Tampere University of Technology

TUTCRIS Research Portal

Use of Modified BM3D Filter and CNN Classifier for SAR Data to Improve Crop Classification Accuracy

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Details

Original languageEnglish
Title of host publication2019 IEEE 2nd Ukraine Conference on Electrical and Computer Engineering (UKRCON)
PublisherIEEE
Number of pages6
ISBN (Electronic)978-1-7281-3882-4
ISBN (Print)978-1-7281-3883-1
DOIs
Publication statusPublished - 24 Oct 2019
Publication typeA4 Article in a conference publication
EventUkraine Conference on Electrical and Computer Engineering -
Duration: 1 Jan 2000 → …

Conference

ConferenceUkraine Conference on Electrical and Computer Engineering
Abbreviated titleUKRCON
Period1/01/00 → …

Abstract

Monitoring of agricultural regions is an important task. Recent trends to solve it are based on applying multi-temporal remote sensing in order to obtain reliable crop classification maps. If a radar remote sensing is used, speckle presence in the original data reduces a classification accuracy. A negative impact of speckle can be reduced by image prefiltering procedure. Recent studies carried out for Sentinel-1 imagery have shown that more efficient pre-filtering usually results in better classification. Thus, here we propose a modification of block matching three-dimensional (BM3D) filter adapted to the properties of Sentinel-1 radar data. We demonstrate that its use leads to improved classification of crops in agricultural region of Ukraine compared to earlier methods which are based on other filters. Additionally, a convolutional neural network approach for crop mapping is investigated in this paper for decreasing noise impact and is compared with a traditional pixel-based multi-layer perceptron.

Keywords

  • agriculture, convolutional neural nets, crops, image classification, image filtering, radar imaging, speckle, synthetic aperture radar, vegetation mapping, crop mapping, BM3D filter, CNN classifier, SAR data, crop classification accuracy, multitemporal remote sensing, crop classification maps, radar remote sensing, speckle presence, image prefiltering procedure, Sentinel-1 imagery, Sentinel-1 radar data, agricultural regions monitoring, block matching three-dimensional filter, convolutional neural network, Agriculture, Speckle, Filtering, Optical filters, Discrete cosine transforms, Radar polarimetry, Three-dimensional displays, SAR, denoising, speckle removal, Sentinel-1, CNN

Publication forum classification

Field of science, Statistics Finland