Summary of Estimate the Building Height at a 10-meter Resolution Based on Sentinel Data, by Xin Yan
Estimate the building height at a 10-meter resolution based on Sentinel data
by Xin Yan
First submitted to arxiv on: 2 May 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG)
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 The proposed study develops a set of spatial-spectral-temporal feature databases for high-resolution building height estimation models. By combining Sentinel-1 SAR, Sentinel-2 optical, and building footprint shape data, the researchers create a rich database of 160 features using statistical indicators on the time scale. Feature importance is determined through permutation feature importance, Shapley Additive Explanations, and Random Forest variable importance, with expert scoring system validation. The study uses 12 US cities as training data, addressing SAR image displacement and building shadows via moving windows. A random forest model is built, and three ensemble methods (bagging, boosting, stacking) are compared. Evaluation results using Lidar data show an R-Square of 0.78, demonstrating the effectiveness of the proposed approach in producing high-resolution building height data. This research has significant implications for large-scale scientific studies and applications across various fields. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study creates a new way to estimate building heights with very high accuracy. It uses a combination of satellite images and maps to build a database that can be used for many different purposes. The researchers tested their method on 12 cities in the US and got an R-Square of 0.78, which is really good! This means that their method can be used to quickly and accurately get building height data, which is important for many fields such as urban planning and architecture. |
Keywords
» Artificial intelligence » Bagging » Boosting » Random forest
