Dataset for Remote Sensing Image Change Captioning and Change Detection

News:

🔥Remote Sensing Spatio-Temporal Vision-Language Models: A Comprehensive Survey: [Paper] [Github]

Paper Source

• LEVIR-CC: A Large Dataset for Remote Sensing Image Change Captioning. [Paper] [code]
• LEVIR-MCI: A Large Dataset for exploring multi-task learning for change detection and change captioning. [Paper] [code]

LEVIR-CC Dataset

Download Source:

• [🤗 Huggingface]
• [Google Drive]
• [Baidu Pan (code:nq9y)]

The path list in the downloaded folder is as follows:

path to LEVIR_CC_dataset:
                ├─LevirCCcaptions.json
                ├─images
                  ├─train
                  │  ├─A
                  │  ├─B
                  ├─val
                  │  ├─A
                  │  ├─B
                  ├─test
                  │  ├─A
                  │  ├─B

where A contains images of pre-phase, B contains images of post-phase.

• Dataset mean and variance:

Folder	R_mean	G_mean	B_mean	R_var	G_var	B_var
A	0.44152	0.43863	0.37418	0.17623	0.16578	0.15337
B	0.33992	0.33383	0.28561	0.13035	0.12678	0.11959
ALL	0.39073	0.38623	0.32989	0.15329	0.14628	0.13648

• The LEVIR-CC dataset contains 10,077 pairs of bi-temporal remote sensing images and 50,385 sentences describing the differences between images:

  

  

• Some examples of our dataset are as follows:

LEVIR- MCI Dataset

• The dataset contains bi-temporal images as well as diverse change detection masks and descriptive sentences. It provides a crucial data foundation for exploring multi-task learning for change detection and change captioning.

• Download link (https://github.com/Chen-Yang-Liu/Change-Agent)

  

• Some examples of our dataset are as follows: