Flow-CDNet: A Novel Network for Detecting Both Slow and Fast Changes in Bitemporal Images

2025-07-03

AI Summary

To address the challenge of simultaneously detecting both slow (e.g., vegetation succession) and fast (e.g., building demolition) changes in bi-temporal remote sensing imagery, this paper proposes Flow-CDNet—a dual-branch collaborative network comprising an optical flow branch (featuring a pyramid architecture and ResNet backbone) to model continuous displacement dynamics, and a binary change detection branch for pixel-level change localization. Key contributions include: (i) a novel self-constructed Flow-Change dataset; (ii) a composite optimization objective integrating binary Tversky loss with L2-based optical flow reconstruction loss; and (iii) FEPE, a new evaluation metric sensitive to change intensity. Experiments demonstrate that Flow-CDNet significantly outperforms state-of-the-art methods on the proposed dataset. Ablation studies confirm the complementary feature representations between branches and their synergistic performance gain.

Technology Category

• Computer Vision: Learning & Optimization for CV
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Models for Web evolution

Abstract

Change detection typically involves identifying regions with changes between bitemporal images taken at the same location. Besides significant changes, slow changes in bitemporal images are also important in real-life scenarios. For instance, weak changes often serve as precursors to major hazards in scenarios like slopes, dams, and tailings ponds. Therefore, designing a change detection network that simultaneously detects slow and fast changes presents a novel challenge. In this paper, to address this challenge, we propose a change detection network named Flow-CDNet, consisting of two branches: optical flow branch and binary change detection branch. The first branch utilizes a pyramid structure to extract displacement changes at multiple scales. The second one combines a ResNet-based network with the optical flow branch's output to generate fast change outputs. Subsequently, to supervise and evaluate this new change detection framework, a self-built change detection dataset Flow-Change, a loss function combining binary tversky loss and L2 norm loss, along with a new evaluation metric called FEPE are designed. Quantitative experiments conducted on Flow-Change dataset demonstrated that our approach outperforms the existing methods. Furthermore, ablation experiments verified that the two branches can promote each other to enhance the detection performance.

Problem

• Detecting both slow and fast changes in bitemporal images
• Addressing weak changes as precursors to major hazards
• Integrating optical flow and binary change detection branches

Innovation

• Uses optical flow for multi-scale displacement detection
• Combines ResNet with optical flow for fast changes
• Introduces new dataset, loss function, and metric