ARMBENCH DATASET

Home Download Contact Us RSS 2023 Workshop ☰

Defect Detection

The defect detection task is to identify if a robotic manipulation activity resulted in a defect. Two types of robot-induced defects are included in the dataset: 1. multi-pick, and 2. package-defect. Multi-pick is used to describe activities where multiple objects were picked and transferred from the source container to the destination container. Package-defect is used to describe activities where the object packaging opened and/or the object separated into multiple parts deconstruction. Two subclasses, open and deconstruction, are defined for package-defect.

The defect detection dataset is divided into:

Image defect detection (66G): This dataset comprises 13,303 images of objects with defects taking through multiple view-points (Transfer-images). For image defection detection, multi-pick and package-defects are the two defect classes. 100,000 images of objects with no defects are available in the dataset.

Video defect detection (255G): This dataset comprises 4,075 videos of objects with defects. Multi-picks are not observable in videos and are excluded from this dataset. At the same time, open and deconstruction defects are observable in videos and are annotated. 100,000 videos of activities that did not result in a defect are available in the dataset.

Train-Test-Split: List of training and test cases.