A Hybrid Shared-Memory Parallel Max-Tree Algorithm for Extreme Dynamic-Range Images

Max-trees, or component trees, are graph structures that represent the connected components of an image in a hierarchical way. Nowadays, many application fields rely on images with high-dynamic range or floating point values. Efficient sequential algorithms exist to build trees and compute attribute...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on pattern analysis and machine intelligence Vol. 40; no. 3; pp. 513 - 526
Main Authors: Moschini, Ugo, Meijster, Arnold, Wilkinson, Michael H. F.
Format: Journal Article
Language:English
Published: United States IEEE 01.03.2018
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Algorithm design and analysis
Algorithms
Buildings
Computer simulation
Connected filters
Data structures
Dynamic range
Floating point arithmetic
Floating structures
Flooding
Heuristic algorithms
hierarchical image representation
Integers
Merging
Parallel algorithms
ISSN:0162-8828, 1939-3539, 2160-9292, 1939-3539
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Max-trees, or component trees, are graph structures that represent the connected components of an image in a hierarchical way. Nowadays, many application fields rely on images with high-dynamic range or floating point values. Efficient sequential algorithms exist to build trees and compute attributes for images of any bit depth. However, we show that the current parallel algorithms perform poorly already with integers at bit depths higher than 16 bits per pixel. We propose a parallel method combining the two worlds of flooding and merging max-tree algorithms. First, a pilot max-tree of a quantized version of the image is built in parallel using a flooding method. Later, this structure is used in a parallel leaf-to-root approach to compute efficiently the final max-tree and to drive the merging of the sub-trees computed by the threads. We present an analysis of the performance both on simulated and actual 2D images and 3D volumes. Execution times are about 20× better than the fastest sequential algorithm and speed-up goes up to 30-40 on 64 threads.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0162-8828
1939-3539
2160-9292
1939-3539
DOI:10.1109/TPAMI.2017.2689765