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 issues revolving around integrating vision systems. They 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, and methods for using external (non-visual) domain- and task-dependent information. These ideas will be illustrated with examples of recent vision for scene understanding, depth estimation, and object recognition.

Bio

Martial Hebert’s work is in the areas of computer vision and perception for autonomous systems. His interests are in the interpretation of perception data (both 2-D and 3-D), including building models of environments. Current research directions include:

• Efficient techniques for object/category recognition
• Use of contextual information, in particular 3-D geometry from images, for scene analysis
• Symbolic knowledge for scene interpretation and reconstruction
• Motion analysis for feature extraction and event detection in video clips
• Efficient tools for the analysis of dynamic 3-D point clouds ("3-D signal processing")
• Perception for autonomous systems
• Detection, tracking, and prediction in dynamic environments