Single Image Water Hazard Detection using FCN with Reflection Attention Units

2018-09-01 · ECCV 2018 9 · Xiaofeng Han, Chuong Nguyen, ShaoDi You, Jianfeng Lu

Water bodies, such as puddles and flooded areas, on and off road pose significant risks to autonomous cars. Detecting water from moving camera is a challenging task as water surface is highly refractive, and its appearance varies with viewing angle, surrounding scene, weather conditions. In this paper, we present a water puddle detection method based on a Fully Convolutional Network (FCN) with our newly proposed Reflection Attention Units (RAUs). An RAU is a deep network unit designed to embody the physics of reflection on water surface from sky and nearby scene. To verify the performance of our proposed method, we collect 11455 color stereo images with polarizers, and 985 of left images are annotated and divided into 2 datasets: On Road (ONR) dataset and Off Road (OFR) dataset. We show that FCN-8s with RAUs improves significantly precision and recall metrics as compared to FCN-8s, DeepLab V2 and Gaussian Mixture Model (GMM). We also show that focal loss function can improve the performance of FCN-8s network due to the extreme imbalance of water versus ground classification problem.

📄 PDF Abstract BibTeX

Code (1)

Cow911/SingleImageWaterHazardDetectionWithRAU 공식 구현 tf

Methods 이 논문이 사용한 방법론

CRF Conditional Random Fields or CRFs are a type of probabilistic graph model that take neighboring sample context into account for tasks like classification. Prediction is…

Dilated Convolution 설명 없음

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Feedforward Network A Feedforward Network, or a Multilayer Perceptron (MLP), is a neural network with solely densely connected layers. This is the classic neural network architecture of the…

DeepLab 설명 없음

Focal Loss A Focal Loss function addresses class imbalance during training in tasks like object detection. Focal loss applies a modulating term to the cross entropy loss in order to…

3D tracking of water hazards with polarized stereo cameras

2017-01-16 · Chuong V. Nguyen, Michael Milford, Robert Mahony

Current self-driving car systems operate well in sunny weather but struggle in adverse conditions. One of the most commonly encountered adverse conditions involves water on the road caused by rain, sleet, melting snow or…

Water Reflection Detection Using Symmetric Attention

2026-07-12 · Shuxuan Yao, Chengjia Wang, Jianyuan Sun, Junyu Dong 외 arxiv

Reflections of water pose a significant challenge for computer vision systems, as standard deep learning models frequently confuse objects with their mirror images, producing spurious false positives and negatives in tas…

Semantic Segmentation Scene Understanding Object Detection

Appearance and Shape from Water Reflection

2019-06-25 · Ryo Kawahara, Meng-Yu Jennifer Kuo, Shohei Nobuhara, Ko Nishino

This paper introduces single-image geometric and appearance reconstruction from water reflection photography, i.e., images capturing direct and water-reflected real-world scenes. Water reflection offers an additional vie…

3D Scene Reconstruction Stereo Matching Stereo Matching Hand

FRED: A Multi-Modal Autonomous Driving Dataset for Flooded Road Environments

2026-05-21 · Connor Malone, Sebastien Demmel, Sebastien Glaser arxiv

The Flooded Road Environments Dataset (FRED) is, to our knowledge, the first multi-modal autonomous driving dataset specifically targeting the collection of data from scenarios involving water hazards on the road. The da…

Autonomous Driving Point Clouds

Water Simulation and Rendering from a Still Photograph

2022-10-05 · Ryusuke Sugimoto, Mingming He, Jing Liao, Pedro V. Sander

We propose an approach to simulate and render realistic water animation from a single still input photograph. We first segment the water surface, estimate rendering parameters, and compute water reflection textures with …