The DUST (Dual-Use Star Tracker) dataset is an openly accessible collection of on-orbit, wide-field near-infrared imagery acquired by the Fast Auroral Imager (FAI) aboard the CASSIOPE spacecraft between January and August 2023. The dataset comprises 1,378 astrometrically calibrated images containing 4,237 manually verified resident space object (RSO) instances across 160 transits. It also includes catalog-matched stars, spacecraft ephemeris and attitude data, and detailed image-background characterization metrics. The images were captured at a cadence of 1 Hz with a 26° field of view and contain challenging real-world imaging conditions, including dense stellar backgrounds, stray light, lens flare, motion blur, optical artifacts, and spacecraft-induced jitter. RSOs are annotated in both YOLO object-detection and MOT multi-object-tracking formats. Star-detection records include pixel centroids, right ascension, declination, catalog magnitudes, and astrometric-match confidence values. DUST supports research in RSO detection, multi-object tracking, star–RSO discrimination, astrometric calibration, and spacecraft attitude estimation using star-tracker-class imagery. It helps bridge the gap between synthetic benchmarks and restricted operational datasets by providing realistic, comprehensively annotated, and reproducible on-orbit observations. The code used for dataset generation, preprocessing, annotation, analysis, and figure production is provided alongside the data to support transparency and reproducibility. Associated Peer-Reviewed Publication The data contained in this repository are formally described, technically validated, and documented in the following peer-reviewed *Scientific Data* Data Descriptor: Suthakar, V., Kunalakantha, P., Lee, R. S. K., and Sohn, G. (2026). “An On-Orbit Star Tracker Benchmark for Resident Space Object Detection and Attitude Estimation.” Scientific Data. https://doi.org/10.1038/s41597-026-07736-9 When using DUST, please cite both the peer-reviewed Data Descriptor and the Zenodo dataset record. bibtex@article{suthakar2026dust, title = {An On-Orbit Star Tracker Benchmark for Resident Space Object Detection and Attitude Estimation}, author = {Suthakar, Vithurshan and Kunalakantha, Perushan and Lee, Regina S. K. and Sohn, Gunho}, journal = {Scientific Data}, year = {2026}, doi = {10.1038/s41597-026-07736-9}, url = {https://doi.org/10.1038/s41597-026-07736-9}} bibtex@dataset{suthakar2026dust_data, title = {DUST: An On-Orbit Star-Tracker Benchmark for RSO Detection and Attitude Estimation}, author = {Suthakar, Vithurshan and Kunalakantha, Perushan and Lee, Regina S. K. and Sohn, Gunho}, year = {2026}, publisher = {Zenodo}, version = {V2}, doi = {10.5281/zenodo.20255672}, url = {https://doi.org/10.5281/zenodo.20255672}} Related Publications Depending on the specific data, annotations, or methodologies used, please also consider citing the following related publications. The following study presents a rules-based method for RSO detection and tracking in low-resolution, non-constant-attitude FAI imagery: @article{kunalakantha2026resident, title = {Resident Space Object ({RSO}) Tracking in Space-Based, Low Resolution, Non-Constant-Attitude Imagery}, author = {Kunalakantha, Perushan and Suthakar, Vithurshan and Harrison, Paul and Driedger, Matthew and Qashoa, Randa and Chianelli, Gabriel and Lee, Regina S. K.}, journal = {Remote Sensing}, volume = {18}, number = {5}, pages = {755}, year = {2026}, publisher = {MDPI}, doi = {10.3390/rs18050755}, url = {https://doi.org/10.3390/rs18050755}} The following study presents the OrbitTrack deep-learning framework for RSO detection and multi-object tracking using wide-field on-orbit imagery: @article{jeong2025orbittrack, title = {{OrbitTrack}: Advanced {RSO} Detection and Tracking from Wide Field-of-View On-Orbit Images}, author = {Jeong, YeonJeong and Suthakar, Vithurshan and Qashoa, Randa and Sohn, Gunho and Lee, Regina S. K.}, journal = {Advances in Space Research}, volume = {76}, number = {8}, pages = {4387--4400}, year = {2025}, publisher = {Elsevier}, doi = {10.1016/j.asr.2025.08.006}, url = {https://doi.org/10.1016/j.asr.2025.08.006}} This work was supported by the Natural Sciences and Engineering Research Council of Canada Discovery Grant (grant number RGPIN-2025-06284), the DND/NSERC Discovery Grant Supplement (Application ID DGDND-2025-06284), and the Canadian Space Agency Flights and Fieldwork for the Advancement of Science and Technology (FAST) program (grant number 23FAYORA06), in collaboration with Magellan Aerospace and Defence Research and Development Canada.