A real-time semantic segmentation algorithm for aerial imagery

A real-time semantic segmentation algorithm for aerial imagery

We propose a novel effective algorithm for real-time semantic segmentation of images that has the best accuracy in its class. Based on a comparative analysis of preliminary segmentation methods, methods for calculating attributes from image segments, as well as various algorithms of machine learning...

Full description

Bibliographic Details
Main Authors: Yury Blokhinov, Vadim Gorbachev, Yury Rakutin, Andrey Dmitrievich Nikitin
Format: Article
Language:English
Published: Samara National Research University 2018-02-01
Series:Компьютерная оптика
Subjects:
image analysis
pattern recognition
detection
classification
aerial images
DSM
superpixels
feature vector
semantic segmentation
machine learning
conditional random fields
Online Access:http://computeroptics.smr.ru/KO/PDF/KO42-1/420117.pdf
Description
Summary:We propose a novel effective algorithm for real-time semantic segmentation of images that has the best accuracy in its class. Based on a comparative analysis of preliminary segmentation methods, methods for calculating attributes from image segments, as well as various algorithms of machine learning, the most effective methods in terms of their accuracy and performance are identified. Based on the research results, a modular near real-time algorithm of semantic segmentation is constructed. Training and testing is performed on the ISPRS Vaihingen collection of aerial photos of the visible and IR ranges, to which a pixel map of the terrain heights is attached. An original method for obtaining a normalized nDSM for the original DSM is proposed.
ISSN:0134-2452
2412-6179

Similar Items