Miniature Mobile Robot Image Localisation Dataset

Deploying deep learning models on low power devices is an increasingly important research challenge. Microcontrollers, in particular, have strict limitations due to the limited processing power and mem-ory. Specifically, object localisation on such devices remains in the early stages of research. The object of localisation in the dataset is a miniature mobile robot in a sand-like terrain with rocks. The dataset consists of 10,000 greyscale images (160\u00d7160 px) with Pascal VOC annotations, featuring robots and rocks and was acquired with the HM01B0 greyscale camera integrated with a low-power RP2040 microcontroller.