Semantic Segmentation Using Regions in Natural Scenes

CORC > 沈阳自动化研究所 > 中国科学院沈阳自动化研究所 > 光电信息技术研究室

	Semantic Segmentation Using Regions in Natural Scenes
	Wu SL(吴士林); Zhu F(朱枫); Hao YM(郝颖明)
	2011
会议名称	2011 International Conference on Electronic & Mechanical Engineering and Information Technology (EMEIT 2011)
会议日期	August 12-14, 2011
会议地点	Harbin
页码	1884-1887
中文摘要	By introducing an over-segmentation algorithm into the conditional model (CM), we propose a new region-based CM model (R-CM), and investigate its performance on semantic segmentation of images. In order to incorporate structure information of objects, we segment an image into regions by using an over-segmentation algorithm. Based on the results of CM model, we first consider assigning all pixels in one region with the same label, and then other feature potentials are included to counteract the influence of false over-segmentation. We compare our results to related work on the Olive & Torralba database and show that aside from improved accuracy of the whole database, our model obtains a perceptual improvement, with boundary of different objects correctly labeled.
收录类别	EI
产权排序	1
会议主办者	IEEE Harbin Sect.
会议录	2011 International Conference on Electronic & Mechanical Engineering and Information Technology (EMEIT 2011)
会议录出版者	IEEE
会议录出版地	Piscataway, NJ, USA
语种	英语
ISBN号	978-1-61284-087-1
内容类型	会议论文
源URL	[http://ir.sia.cn/handle/173321/8021]
专题	沈阳自动化研究所_光电信息技术研究室
推荐引用方式 GB/T 7714	Wu SL,Zhu F,Hao YM. Semantic Segmentation Using Regions in Natural Scenes[C]. 见:2011 International Conference on Electronic & Mechanical Engineering and Information Technology (EMEIT 2011). Harbin. August 12-14, 2011.