Category Level Object Discovery using Dynamic Topic Model

摘要：

　　Category level object discovery is important for a number of applications such as remote sensing image classification, and data mining in images and video sequences.This paper presents a novel unsupervised learning algorithm for discovering object category and their locations in video sequences.Both appearance consistency and motion consistency of local patches across frames are exploited.Video patches are first extracted and represented by spatial-temporal context words.A dynamic topic model is then introduced to learn object categories in video sequences.The proposed dynamic model can categorize and localize multiple objects in a single video.Experimental results on the CamVid dataset and the VISATTM dataset demonstrate the effectiveness of our method.

关键词： spatial-temporal context word unsupervised learning dynamic topic model

作者: Guo Jun Sun Hao Zhu Chang-ren

作者单位: School of Electronic Science and Engineering,National University of Defense Technology,Changsha 410073,China

会议类型: 国际会议

会议名称: the 3nd International Conference on Digital Manufacturing & Automation (第三届数字制造与自动化国际会议(ICDMA 2012))

会议地点: 桂林

会议语种:英文

页码: 944-948

在线出版日期: 2012-08-01（万方平台首次上网日期，不代表论文的发表时间）