Wei Zhou, Alex Zyner, Stewart Worrall, and Eduardo Nebot
Abstract: Semantic segmentation using deep neural networks has been widely explored to generate high-level contextual information for autonomous vehicles. To acquire a complete 180◦ semantic understanding of the forward surroundings, we propose to stitch semantic images from multiple cameras with varying orientations. However, previously trained semantic segmentation models showed unacceptable performance after significant changes to the camera orientations and the lighting conditions. To avoid time-consuming hand labeling, we explore and evaluate the use of data augmentation techniques, specifically skew and gamma correction,from a practical real-world standpoint to extend the existing model and provide more robust performance. The experimental results presented have shown significant improvements with varying illumination and camera perspective changes. A comparison of the results from a high-performance network (PSPNet), and a real-time capable network (ENet) is provided.