Land Use Classification Using Multi-neighborhood LBPs

TL;DR

This paper introduces a land use classification method using multi-neighborhood local binary patterns (LBPs) combined with a nearest neighbor classifier, achieving 77.76% accuracy on the UC Merced dataset.

Contribution

It presents a novel approach of using multi-neighborhood LBPs for land use classification, addressing intra-class variability and inter-class similarity.

Findings

Achieved 77.76% classification accuracy on UC Merced dataset.

Demonstrated effectiveness of multi-neighborhood LBPs over traditional methods.

Provided class-wise analysis and suggestions for future improvements.

Abstract

In this paper we propose the use of multiple local binary patterns(LBPs) to effectively classify land use images. We use the UC Merced 21 class land use image dataset. Task is challenging for classification as the dataset contains intra class variability and inter class similarities. Our proposed method of using multi-neighborhood LBPs combined with nearest neighbor classifier is able to achieve an accuracy of 77.76%. Further class wise analysis is conducted and suitable suggestion are made for further improvements to classification accuracy.