Awesome
SingleImageWaterHazardDetectionWithRAU
Single Image Water Hazard Detection using FCN with Reflection Attention Units <br> Xiaofeng Han <sup>1</sup>, Chuong Nguyen <sup>234</sup>, Shaodi You <sup>23</sup>, Jianfeng Lu <sup>1</sup> <br> <sup>1</sup>School of Computer Science and Engineering, Nanjing University of Science and Technology <br> <sup>2</sup>Australian National University <br> <sup>3</sup>CSIRO DATA61, Australia <br> <sup>4</sup>Australian Centre of Excellence for Robotic Vision <br> ECCV 2018
This is a work in progress and the final codes are coming soon.
Water Hazard Detection
The figure below shows one example of water hazard detection. In this figure, the red areas are the water areas.
Network Architecture
The figure shows our network architecture.
The figure below shows our proposed Reflection Attention Units
our paper
<br>The paper can be downloaded here: Single Image Water Hazard Detection using FCN with Reflection Attention Units
demo videos
The demo videos can be downloaded here: <br> ECCV DEMO video <br> OFF ROAD <br> ON ROAD
"Puddle-1000" dataset
The dataset used in our paper can be downloaded here: <br>Puddle-1000
The codes are modified based on this project: https://github.com/shekkizh/FCN.tensorflow, and we'd like to thank the authors very much.