Development and Implementation of Image Caption System with Deep Learning Algorithms and Edge Computing Scheme

Project: National Science and Technology CouncilNational Science and Technology Council Academic Grants

Project Details

Abstract

圖像描述演算法目的是從圖片中自動生成一段描述性文字,簡言之即是「看圖說話」。難度是不僅要能檢測出影像中的物件,而且還要理解物件之間的相互關係,最後還要用合理的語言表達出來。本計畫將採用NVIDIA Jetson Nano做為邊緣運算裝置,另將搭配攝影模組與藍牙播放裝置,以執行影像初步辨識。雲端裝置將使用硬體效能更好的GPU運算主機,用以執行運算較為複雜的圖像描述與物件辨識演算法,並將結果回傳至邊緣運算裝置。

Project IDs

Project ID:PB11007-5324
External Project ID:MOST110-2221-E182-055
StatusFinished
Effective start/end date01/08/2131/07/22

Keywords

  • Image caption
  • Object detection
  • Color analysis
  • Edge Computing

Fingerprint

Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.