Abstract | ||
---|---|---|
In this paper, we introduce an AC-Retina approach, which uses RetinaNet as a base architecture and integrates an atrous convolution (AC) module to extract multiscale context information for hand detection in intelligent homecare (IH) systems. Given that the AC module is adopted in the feature pyramid network (FPN), rich semantic information of higher pyramid layers is added to the lower pyramid layers to improve the detection performance. The experimental results show that our AC-Retina method obtains 82.99% AP and outperforms the original RetinaNet on the Oxford hand dataset. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/ICCE-Taiwan49838.2020.9258335 | 2020 IEEE International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan) |
Keywords | DocType | ISSN |
feature pyramid network,semantic information,pyramid layers,RetinaNet,Oxford hand dataset,hand detection,intelligent homecare systems,base architecture,atrous convolution module,multiscale context information,AC module,AC-retina | Conference | 2575-8276 |
ISBN | Citations | PageRank |
978-1-7281-7400-6 | 0 | 0.34 |
References | Authors | |
2 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Quoc-Viet Hoang | 1 | 0 | 0.68 |
Trung-Hieu Le | 2 | 2 | 1.55 |
Shih-Chia Huang | 3 | 657 | 42.31 |