draft.pdf (2.57 MB)
A benchmark image dataset for industrial tools
journal contribution
posted on 2020-03-19, 12:15 authored by Cai Luo, Leijian Yu, Erfu Yang, Huiyu Zhou, Peng RenRobots and Artificial Intelligence (AI) play an increasingly important role in manufacture. One of the tasks is to identify tools in the scene so that the tools can be applied to different assembly purposes. In the AI community, many datasets have been generated and deployed to train robots to recognize individual items, however, these datasets are scene-specific and lack generic background. In this paper, we report our dataset contains photos of 8 objects types that would be easily recognized by qualified workers. This is achieved by gathering images of common tools in a typical factory. The ground truth categories of our dataset are manually labeled by experienced workers, which would be worthy evaluation tools for the intelligence industrial systems. The equipment used and the image collection process are discussed, along with the data format. The mean average precisions range from 64.37% to 78.20%, which bring the possibility for future improvement. The dataset is ideal to evaluate and benchmark view-point variant, vision-based control algorithm for industry robots. It is now public available from https://github.com/tools-dataset/Industrial-Tools-Detection-Dataset.
History
Citation
Pattern Recognition Letters, Volume 125, 2019, P 341-348Author affiliation
Department of InformaticsVersion
- AM (Accepted Manuscript)
Published in
PATTERN RECOGNITION LETTERSVolume
125Pagination
341 - 348Publisher
ELSEVIERissn
0167-8655eissn
1872-7344Acceptance date
2019-05-16Copyright date
2019Available date
2019-05-17Publisher DOI
Publisher version
https://www.sciencedirect.com/science/article/pii/S0167865519301606Language
EnglishUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC