braun-steven/DAFNe
Code for our paper "DAFNe: A One-Stage Anchor-Free Deep Model for Oriented Object Detection".
This project helps computer vision engineers and researchers accurately identify and locate objects in aerial or satellite images, even when they are oriented at various angles. You input an image containing objects like ships, vehicles, or buildings, and it outputs bounding boxes that precisely outline each object, noting its orientation. This is ideal for those developing advanced object recognition systems for geospatial analysis or surveillance.
No commits in the last 6 months.
Use this if you need to detect objects in images that are not always upright and require precise bounding boxes that account for rotation.
Not ideal if your application only requires standard axis-aligned bounding box detection for upright objects.
Stars
61
Forks
12
Language
Python
License
MIT
Category
Last pushed
Apr 01, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/braun-steven/DAFNe"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
broadinstitute/keras-rcnn
Keras package for region-based convolutional neural networks (RCNNs)
alankbi/detecto
Build fully-functioning computer vision models with PyTorch
sovit-123/fasterrcnn-pytorch-training-pipeline
PyTorch Faster R-CNN Object Detection on Custom Dataset
kenshohara/video-classification-3d-cnn-pytorch
Video classification tools using 3D ResNet
lufficc/SSD
High quality, fast, modular reference implementation of SSD in PyTorch