邊緣運算攝影機原型開發;Edge computing camera prototype development

NCUIR > Engineering College > Graduate Institute of Mechanical Engineering > Electronic Thesis & Dissertation > Item 987654321/90130

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/90130

Title:	邊緣運算攝影機原型開發;Edge computing camera prototype development
Authors:	林志陽;Lin, Zhih-Yang
Contributors:	機械工程學系
Keywords:	JPEG壓縮;FFT轉換;攝影機;JPEG;FFT;camera
Date:	2022-07-21
Issue Date:	2022-10-04 12:11:51 (UTC+8)
Publisher:	國立中央大學
Abstract:	本研究的目的為在攝影機上實現邊緣運算，在攝影機上加裝一顆(Micro Control Unit, MCU)，在拍攝後立即對相片進行數位影像處理，將相片壓縮，而數據減量後的相片能夠比原本的相片節省更多的傳輸時間。本論文會利用降解析、JPEG壓縮、單色化、縱向橫向積分和快速傅立葉轉換減少相片的資料量，使得高解析的攝影機能夠使用在小型機器人或是大型系統上可以減少後級運算的負擔，讓機器人的控制能夠更為及時。最後透過JPEG壓縮驗證實驗的可行性，只要相片的解析度大於64 * 64，壓縮加上傳輸JPEG檔案就可以比傳輸原始相片更加的快速，而且解析度越大效果越好。 ;In this research, we focus on development of Edge computing on camera. Adding a MCU on the camera, so we can execute digital image processing to the photo immediately after taking photo. After compressing the photo, it can save more time than the photo without compressed. We use downsampling, JPEG compression, monochromatization, horizontal and vertical integration, and FFT to decrease the quantity of the photo. Thus, the higher resolution camera can use on small robot or big system and it can reduce the burden in the system. It will make the robot control timely. In the end of paper, we verify the performance of the JPEG compression. If the resolution of photo if bigger than 64 * 64, it can transfer faster than raw picture. When the photo has higher resolution, it’s performance will be better.
Appears in Collections:	[Graduate Institute of Mechanical Engineering] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	37	View/Open

社群 sharing

Loading...