Research
Generally speaking, I am interested in many aspects of visual computing and robotic vision algorithms, systems, and applications. They include: 1) Sensory data preprocessing, 2) Vision and visual content analytics, 3) Video and meta data representation and coding, 4) Graphics and human-computer interaction, and 5) Video communication, interactive multimedia systems/applications. The general research methodology and novelty often exhibit themselves as follows:
Develop solid basic theory as well as innovative computational tools to process, represent, and interpret (often non-ideal) raw sensory data efficiently and effectively;
Take a holistic and integrative approach to solving sets of problems that are typically solved in isolation and also in a conventional manner;
Conduct application-driven, use-inspired system design and optimization by leveraging multi-disciplinary expertise
My current research directions are centered around the following major themes, which are further illustrated in the figure below:
Using commodity sensing and computing hardware to create exciting consumer-level visual computing applications, and transforming the ways people interact with and manipulate various visual media
Exploiting large-scale structured capturing data and dynamic Internet media or community images/videos to create compelling cloud-based navigation, visual analytics and visualisation services
Robotic vision for autonomous aerial/ground vehicles, wearable visual sensors, and augmented reality (AR), where geometric reconstruction meets semantic recognition for 3D holistic vision [My recent talk slides on "Computer Vision for Autonomous Systems: A VMA Perspective"]
My recent areas of interests and contributions include (and the scope is just ever-expanding):
ADSC core project links, news, and demos