DeepAI AI Chat
Log In Sign Up

River Ice Segmentation with Deep Learning

by   Abhineet Singh, et al.
University of Alberta

This paper deals with the problem of computing surface ice concentration for two different types of ice from river ice images. It presents the results of attempting to solve this problem using several state of the art semantic segmentation methods based on deep convolutional neural networks (CNNs). This task presents two main challenges - very limited availability of labeled training data and the great difficulty of visually distinguishing the two types of ice, even for humans, leading to noisy labels.. The results are used to analyze the extent to which some of the best deep learning methods currently in existence can handle these challenges.


page 1

page 8

page 9

page 10


Deep Learning on Image Denoising: An overview

Deep learning techniques have obtained much attention in image denoising...

Learning Aerial Image Segmentation from Online Maps

This study deals with semantic segmentation of high-resolution (aerial) ...

Deep Projective 3D Semantic Segmentation

Semantic segmentation of 3D point clouds is a challenging problem with n...

Review on Indoor RGB-D Semantic Segmentation with Deep Convolutional Neural Networks

Many research works focus on leveraging the complementary geometric info...

Normalization in Training Deep Convolutional Neural Networks for 2D Bio-medical Semantic Segmentation

2D bio-medical semantic segmentation is important for surgical robotic v...

Singular points detection with semantic segmentation networks

Singular points detection is one of the most classical and important pro...