Abstract: Despite considerable progress in all aspects of machine perception, using machine vision in autonomous systems remains a formidable challenge. This is especially true in applications such as robotics, in which even a small error rate in the perception system can have catastrophic consequences for the overall system.
This talk will review a few ideas that could be used to start formalizing the research issues involved in developing robust vision systems. These include a systematic approach to the problem of self-assessment of vision algorithms and predicting quality metrics on the inputs to the vision algorithms, ideas on how to manage multiple hypotheses generated from a vision algorithm rather than relying on a single "hard" decision, learning perception from few examples and from unsupervised data, and transfer learning for rapid adaptation to new environments and tasks. These ideas will be illustrated with examples of recent vision for scene understanding, depth estimation, and object recognition, and with applications to autonomous air and ground robots.
Bio: Martial Hebert is a Professor of Robotics Carnegie Mellon University and Director of the Robotics Institute, which he joined in 1984. His interests include computer vision, especially recognition in images and video data, model building and object recognition from 3D data, and perception for autonomous robots. His group has developed approaches for object recognition and scene analysis in images, 3D point clouds, and video sequences, with application to ground and air robots.
He has served on the editorial boards of the IEEE Transactions on Robotics and Automation, the IEEE Transactions on Pattern Analysis and Machine Intelligence, and the International Journal of Computer Vision (for which he currently serves as Editor-in-Chief).