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

TL;DR

Flow-CDNet is a novel neural network architecture designed to detect both slow and fast changes in bitemporal images, leveraging optical flow and binary change detection branches, and validated on a new dataset with superior performance.

Contribution

The paper introduces Flow-CDNet, a dual-branch network that simultaneously detects slow and fast changes, along with a new dataset, loss function, and evaluation metric for change detection.

Findings

Outperforms existing change detection methods on the Flow-Change dataset.

Ablation studies show the two branches enhance each other's performance.

The proposed framework effectively detects both slow and fast changes in bitemporal images.

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.