Aerial LaneNet: Lane Marking Semantic Segmentation in Aerial Imagery using Wavelet-Enhanced Cost-sensitive Symmetric Fully Convolutional Neural Networks
This work addresses the need for accurate lane marking detection in aerial imagery to support autonomous driving and urban planning, but it appears incremental as it builds on existing segmentation methods with specific enhancements.
The authors tackled lane marking segmentation in aerial imagery for autonomous driving and mapping by proposing a wavelet-enhanced symmetric fully convolutional neural network with a custom loss and data augmentation, achieving very high accuracy in pixel-wise localization.
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.