SSORT: Semantic Segmentation for Off-Road Traversibility
Real-time semantic scene understanding is a challenging computer vision task for autonomous vehicles. In the context of autonomous driving, the existing semantic segmentation concept strongly supports on-road driving where hard inter-class bound- aries are enforced and objects can be categorized based on their visible structures with high confidence. Due to the well-structured nature of typical on-road scenes, current road extraction processes are largely successful and most types of vehicles are able to traverse through the area that is detected as road. However, the off-road driving domain has many additional uncertainties such as uneven terrain structure, positive and negative obstacles, hidden objects, etc. making it very unstructured. Traversing through such unstructured area is constrained by a vehicle’s type and its capabil- ity. Most modern convolutional neural networks require large computing resources that go beyond the capabilities of many robotic platforms. Image segmentation is a key task in computer vision and image processing with important applications such as scene understanding, robotic perception and video surveillance. This project will serve as an extension of existing off-road semantic segmentation studies. The primary emphasis of the thesis is on locating and visualising the route over off-road terrain