A framework based on Deep Learning for feature extraction

Road markings play a critical role in road traffic safety and are one of the most important elements for guiding autonomous vehicles (AVs). 

High-Definition (HD) maps with accurate road marking information are very useful for many applications ranging from road maintenance, improving navigation, and prediction of upcoming road situations within AVs. 

This paper presents a deep learning-based framework for road marking extraction, classification and completion from three-dimensional (3D) mobile laser scanning (MLS) point clouds. 

Compared with existing road marking extraction methods, which are mostly based on intensity thresholds, our method is less sensitive to data quality. 

We added the step of road marking completion to further optimize the results. 

At the extraction stage, a modified U-net model was used to segment road marking pixels to overcome the intensity variation, low contrast and other issues. 

At the classification stage, a hierarchical classification method by integrating multi-scale clustering with Convolutional Neural Networks (CNN) was developed to classify different types of road markings with considerable differences. 

At the completion stage, a method based on a Generative Adversarial Network (GAN) was developed to complete small-size road markings first, then followed by completing broken lane lines and adding missing markings using a context-based method. In addition, we built a point cloud road marking dataset to train the deep network model and evaluate our method. 

The dataset contains urban road and highway MLS data and underground parking lot data acquired by our own assembled backpacked laser scanning system. 

Our experimental results obtained using the point clouds of different scenes demonstrated that our method is very promising for road marking extraction, classification and completion.