Imaging Science Seminar: Open Geospatial Data Machine Learning
Imaging Science Seminar
Open Geospatial Data Machine Learning
Dr. Xin Chen
Head of Central US and Automotive Vertical
Amazon Machine Learning Solutions Lab
Dr. Chen will share his vision of a one-stop-shop on AWS where developers can easily access and contribute to the Open Data Registry. Developers will be able to leverage broad and deep machine learning services and tools to develop and deploy machine learning models. They will be able to use sample notebooks on AWS SageMaker using the open datasets regardless of machine learning background.
Abstract:
I will share my perspective on open data in the cloud, in particular open geospatial data, and present the Open Data Registry on AWS. The datasets range from genomics to climate to transportation information. They are well-structured and easily accessible but there is a lack of sample scripts/notebooks for users to leverage these datasets in machine learning development. I will share my vision of a one-stop-shop on AWS where developers can easily access and contribute to the Open Data Registry and can leverage AWS broad and deep machine learning services and tools to develop and deploy machine learning models with sample notebooks on AWS SageMaker using the open datasets regardless of machine learning background. As proof of concept I will present a case study developing notebooks to train and test deep learning models using AWS SageMaker to extract building footprints and road networks from city scale satellite imagery and LiDAR data in the Open Data Registry. The notebooks reproduce winning algorithms from the SpaceNet challenges. In addition to the SpaceNet satellite images, we compare and combine USGS 3D Elevation Program (3DEP) LiDAR data to extract the buildings and roads.
Speaker Bio:
Dr. Xin Chen is the Head of Central US and Automotive Vertical in Amazon Machine Learning Solutions Lab. He leads his team to help AWS customers identify and build machine learning solutions to address their organization’s highest return-on-investment machine learning opportunities. Prior to Amazon, Xin was a Director of Engineering at HERE Technologies whose team completed pioneering work to achieve the automation of next generation map creation using computer vision and machine learning technologies. Xin has 55 issued U.S. Patents and numerous publications at CVPR, CVIU, Proceedings of the IEEE, and IEEE Transactions on ITS. He has served on an NSF (National Science Foundation) panel multiple times to evaluate and award funding to multi-million dollar projects advancing AI research. Xin is an adjunct faculty at Northwestern U. and Illinois Institute of Technology teaching “Geospatial Vision and Visualization” and “Biometrics” courses. Xin obtained his Ph.D. in Computer Science and Engineering from the U. of Notre Dame.
Intended Audience:
Undergraduates, graduates, and experts. Those with interest in the topic.
Event Snapshot
When and Where
Who
Open to the Public
Interpreter Requested?
No