Detecting cities in aerial night-time images by learning structural invariants using single reference augmentation

TL;DR

This study investigates whether structural invariants of city images can be learned from a single reference image using data augmentation, PCA with Fourier transform, and CNNs, finding CNNs effective but PCA with Fourier transform ineffective.

Contribution

It demonstrates that CNNs can learn city image invariants from minimal data, whereas PCA with Fourier transform does not succeed in this task.

Findings

CNN successfully identifies city images across variants

PCA with Fourier transform fails to classify city images

Single reference augmentation can be effective for CNN training

Abstract

This paper examines, if it is possible to learn structural invariants of city images by using only a single reference picture when producing transformations along the variants in the dataset. Previous work explored the problem of learning from only a few examples and showed that data augmentation techniques benefit performance and generalization for machine learning approaches. First a principal component analysis in conjunction with a Fourier transform is trained on a single reference augmentation training dataset using the city images. Secondly a convolutional neural network is trained on a similar dataset with more samples. The findings are that the convolutional neural network is capable of finding images of the same category whereas the applied principal component analysis in conjunction with a Fourier transform failed to solve this task.