Analyzing Images Over Time

Understanding time-varying processes and phenomena is fundamental to science and engineering. Due to tremendous progress in digital photography, images and videos (including images from webcams, timelapse photography captured by scientists, surveillance videos, and Internet photo collections) are becoming an important source of information about our dynamic world. However, techniques for automated understanding and visualization of time-varying processes from images or videos are scarce and underdeveloped, requiring fundamental new models and algorithms for representing changes over time.

The goal of this project is to create complete end-to-end systems that enable modeling, analysis, and visualization of time-varying processes based on image data. These will include both general systems applicable to arbitrary time-varying image sequences and more constrained systems targeted for specific types of data, such as outdoor multi-view time-lapse photography. These models and algorithms will form the basis for a new set of tools that can help answer important questions about how our environment is changing, how our cities are evolving, and what significant events are happening around the world.

Team members: Deqing Sun, James Tompkin, Hanspeter Pfister