DesertFormer: Transformer-Based Semantic Segmentation for Off-Road Desert Terrain Classification in Autonomous Navigation Systems

Reliable terrain perception is a fundamental requirement for autonomous navigation in unstructured, off-road environments. We present DesertFormer, a semantic segmentation pipeline for off-road desert terrain analysis based on SegFormer B2 with a hierarchical Mix Transformer (MiT-B2) backbone. The system classifies terrain into ten ecologically meaningful categories—Trees, Lush Bushes, Dry Grass, Dry Bushes, Ground Clutter, Flowers, Logs, Rocks, Landscape, and Sky—enabling safety-aware path planning for ground robots and autonomous vehicles. Trained on a purpose-built dataset of 4,176 annotated off-road images at 512×512 resolution, DesertFormer achieves a mean Intersection-over-Union (mIoU) of 64.4% and pixel accuracy of 86.1%, representing a +24.2% absolute improvement over a DeepLabV3 MobileNetV2 baseline (41.0% mIoU). Failure analysis identifies the primary confusion patterns—Ground Clutter ↔ Landscape and Dry Grass ↔ Landscape—arising from spectral similarity under desert lighting. Code, checkpoints, and an interactive inference dashboard are released at https://github.com/Yasaswini-ch/Vision-based-Desert-Terrain-Segmentation-using-SegFormer.