DocumentCode :
2050680
Title :
Research on wireless video encoding algorithm for underground based on background registration and motion segmentation
Author :
Tian Hongxian ; Yang Wei
Author_Institution :
State Key Lab. of Rail Traffic Control & Safety, Beijing Jiaotong Univ., Beijing, China
fYear :
2011
fDate :
27-30 Nov. 2011
Firstpage :
229
Lastpage :
233
Abstract :
Regarding to the specialty that the background picture keeps unchangeable with perspective motion objects varying for wireless video monitoring of underground mines, the motion segmentation encoding based on background registration algorithm is brought forward in this article. In this motion segmentation algorithm, each frame for wireless underground video encoding is segmented by motion objects and background, then, they are processed and transmitted according to separated algorithm regulations. Furthermore, because of low illumination and image blurring, the image enhanced algorithm is integrated into the encoding process to enhance the main motion objects to improve the subject quality. At last, the real time transmitted motion object and local saved background image is integrated together to show on the terminal monitoring screen. By this algorithm, the complexity of video encoding and code rate is reduced with high definition video sequences.
Keywords :
image enhancement; image motion analysis; image segmentation; image sequences; mining; radio applications; video coding; background registration algorithm; high definition video sequences; image blurring; image enhanced algorithm; local saved background image; low illumination; motion segmentation encoding; perspective motion objects; real time transmitted motion object; terminal monitoring screen; underground mines; wireless video encoding algorithm; background registration; mine Underground; motion segmentation; video Encoding;
fLanguage :
English
Publisher :
iet
Conference_Titel :
Wireless, Mobile & Multimedia Networks (ICWMMN 2011), 4th IET International Conference on
Conference_Location :
Beijing
Electronic_ISBN :
978-1-84919-507-2
Type :
conf
DOI :
10.1049/cp.2011.0995
Filename :
6197862
Link To Document :
بازگشت