We have conducted a pilot study to investigate how to collect videos. During that pilot study, we gathered 193 videos from eight people who are blind or low vision, each of whom were asked to take videos of five different objects. For each thing, we have videos in different settings in their home and using different filming techniques, some of which they were free to choose. If you would like access to this limited dataset for research purposes, please contact us.
Phase 1 and Phase 2 datasets
The dataset is publicly available from our servers https://doi.org/10.25383/city.14294597. It’s provided under a CC-BY4.0 licence so please attribute it by citing:
Daniela Massiceti, Lida Theodorou, Luisa Zintgraf, Matthew Tobias Harris, Simone Stumpf, Cecily Morrison, Edward Cutrell, and Katja Hofmann. 2021. ORBIT: A real-world few-shot dataset for teachable object recognition collected from people who are blind or low vision. DOI:https://doi.org/10.25383/city.14294597
We also have an arXiv paper which describes the dataset and some benchmarks: http://arxiv.org/abs/2104.03841
The dataset is aimed at developing few shot learning algorithms so it might not be the most suitable for your purposes. However, we are very keen to find out if and how you use this dataset. Please let us know about your project!