Summary of Bd-sat: High-resolution Land Use Land Cover Dataset & Benchmark Results For Developing Division: Dhaka, Bd, by Ovi Paul et al.
BD-SAT: High-resolution Land Use Land Cover Dataset & Benchmark Results for Developing Division: Dhaka, BD
by Ovi Paul, Abu Bakar Siddik Nayem, Anis Sarker, Amin Ahsan Ali, M Ashraful Amin, AKM Mahbubur Rahman
First submitted to arxiv on: 9 Jun 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper presents a high-resolution dataset called BD-SAT for Land Use Land Cover (LULC) analysis on satellite images. The dataset provides pixel-by-pixel annotations of LULC classes for Dhaka metropolitan city and surrounding rural/urban areas. The authors use Bing satellite imagery with a ground spatial distance of 2.22 meters per pixel to create the ground truth, following a three-stage annotation process with GIS experts. They establish benchmark results through several experiments, demonstrating that the annotated BD-SAT is sufficient to train large deep learning models with adequate accuracy for five major LULC classes: forest, farmland, built-up areas, water bodies, and meadows. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper creates a special dataset called BD-SAT that helps computers understand what’s in satellite pictures. They want to use this to see how cities grow and people live in poor countries. It’s hard because they don’t have enough pictures with the right information. The authors make their own pictures and label them, so computers can learn from them. They test it to make sure it works well. |
Keywords
» Artificial intelligence » Deep learning
