3DFR: A Swift 3D Feature Reductionist Framework for Scene Independent Change Detection

TL;DR

This paper introduces 3DFR, an efficient 3D feature reduction framework for scene-independent change detection that combines multiple feature streams and deep learning to improve robustness and accuracy.

Contribution

The paper presents a novel end-to-end 3D feature reductionist framework that integrates multiple feature streams and deep learning for scene-independent change detection.

Findings

Outperforms state-of-the-art methods on CDnet 2014 dataset

Demonstrates robustness and generalization across different scenes

Effectively learns high-level appearance and semantic features

Abstract

In this paper we propose an end-to-end swift 3D feature reductionist framework (3DFR) for scene independent change detection. The 3DFR framework consists of three feature streams: a swift 3D feature reductionist stream (AvFeat), a contemporary feature stream (ConFeat) and a temporal median feature map. These multilateral foreground/background features are further refined through an encoder-decoder network. As a result, the proposed framework not only detects temporal changes but also learns high-level appearance features. Thus, it incorporates the object semantics for effective change detection. Furthermore, the proposed framework is validated through a scene independent evaluation scheme in order to demonstrate the robustness and generalization capability of the network. The performance of the proposed method is evaluated on the benchmark CDnet 2014 dataset. The experimental results show that the proposed 3DFR network outperforms the state-of-the-art approaches.