Detecting Pedestrians Using Patterns of Motion and Appearance
Speaker: Michael Jones , Mitsubishi Electric Research Laboratories (MERL)
Date: February 4 2004
Location: Room E25-401
Contact: Mary Pat Fitzgerald, 617-253-0551, firstname.lastname@example.org
I will describe a pedestrian detection system that integrates image intensity information with motion information. We use a detection style algorithm that scans a detector over two consecutive frames of a video sequence. The detector is trained (using AdaBoost) to take advantage of both motion and appearance information to detect a walking person. Past approaches have built detectors based on motion information or detectors based on appearance information, but ours is the first to combine both sources of information in a single detector. The implementation described runs at about 4 frames/second, detects pedestrians at very small scales (as small as 20x15 pixels), and has a very low false positive rate. Our approach builds on the previous detection work of Viola and Jones. Novel contributions include: i) development of a representation of image motion which is extremely efficient, and ii) implementation of a state of the art pedestrian detection system which operates on low resolution images under difficult conditions (such as rain and snow.
Mike Jones received his Ph.D. from MIT under the supervision of Prof. Tomaso Poggio in 1997. His thesis work introduced the idea of morphable models for modeling object classes which is now widely used in computer vision. After MIT, Mike joined the vision group at DEC's Cambridge Research Lab where he focused on skin and face detection. Together with Paul Viola, he developed the fast face detection framework that has recently become popular. Mike moved to the Mitsubishi Electric Research Lab in October 2001 where he continues to focus on various problems in object detection with emphasis on detecting and recognizing people.
See other events that are part of Brains & Machines Seminar Series Spring 2004
See other events happening in February 2004