Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

Regression Tree CNN for Estimation of Ground Sampling Distance Based on Floating-Point Representation

Authors
Lee, Jae-HunSull, Sanghoon
Issue Date
10월-2019
Publisher
MDPI
Keywords
floating-point representation; binomial tree; tree CNN; regression tree; GSD estimation; aerial image; satellite image; spatial resolution
Citation
REMOTE SENSING, v.11, no.19
Indexed
SCIE
SCOPUS
Journal Title
REMOTE SENSING
Volume
11
Number
19
URI
https://scholar.korea.ac.kr/handle/2021.sw.korea/62608
DOI
10.3390/rs11192276
ISSN
2072-4292
Abstract
The estimation of ground sampling distance (GSD) from a remote sensing image enables measurement of the size of an object as well as more accurate segmentation in the image. In this paper, we propose a regression tree convolutional neural network (CNN) for estimating the value of GSD from an input image. The proposed regression tree CNN consists of a feature extraction CNN and a binomial tree layer. The proposed network first extracts features from an input image. Based on the extracted features, it predicts the GSD value that is represented by the floating-point number with the exponent and its mantissa. They are computed by coarse scale classification and finer scale regression, respectively, resulting in improved results. Experimental results with a Google Earth aerial image dataset and a mixed dataset consisting of eight remote sensing image public datasets with different GSDs show that the proposed network reduces the GSD prediction error rate by 25% compared to a baseline network that directly estimates the GSD.
Files in This Item
There are no files associated with this item.
Appears in
Collections
College of Engineering > School of Electrical Engineering > 1. Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Researcher Sull, Sang hoon photo

Sull, Sang hoon
공과대학 (전기전자공학부)
Read more

Altmetrics

Total Views & Downloads

BROWSE