Summary of Paved or Unpaved? a Deep Learning Derived Road Surface Global Dataset From Mapillary Street-view Imagery, by Sukanya Randhawa et al.
Paved or unpaved? A Deep Learning derived Road Surface Global Dataset from Mapillary Street-View Imagery
by Sukanya Randhawa, Eren Aygun, Guntaj Randhawa, Benjamin Herfort, Sven Lautenbach, Alexander Zipf
First submitted to arxiv on: 24 Oct 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 The proposed hybrid deep learning approach combines SWIN-Transformer-based road surface prediction with CLIP-and-DL segmentation-based thresholding for filtering out bad-quality images. This method is used to derive an open dataset of global coverage on road surface characteristics, leveraging state-of-the-art geospatial AI methods and 105 million images from the Mapillary platform. The resulting data provides insights into the spatial distribution of paved and unpaved roads across continents, countries, and rural/urban areas. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study provides a large dataset of global road surface information, which can be used for various applications such as urban planning, disaster routing, logistics optimization, and addressing Sustainable Development Goals. The data shows that most regions have moderate to high paved road coverage, but there are significant gaps in specific areas of Africa and Asia. Urban areas tend to have near-complete paved coverage, while rural regions display more variability. |
Keywords
» Artificial intelligence » Deep learning » Optimization » Transformer
