ISOD (Indoor Small Object Dataset)
Introduced by Chen et al. in A Self-Supervised Miniature One-Shot Texture Segmentation (MOSTS) Model for Real-Time Robot Navigation and Embedded Applications
ISOD contains 2,000 manually labelled RGB-D images from 20 diverse sites, each featuring over 30 types of small objects randomly placed amidst the items already present in the scenes. These objects, typically ≤3cm in height, include LEGO blocks, rags, slippers, gloves, shoes, cables, crayons, chalk, glasses, smartphones (and their cases), fake banana peels, fake pet waste, and piles of toilet paper, among others. These items were chosen because they either threaten the safe operation of indoor mobile robots or create messes if run over.
In addition to RGB images, ISOD also includes corresponding depth images and IMU readings. A reference image of each floor type was also recorded using a smartphone.
This dataset was used as a real-world validation dataset in the original work to explore the performance of the model beyond synthetic data, specifically focusing on the potential application of real-time robot navigation.
Papers
| Paper | Code | Results | Date | Stars |
|---|
