# Change Detection between Multimodal Remote Sensing Data Using Siamese CNN

arXiv: https://arxiv.org/abs/1807.09562 · HTML: https://mlsanity.com/paper/1807.09562/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jul 2018.

## Built on by (most cited first, 9 of 9)

- [The QXS-SAROPT Dataset for Deep Learning in SAR-Optical Data Fusion](https://mlsanity.com/paper/2103.08259/) (2021)
- [Mind the Modality Gap: Towards a Remote Sensing Vision-Language Model via Cross-modal Alignment](https://mlsanity.com/paper/2402.09816/) (2024)
- [Transformer-based Multimodal Change Detection with Multitask Consistency Constraints](https://mlsanity.com/paper/2310.09276/) (2023)
- [Change detection needs change information: improving deep 3D point cloud change detection](https://mlsanity.com/paper/2304.12639/) (2023)
- [DC3DCD: unsupervised learning for multiclass 3D point cloud change detection](https://mlsanity.com/paper/2305.05421/) (2023)
- [Image change detection with only a few samples](https://mlsanity.com/paper/2311.03762/) (2023)
- [Trusting small training dataset for supervised change detection](https://mlsanity.com/paper/2104.05443/) (2021)
- [Implicit neural representation for change detection](https://mlsanity.com/paper/2307.15428/) (2023)
- [Deep learning-based interactive segmentation in remote sensing](https://mlsanity.com/paper/2308.13174/) (2023)

## Abstract (arXiv)

Detecting topographic changes in the urban environment has always been an important task for urban planning and monitoring. In practice, remote sensing data are often available in different modalities and at different time epochs. Change detection between multimodal data can be very challenging since the data show different characteristics. Given 3D laser scanning point clouds and 2D imagery from different epochs, this paper presents a framework to detect building and tree changes. First, the 2D and 3D data are transformed to image patches, respectively. A Siamese CNN is then employed to detect candidate changes between the two epochs. Finally, the candidate patch-based changes are grouped and verified as individual object changes. Experiments on the urban data show that 86.4% of patch pairs can be correctly classified by the model.