Summary of Cloudtracks: a Dataset For Localizing Ship Tracks in Satellite Images Of Clouds, by Muhammad Ahmed Chaudhry et al.
CloudTracks: A Dataset for Localizing Ship Tracks in Satellite Images of Clouds
by Muhammad Ahmed Chaudhry, Lyna Kim, Jeremy Irvin, Yuzu Ido, Sonia Chu, Jared Thomas Isobe, Andrew Y. Ng, Duncan Watson-Parris
First submitted to arxiv on: 25 Jan 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 A new machine learning approach is presented to localize and count ship tracks in satellite images, which are distinct from adjacent cloud regions and serve as a useful sandbox to study human-induced clouds. The dataset, CloudTracks, contains 3,560 labeled satellite images with over 12,000 ship track instance annotations. State-of-the-art semantic segmentation and instance segmentation model baselines are trained on the dataset, achieving an IoU of 61.29 and MAE of 1.64, respectively. However, the best model struggles to accurately localize and count elongated and overlapping features in satellite images. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Clouds help keep our planet cool by reflecting sunlight, but human activities like ship pollution can change how clouds work. By looking at pictures taken from space, scientists can see how ships affect the surrounding clouds. However, it’s hard to study this effect because there isn’t much data available. To fix this problem, a new dataset called CloudTracks was created, which includes over 3,500 labeled satellite images with more than 12,000 ship tracks identified. This helps machines learn to spot and count these ship tracks better. |
Keywords
* Artificial intelligence * Instance segmentation * Machine learning * Mae * Semantic segmentation
