: Object-Detection
-
HRSC2016 in oriented-det — recipes, trains, and a held-out 90.41%
Native HRSC2016 ship detection in oriented-det: ImageSets trainval in, held-out test out, three 3× Hub weights. Oriented R-CNN 90.41%, Faster R-CNN 88.77%, FCOS 88.34% mAP50 on NVIDIA L4.
-
A static demo of three oriented detectors on optical satellite imagery
A browser demo of Oriented-Det’s three 3× DOTA checkpoints — Oriented R-CNN, Rotated Faster R-CNN, and Rotated FCOS — on seven optical satellite scenes, with a side by side comparison that lands in parity with state of the art frameworks.
-
Detecting ships in satellite imagery: five years later…
Revisiting ship detection in SPOT imagery — from Kaggle to MMRotate.
-
Is YOLOv8 suitable for satellite imagery?
Tuning YOLOv8 for satellite imagery — what works and what to change.
-
How to choose a deep learning architecture to detect aircrafts in satellite imagery?
Comparing deep learning architectures for aircraft detection in satellite imagery.
-
Oil Storage Detection on Airbus Imagery with YOLOX
Detecting oil storage tanks on Airbus imagery with YOLOX.
-
Detecting aircraft on Airbus Pleiades imagery with YOLOv5
Training YOLOv5 on Airbus Pleiades imagery for aircraft detection.