Automated Harnessing of Complex Distributed Attributes for Robust Object Recognition

Robotics and Automation Society – 6:00PM, 10 February

Automated Harnessing of Complex Distributed Attributes for Robust Object Recognition, Presented by Robert McConnell

Tuesday, February 10, 2015

Doors open: 6:00 P.M – Presentation: 6:30 P.M. – Dinner: 8:00 P.M.

Olin College, 1000 Olin Way, Needham, MA 02492, Milas Hall Auditorium

Classification, verification and anomaly detection are often key components of robotics and automation projects.

Most of us are comfortable automating such recognition decisions based on properties that can be adequately represented by a simple mean value and Gaussian distribution. Dimensions of simple shapes, areas and weights usually fall into this category.

Unfortunately, sometimes the distinguishing information provided is more complex, and the simple models are unjustified. Yet, all too often, the methods suitable for those simple models are still applied. This commonly results in less than satisfactory outcomes and complexity tends to be regarded as an obstacle to reliable results. Such should not be the case.

Attribute complexity offers the advantages of increased potential to distinguish classes, redundancy to increase reliability, and robustness. This complexity appears in many forms and in most properties that can be sensed including, but not limited to, touch, sound and visual attributes. Color-based recognition provides a good example because it’s easy to visualize and, in the field of machine vision, institutionally misunderstood.

The presentation will demonstrate the advantages of complex attribute distributions for recognition and segmentation. Using examples from color, multispectral and hyperspectral imagery it will first show the basics of a general integrated approach to classification, verification and anomaly detection based on such attributes and then describe a new, closely related, method for selection of an optimum subset of the available attributes.

SPEAKER’S BIOGRAPHY

Robert McConnell

Robert McConnell received a B.S.E from Princeton University, M.A.Sc. and Ph.D. from the University of Toronto. Past positions include Director of Research, Wayland Research, Inc.; technical staff, Arthur D. Little, Inc.; Visiting Professor, University of Rhode Island Graduate School of Oceanography and President, Earth Sciences Research Inc.

Current professional interests focus on statistical pattern recognition methods for color, hyperspectral, and other images. They include development of WAY-2C a color machine vision software system for inspection and process control, used in such industries as automotive, food, recycling, wood products, and high level nuclear waste disposal.

He is the author of over 35 professional papers, and two comprehensive pattern recognition patents. Memberships include AIA, SME, SPIE and ASPRS. He occasionally helps out on the steering committee of the Boston Chapter of the IEEE-R&AS.

UNHOSTED DINNER

Bertucci’s, 1257 Highland Ave., Needham, MA 02492

Have more questions? Want to share a drink with the speaker? Want to network with fellow engineers and professionals? Just want to chat about the current goings-on in Robotics, or technology in general? Join us for dinner, where you can talk about Robotics in a more casual setting!

GENERAL INFORMATION

This and other RAS meetings are open to the general public. For more information about the RAS Boston Chapter, contact Chapter Chair Ryan Pettigrew at chair@robotics-boston.org or visit http://www.robotics-boston.org/.