Learning Aerial Image Segmentation from Online Maps

by   Pascal Kaiser, et al.

This study deals with semantic segmentation of high-resolution (aerial) images where a semantic class label is assigned to each pixel via supervised classification as a basis for automatic map generation. Recently, deep convolutional neural networks (CNNs) have shown impressive performance and have quickly become the de-facto standard for semantic segmentation, with the added benefit that task-specific feature design is no longer necessary. However, a major downside of deep learning methods is that they are extremely data-hungry, thus aggravating the perennial bottleneck of supervised classification, to obtain enough annotated training data. On the other hand, it has been observed that they are rather robust against noise in the training labels. This opens up the intriguing possibility to avoid annotating huge amounts of training data, and instead train the classifier from existing legacy data or crowd-sourced maps which can exhibit high levels of noise. The question addressed in this paper is: can training with large-scale, publicly available labels replace a substantial part of the manual labeling effort and still achieve sufficient performance? Such data will inevitably contain a significant portion of errors, but in return virtually unlimited quantities of it are available in larger parts of the world. We adapt a state-of-the-art CNN architecture for semantic segmentation of buildings and roads in aerial images, and compare its performance when using different training data sets, ranging from manually labeled, pixel-accurate ground truth of the same city to automatic training data derived from OpenStreetMap data from distant locations. We report our results that indicate that satisfying performance can be obtained with significantly less manual annotation effort, by exploiting noisy large-scale training data.


page 1

page 4

page 5

page 6

page 7

page 10

page 11

page 12


Can Ground Truth Label Propagation from Video help Semantic Segmentation?

For state-of-the-art semantic segmentation task, training convolutional ...

River Ice Segmentation with Deep Learning

This paper deals with the problem of computing surface ice concentration...

PolyMapper: Extracting City Maps using Polygons

We propose a method to leapfrog pixel-wise, semantic segmentation of (ae...

Map Generation from Large Scale Incomplete and Inaccurate Data Labels

Accurately and globally mapping human infrastructure is an important and...

Semantic Segmentation of Remote Sensing Images with Sparse Annotations

Training Convolutional Neural Networks (CNNs) for very high resolution i...

EZLearn: Exploiting Organic Supervision in Large-Scale Data Annotation

Many real-world applications require large-scale data annotation, such a...

Please sign up or login with your details

Forgot password? Click here to reset