资环论坛第73期特别邀请美国老道明大学 李江 副教授主讲,欢迎广大师生参加,具体安排如下:
时间:2018年5月21日(周一)上午10:30
地点:创新中心5楼A503
主讲人:美国老道明大学 李江 副教授
报告题目:Quantifying seagrass distribution in coastal water through deep capsule networks
报告内容:Seagrass is a highly valuable component of coastal ecosystems ecologically and economically, yet reliable mapping of seagrass density is not available due to the high cost of comprehensive labeling and quantification. In this talk, we present a deep learning approach for quantification of leaf area index (LAI) levels of seagrass in coastal water using high resolution multispectral satellite images. Specifically, a deep capsule network is developed for simultaneous classification and quantification of seagrass based on the multispectral images. The deep capsule network is jointly optimized for classification and regression and is capable of performing end-to-end seagrass quantification. We separately validated the proposed method on three images taken in Florida coastal area and achieved much better results in end-to-end seagrass quantification than those by a deep convolutional neural network (CNN) model. Our experimental results show that the developed capsule network achieved superb performances in few-shot transfer learning as compared to direct linear regression and traditional CNN models.
主讲人简介:李江,现任美国Old Dominion University(老道明大学)电子与计算机工程系副教授。李教授于1992年,2000年和2004年分别毕业于上海交通大学,清华大学和得克萨斯大学阿灵顿分校获得学士,硕士和博士学位。曾于2004年到2006年在美国国立卫生院(National Institutes of Health)从事博士后研究工作。2007年春季加入老道明大学,并于2012年获得终身教授职位。多个杂志的审稿人,Medical Physics客座编委,近5年H指数为12。