IROS 2019 Lifelong Robotic Vision Challenge -- Lifelong Object Recognition Report
Abstract
This report summarizes IROS 2019-Lifelong Robotic Vision Competition (Lifelong Object Recognition Challenge) with methods and results from the top finalists (out of over~ teams). The competition dataset (L)ifel(O)ng (R)obotic V(IS)ion (OpenLORIS) - Object Recognition (OpenLORIS-object) is designed for driving lifelong/continual learning research and application in robotic vision domain, with everyday objects in home, office, campus, and mall scenarios. The dataset explicitly quantifies the variants of illumination, object occlusion, object size, camera-object distance/angles, and clutter information. Rules are designed to quantify the learning capability of the robotic vision system when faced with the objects appearing in the dynamic environments in the contest. Individual reports, dataset information, rules, and released source code can be found at the project homepage: "https://lifelong-robotic-vision.github.io/competition/".
Cite
@article{arxiv.2004.14774,
title = {IROS 2019 Lifelong Robotic Vision Challenge -- Lifelong Object Recognition Report},
author = {Qi She and Fan Feng and Qi Liu and Rosa H. M. Chan and Xinyue Hao and Chuanlin Lan and Qihan Yang and Vincenzo Lomonaco and German I. Parisi and Heechul Bae and Eoin Brophy and Baoquan Chen and Gabriele Graffieti and Vidit Goel and Hyonyoung Han and Sathursan Kanagarajah and Somesh Kumar and Siew-Kei Lam and Tin Lun Lam and Liang Ma and Davide Maltoni and Lorenzo Pellegrini and Duvindu Piyasena and Shiliang Pu and Debdoot Sheet and Soonyong Song and Youngsung Son and Zhengwei Wang and Tomas E. Ward and Jianwen Wu and Meiqing Wu and Di Xie and Yangsheng Xu and Lin Yang and Qiaoyong Zhong and Liguang Zhou},
journal= {arXiv preprint arXiv:2004.14774},
year = {2020}
}
Comments
9 pages, 11 figures, 3 tables, accepted into IEEE Robotics and Automation Magazine. arXiv admin note: text overlap with arXiv:1911.06487