Skip to content

gupta-lokesh/Dstl-Satellite-Imagery-Feature-Detection

Repository files navigation

Dstl-Satellite-Imagery-Feature-Detection. Can you train an eye in the sky? (Image Segmentation)

Objective: Semantic segmentation of different classes in satellite imagery.

Models: Built U-net and Seg-Net models to generate masks.

Results: Using U-net model received Jaccard score 0.3752 on test data and for the Seg-Net test Jaccard score as 0.4463.

Use-cases: The model can be trained for various image segmentation tasks in satellite imagery, can be used in defense and security systems, creating and keeping up-to-date maps, disaster relief, and improving urban planning.

About

Semantic segmentation of different classes in satellite imagery.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published