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

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 high accuracy in pixelwise localization of lane markings compared with the state-ofthe-art methods 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 today's transportation systems. This dataset will be publicly available and hence, it can be used as the benchmark dataset for future algorithms within this domain.

FastDraw: Addressing the Long Tail of Lane Detection by Adapting a Sequential Prediction Network

“…Lane detection is not isolated to dashcam imagery. Models that detect lanes in dashcams can in general be adapted to detect lanes in lidar point-clouds, open street maps, and satellite imagery [16,23,4]. The success of semantic segmentation based approaches to lane detection has benefited tremendously from rapid growth in architectures that empirically perform well on dense segmentation tasks [5,26,25].…”

3D Semantic Segmentation from Multi-View Optical Satellite Images

“…Inspired by the works of [7,8,9, 10], we use a second network named "Small and large structure-sensitive CNN" (SLSS-CNN). It consists of two streams and is trained on RGB im- 1 https://github.com/pubgeo/dfc2019 ages only.…”

Fully Convolutional Neural Network with Augmented Atrous Spatial Pyramid Pool and Fully Connected Fusion Path for High Resolution Remote Sensing Image Segmentation

“…Remote sensing (RS) image segmentation technology plays a key role in the fields of urban planning [1], RS mapping [2,3], precision agriculture [4,5], landscape classification [6,7], traffic monitoring [8], environmental protection [9], climate change [10] and forest vegetation [11], and therefore provides important decision support for human work and life.…”