TOMD: A Trail-based Off-road Multimodal Dataset for Traversable Pathway Segmentation under Challenging Illumination Conditions
We present TOMD, designed to capture complex, unstructured trail environments using a medium-scale all-terrain robot platform. The dataset integrates high-fidelity 3D LiDAR (128 channels), stereo imagery, GNSS, IMU, telemetry control data, and illumination measurements, all collected through repeated traversals under varying environmental conditions. Data was gathered in the hilly regions near the Department of Mathematics and Computer Science at Durham University (United Kingdom), encompassing diverse natural terrains such as grasslands, bushes, tree-dense areas, leaf-covered trails, and slopes.
Descriptions
Items in this Collection
Title | Date Uploaded | Visibility | Action |
---|