An Efficient Video Object Segmentation Based on Mask Pre-Filling Algorithm

淡江大學機構典藏 > 工學院 > 電機工程學系暨研究所 > 會議論文 > Item 987654321/96046

請使用永久網址來引用或連結此文件: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/96046

題名:	An Efficient Video Object Segmentation Based on Mask Pre-Filling Algorithm
作者:	Chang, Chih-Yueh;Chiang, Jen-Shiun;Ye, Fun;Hsia, Chih-Hsien
貢獻者:	淡江大學電機工程學系
關鍵詞:	Edge detection;Mathematical morphology;Video object segmentation
日期:	2007-03
上傳時間:	2014-02-13 11:38:49 (UTC+8)
摘要:	In this paper, we propose a new video object segmentation algorithm using the morphologi-cal technique. Several video object segmenta-tion algorithms used mathematical morphology to generate the object masks, but operations of mathematical morphology have two drawbacks: (1) high computation load, and (2) the quality of masks depends on the chosen morphological structuring element. There are many techniques to speed up the morphological operations by hardware implementation, but no discussions about reducing the influence of the choice of structuring elements. By adding a pre-processing mechanism, we effectively reduce the influences of the chosen structuring elements based on continuity of shape features and times of morphological operations. Experimental re-sults indicate that our algorithm can improve the speed of filling operations of the object masks and accuracy of segmentation.
關聯:	第五屆現代通訊科技應用學術研討會論文集=Proceedings of the 5th Conference on Communication Application，4頁
顯示於類別:	[電機工程學系暨研究所] 會議論文

文件中的檔案:

檔案	大小	格式	瀏覽次數
An Efficient Video Object Segmentation Based on Mask Pre-Filling Algorithm_英文摘要.docx	16Kb	Microsoft Word	126	檢視/開啟

在機構典藏中所有的資料項目都受到原著作權保護.

TAIR相關文章