OFFSEG: A Semantic Segmentation Framework For Off-Road Driving

TL;DR

OFFSEG is a novel deep learning framework designed for off-road semantic segmentation, effectively handling uneven terrains and complex textures to improve vehicle perception and path planning.

Contribution

It introduces a combined approach of pooled class segmentation and color-based sub-class segmentation tailored for off-road environments.

Findings

Achieves good performance on RELLIS-3D and RUGD datasets.

Provides detailed scene understanding for off-road driving.

Effective in segmenting traversable regions and obstacles.

Abstract

Off-road image semantic segmentation is challenging due to the presence of uneven terrains, unstructured class boundaries, irregular features and strong textures. These aspects affect the perception of the vehicle from which the information is used for path planning. Current off-road datasets exhibit difficulties like class imbalance and understanding of varying environmental topography. To overcome these issues we propose a framework for off-road semantic segmentation called as OFFSEG that involves (i) a pooled class semantic segmentation with four classes (sky, traversable region, non-traversable region and obstacle) using state-of-the-art deep learning architectures (ii) a colour segmentation methodology to segment out specific sub-classes (grass, puddle, dirt, gravel, etc.) from the traversable region for better scene understanding. The evaluation of the framework is carried out on two off-road driving datasets, namely, RELLIS-3D and RUGD. We have also tested proposed framework in IISERB campus frames. The results show that OFFSEG achieves good performance and also provides detailed information on the traversable region.