AdaSpectrum: Lightweight Hyperspectral Fine-Grained Classification of Visually Similar Materials from RGB Images on Mobile Platforms

Geyang Song, Bin Guo, Sicong Liu, Lehao Wang, Zhiwen Yu

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

To solve the classification problem of visually similar materials on mobile devices, this paper proposes AdaSpectrum, a mobile hyperspectral imaging system for visually similar material classification, such as powder material,it processes RGB and near-infrared(NIR) images to generate hyperspectral data and classify materials directly on mobile devices. It focuses on optimizing performance for mobile devices, reducing computational load and improving speed and memory efficiency. Preliminary results show the system effectively balances accuracy and resource constraints, with plans to expand its applications to more material types.

源语言英语
主期刊名RMELS 2024 - Proceedings of the 1st ACM International Workshop on Resource-efficient Mobile and Embedded LLM System in AIoT, Part of
主期刊副标题ACM Sensys 2024
出版商Association for Computing Machinery, Inc
1-2
页数2
ISBN(电子版)9798400712951
DOI
出版状态已出版 - 4 11月 2024
活动1st ACM International Workshop on Resource-efficient Mobile and Embedded LLM System in AIoT, RMELS 2024 - Hangzhou, 中国
期限: 4 11月 2024 → …

出版系列

姓名RMELS 2024 - Proceedings of the 1st ACM International Workshop on Resource-efficient Mobile and Embedded LLM System in AIoT, Part of: ACM Sensys 2024

会议

会议1st ACM International Workshop on Resource-efficient Mobile and Embedded LLM System in AIoT, RMELS 2024
国家/地区中国
Hangzhou
时期4/11/24 → …

指纹

探究 'AdaSpectrum: Lightweight Hyperspectral Fine-Grained Classification of Visually Similar Materials from RGB Images on Mobile Platforms' 的科研主题。它们共同构成独一无二的指纹。

引用此