https://github.com/onapte/urbangreenspaces-satellite-imagery

(ONGOING) Developing a Generalizable Computer Vision Model for Detecting Urban Green Spaces and Outdoor Sports Facilities in Aerial Imagery
https://github.com/onapte/urbangreenspaces-satellite-imagery

Last synced: 28 days ago
JSON representation

(ONGOING) Developing a Generalizable Computer Vision Model for Detecting Urban Green Spaces and Outdoor Sports Facilities in Aerial Imagery

• Host: GitHub
• URL: https://github.com/onapte/urbangreenspaces-satellite-imagery
• Owner: onapte
• Created: 2024-11-06T19:10:23.000Z (about 2 months ago)
• Default Branch: main
• Last Pushed: 2024-11-28T23:49:09.000Z (about 1 month ago)
• Last Synced: 2024-11-29T00:27:23.095Z (about 1 month ago)
• Size: 1000 Bytes
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# urbangreenspaces-satellite-imagery

(ONGOING)  Developing a Generalizable Computer Vision Model for Detecting Urban Green Spaces and  Outdoor Sports Facilities in Aerial Imagery

## Current results

![image](https://github.com/user-attachments/assets/096bbba3-f6eb-46a0-b029-a08be029c997)

![image](https://github.com/user-attachments/assets/69d12047-7931-470f-85d0-608f54b01a82)

## Next Steps

-	Collect and annotate additional aerial images featuring open grounds, and incorporate some images from the DOTA dataset.

-	Train and evaluate various object detection models (EfficientDet, RetinaNet, and SSD), including currently used, on aerial images that include all three classes: parks, open grounds, and specialized sports facilities.

-	Compile the results in a table and provide an interpretation of the findings.