Skip to main content
MSU CSE Colloquium Series 2016-2017: Dr. Sharathchandra Pankanti
Learning and Recognizing Archeological Features from LiDAR Data

Dr. Sharathchandra Pankanti
Manager, Exploratory Computer Vision Group
IBM T.J. Watson Research Center
Personal Website

Time: Friday, April 7, 2017, 11 AM - 12 PM
Location: EB 3105

New remote sensing techniques such as light detection and ranging (LiDAR) are revolutionizing many industries and fields, among them the one of archaeology by providing rapid, high resolution scans of topography which might indicate the existence of ancient cities and landscapes. The problem is that, given the cost and labor intensive nature of traditional methods, archaeologists cannot effectively analyze these datasets -- simply because it is too big. Via field-work and manual mapping, the archaeologists exploit their domain knowledge to recognize human artifacts and classify them as houses, temples, walls, streets, and other elements of past settlements. In this talk, we will describe how artificial intelligence techniques can be used to "scale" the archeologists' work. Using LiDAR data from the ancient Purepecha city of Angamuco in Mexico, we exploit domain knowledge to learn and recognize promising ancient artifacts in the city (such as houses). This allows us identifying more effectively areas of interest to the archeologists and to automatically classify and localize ancient human-made artifacts. Although, for now, this work is discussed in terms of recognizing houses, the performance and accuracy of the methods described show potential in demonstrating how machine learnt models can expedite scientific investigation from unstructured data. Joint work with Prof. Chris Fisher (Colorado State University) and Florencia Pezzutti (Colorado State University), Conrad Albrecht (IBM Research), Marcus Frietag (IBM Research), Francesca Rossi (IBM Research).

Sharath Pankanti is a Principal Research Staff Member in Cognitive Computing Department at the Thomas J. Watson Research Center. He received Ph.D. degree in Computer Science from the Michigan State University. Sharath has led a number of safety, productivity, education, healthcare, and security focused projects involving biometrics, multi-sensor surveillance, rail-safety, driver assistance technologies that entail object/event modeling, detection and recognition from information provided by static and moving sensors/cameras. Results of many of these efforts have demonstrated competitive results in scientific evaluations (NIST TRECVID-2012, 2013 and 2014, ImageClef 2013) and been integrated into real world applications. His work contributed to world's first large scale biometric civilian fingerprint identification system in Peru and to award-winning IBM surveillance offering that have been featured in news media (ABC3/Fox/CBS/NBC), mentioned in popular TV media (CSI:Miami) and covered in social ( media. He is a co-author of over 150 peer-reviewed publications (over 20,000 citations with an h-index of 49 according to Google Scholar) and co-inventor of more than 100 inventions. He is Fellow of IEEE, IAPR, and SPIE.

Dr. Anil Jain