Cloud Detection through Wavelet Transforms in Machine Learning and Deep Learning

TL;DR

This paper explores the use of Wavelet Transforms as an effective feature extraction method for cloud detection in remote sensing images, aiming to improve efficiency and accuracy in machine learning and deep learning applications.

Contribution

It introduces Wavelet Transform theory and demonstrates its advantages over traditional transforms for cloud detection in remote sensing data.

Findings

WT effectively compresses signals and extracts features for classification.

WT-based features improve the performance of ML/DL classifiers.

The approach enhances real-time cloud detection efficiency.

Abstract

Cloud detection is a specialized application of image recognition and object detection using remotely sensed data. The task presents a number of challenges, including analyzing images obtained in visible, infrared and multi-spectral frequencies, usually without ground truth data for comparison. Moreover, machine learning and deep learning (MLDL) algorithms applied to this task are required to be computationally efficient, as they are typically deployed in low-power devices and called to operate in real-time. This paper explains Wavelet Transform (WT) theory, comparing it to more widely used image and signal processing transforms, and explores the use of WT as a powerful signal compressor and feature extractor for MLDL classifiers.