattern recognition. Digital image processing. Computational geometry
Pixel classification
Range data
Reflectivity
Registration
Reproducibility of Results
Sample Size
Sensitivity and Specificity
Sensors
Shadows
Solids
Subtraction Technique
Testing
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Missing data are common in range images, due to geometric occlusions, limitations in the sensor field of view, poor reflectivity, depth discontinuities, and cast shadows. Using registration to align these data often fails, because points without valid correspondences can be incorrectly matched. This paper presents a maximum-likelihood method for registration of scenes with unmatched or missing data. Using ray casting, correspondences are formed between valid and missing points in each view. These correspondences are used to classify points by their visibility properties, including occlusions, field of view, and shadow regions. The likelihood of each point match is then determined using statistical properties of the sensor, such as noise and outlier distributions. Experiments demonstrate high rates of convergence on complex scenes with varying degrees of overlap.
ISSN:0162-8828
1939-3539
DOI:10.1109/TPAMI.2007.1130