Parallel Classification of Large Aerospace Images by the Multi-alternative Discrete Accumulation Method

被引：0

作者：

Vorobiev, Vladimir I. ^{[1
]}

Evnevich, Elena L. ^{[1
]}

Levonevskiy, Dmitriy K. ^{[1
]}

机构：

[1] Russian Acad Sci, Inst Informat & Automat, St Petersburg, Russia

来源：

ADVANCES IN NEURAL NETWORKS - ISNN 2016 | 2016年 / 9719卷

关键词：

Parallel computing; Aerospace images; Satellite imagery; Neural networks; Image processing; Image classification; Geographic information systems; GIS;

D O I：

10.1007/978-3-319-40663-3_5

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The paper deals with parallel large aerospace images processing. We considered a simple multi-alternative discrete accumulation method for reliable distinction of satellite imagery and implemented a parallel classification system to increase the algorithm efficiency. The process of development of the distinction algorithm and system architecture was described. The system prototype was successfully tested. The experiments allowed to draw conclusion about the system performance and to estimate the effect of using the parallel architecture. The considered approach could be used in complex neural networks processing.

引用

页码：40 / 48

页数：9

共 12 条

[1]

[Anonymous], COMPUT MODEL

[2]

[Anonymous], 4 RUSS OP C MOD PROB

[3]

[Anonymous], MODERN FEATURES MESS

[4]

[Anonymous], MOD PROBL EARTH STUD

[5]

[Anonymous], EARTH STUDYING SPACE

[6]

[Anonymous], ELEMENTS REUSABLE OB

[7]

[Anonymous], STUDY STUDYING EARTH

[8]

Jensen J, 2005, INTRO DIGITAL IMAGE, V3rd

[9] Aerial Scene Classification with Convolutional Neural Networks [J].

Jia, Sibo ;

Liu, Huaping ;

Sun, Fuchun .

ADVANCES IN NEURAL NETWORKS - ISNN 2015, 2015, 9377 :258-265

[10] Principle of representational minimum description length in image analysis and pattern recognition [J].

Potapov, A.S. .

Pattern Recognition and Image Analysis, 2012, 22 (01) :82-91

← 1 2 →