yangxue0827/R2CNN_FPN_Tensorflow
A Tensorflow implementation of rotational region CNN for oriented object detection using feature pyramid networks.
Not currently ranked — collecting fresh signals.
star history
This project implements R2CNN and FPN detection frameworks for rotation-robust scene text detection and arbitrary-oriented object detection such as ships in remote sensing imagery. It uses ResNet as a backbone with multi-scale feature pyramid networks, operates on oriented bounding boxes rather than axis-aligned boxes, and is applied to satellite/remote sensing ship detection and scene text detection tasks. The implementation targets research use with Tensorflow and CUDA support.
Frequently asked
- What is yangxue0827/R2CNN_FPN_Tensorflow?
- A Tensorflow implementation of rotational region CNN for oriented object detection using feature pyramid networks.
- Is R2CNN_FPN_Tensorflow open source?
- Yes — yangxue0827/R2CNN_FPN_Tensorflow is an open-source project tracked on heatdrop.
- What language is R2CNN_FPN_Tensorflow written in?
- yangxue0827/R2CNN_FPN_Tensorflow is primarily written in Python.
- How popular is R2CNN_FPN_Tensorflow?
- yangxue0827/R2CNN_FPN_Tensorflow has 420 stars on GitHub.
- Where can I find R2CNN_FPN_Tensorflow?
- yangxue0827/R2CNN_FPN_Tensorflow is on GitHub at https://github.com/yangxue0827/R2CNN_FPN_Tensorflow.