Advances in sensing technology have enabled organizations to collect real-time spatio-temporal data from multiple sensors for various applications. In this project, we propose to develop techniques for detecting and locating surrounding vehicles from multiple scans generated by LIDAR sensors (Ibeo and Velodyne) installed on a moving vehicle. Specifically, we consider the spatio-temporal data from each sensor as providing a separate view for the detection task and develop techniques for fusing data from multiple sensors to improve the overall detection accuracy. We present preliminary evidence demonstrating the limitations of using data from a single source in the vehicle detection problem. We then propose a multi-view learning framework to effectively combine the data from different sensors.
Crowdsourcing of Network DataNeural Networks (IJCNN), 2016 International Joint Conference on, 2016Status of the Beam Dynamics Code DynacProceedings of LINAC 2012, 2012Highly Oriented Carbon Nanotube Papers made of Aligned Carbon NanotubesNanotechnology, 2008Directed subgroup graph for studying the subgroup properties of finite groupsJournal of Tsinghua University (Science and Technology), 2008
Patents in USA (Application No.)
Patents in China (Mainland Application No.)
Patents in China (TaiWan Application No.)