A Multi-Stage Multi-Task Neural Network for Aerial Scene Interpretation and Geolocalization
This addresses the problem of efficient and accurate aerial image analysis for applications like UAV navigation, though it is incremental as it builds on existing deep learning methods.
The paper tackles aerial scene interpretation and geolocalization by proposing a multi-stage multi-task neural network that simultaneously performs semantic segmentation and location prediction in a single forward pass, achieving commercial GPS-level localization accuracy and state-of-the-art results on two datasets.
Semantic segmentation and vision-based geolocalization in aerial images are challenging tasks in computer vision. Due to the advent of deep convolutional nets and the availability of relatively low cost UAVs, they are currently generating a growing attention in the field. We propose a novel multi-task multi-stage neural network that is able to handle the two problems at the same time, in a single forward pass. The first stage of our network predicts pixelwise class labels, while the second stage provides a precise location using two branches. One branch uses a regression network, while the other is used to predict a location map trained as a segmentation task. From a structural point of view, our architecture uses encoder-decoder modules at each stage, having the same encoder structure re-used. Furthermore, its size is limited to be tractable on an embedded GPU. We achieve commercial GPS-level localization accuracy from satellite images with spatial resolution of 1 square meter per pixel in a city-wide area of interest. On the task of semantic segmentation, we obtain state-of-the-art results on two challenging datasets, the Inria Aerial Image Labeling dataset and Massachusetts Buildings.