学术报告：Recent Developments in Motion Segmentation and Human Activity Recognition

报告内容：Motion segmentation in terms of dynamic textures, and human activity recognition are topics that have attracted growing attention in computer vision community. This talk is mainly concentrated on recent trends in dynamic texture segmentation, and human activity recognition. We first present two techniques for dynamic texture: a feature selection based dynamic mixture model for motion segmentation, and a linear-time video segmentation method which is scalable and temporally consistent for streaming videos. We then present a general framework to efficiently identify objects of interest in still images and later extend its application to human action recognition in videos. Such scheme can also be implemented in a situation where training data is coming in a serial mode and training needs to be performed in an incremental fashion. A brief overview of other related research activities in the presenter’s laboratory is also provided. Applications have been extended towards intelligent transportation systems, surveillance and security, face and gesture recognition, vision-guided robotics, and bio-medical imaging, among others.

报告人：武庆明（Q. M. Jonathan Wu） 教授，现任加拿大温莎大学电子工程系教授，博士生导师，计算机视觉和传感系统研究所主任，长期从事图像处理，模式识别与智能系统的教学与研究工作，先后主持完成加拿大国家科学与工程研究项目(NSERC)，国际合作重大项目、加拿大国家重点基金项目，加拿大汽车电子和信息系统领域首席科学家，至今共培养博士、博士后30 余人。现任国际杂志《IEEE Transaction on Neural Networks and Learning Systems》、《International Journal of Robotics and Automation》与《Cognitive Computation》副主编，《IEEE Computational Intelligence Magazine》客座编委。在过去的研究工作中，申请人对图像实时分割、图像压缩与特征提取、图像去噪与识别、三维重建等问题进行了深入研究，SCI 收录论文100 多篇，IEEE Transactions 论文40 余篇，在图像处理、智能信息处理、机器学习与模式识别领域，取得多项重大研究成果。

报告时间：2015年4月27日下午15：00

报告地点：千佛山校区4号教学楼（williamhill官网）三层报告厅