An Incremental Boolean Tensor Factorization approach to model Change Patterns of Objects in Images

TL;DR

This paper introduces an incremental Boolean tensor factorization framework for modeling change patterns in objects within images, enhancing change detection in remote sensing through a knowledge-based, tensor-based approach.

Contribution

It proposes a novel incremental Boolean tensor factorization method for better modeling of change patterns in spatiotemporal image data, improving upon traditional methods.

Findings

The proposed method effectively models change patterns in various datasets.

It outperforms traditional Boolean tensor factorization in accuracy.

The framework visualizes dependency factors in change detection.

Abstract

Change detection process has recently progressed from a post-classification method to an expert knowledge interpretation process of the time-series data. The technique finds applications mainly in remote sensing images and can be utilized to analyze urbanization and monitor forest regions. In this paper, a framework to perform a knowledge based interpretation of the changes/no changes observed in a spatiotemporal domain using tensor based approaches is presented. An incremental approach to Boolean Tensor Factorization method is proposed in this work, which is adopted to model the change patterns of objects/classes as well as their associated features. The framework is evaluated under different datasets to visualize the performance for the dependency factors. The algorithm is also validated in comparison with the tradition Boolean Tensor Factorization method and the results are substantial.