Aerial LaneNet: Lane Marking Semantic Segmentation in Aerial Imagery using Wavelet-Enhanced Cost-sensitive Symmetric Fully Convolutional Neural Networks

TL;DR

This paper introduces Aerial LaneNet, a novel neural network architecture enhanced with wavelet transforms and cost-sensitive learning, achieving high-accuracy lane marking segmentation in aerial imagery for autonomous driving and urban planning.

Contribution

It presents a new symmetric fully convolutional neural network with wavelet enhancement and a custom loss function, along with the first high-quality aerial lane marking dataset for benchmarking.

Findings

High pixel-wise accuracy in lane marking segmentation

Effective handling of class imbalance with customized loss and data augmentation

Introduction of a publicly available aerial lane marking dataset

Abstract

The knowledge about the placement and appearance of lane markings is a prerequisite for the creation of maps with high precision, necessary for autonomous driving, infrastructure monitoring, lane-wise traffic management, and urban planning. Lane markings are one of the important components of such maps. Lane markings convey the rules of roads to drivers. While these rules are learned by humans, an autonomous driving vehicle should be taught to learn them to localize itself. Therefore, accurate and reliable lane marking semantic segmentation in the imagery of roads and highways is needed to achieve such goals. We use airborne imagery which can capture a large area in a short period of time by introducing an aerial lane marking dataset. In this work, we propose a Symmetric Fully Convolutional Neural Network enhanced by Wavelet Transform in order to automatically carry out lane marking segmentation in aerial imagery. Due to a heavily unbalanced problem in terms of number of lane marking pixels compared with background pixels, we use a customized loss function as well as a new type of data augmentation step. We achieve a very high accuracy in pixel-wise localization of lane markings without using 3rd-party information. In this work, we introduce the first high-quality dataset used within our experiments which contains a broad range of situations and classes of lane markings representative of current transportation systems. This dataset will be publicly available and hence, it can be used as the benchmark dataset for future algorithms within this domain.