This is a past event.

Assistant Professor, Electrical and Computer Engineering, Mississippi State University 

Fusion here, there and almost everywhere in computer vision - driving new advances in fuzzy integrals

Abstract: Computer vision is a well-known area where computational intelligence has made a significant impact. In general, the field is diverse and objectives include filtering, object detection, image/scene understanding and linguistic summarization/description (signal-to-text), to name a few. As simple as it may sound, we have been trying to make a computer “describe what it saw” since the 1960s. In an attempt to achieve this goal, researchers look to data/information fusion. However, most aggregation strategies are additive and assume independence between inputs. On the other hand, fuzzy measure theory provides a powerful parametric way to specify or learn input interactions (when/if available). More importantly, the fuzzy integral utilizes the fuzzy measure to achieve nonlinear aggregation. In this talk, I discuss the role of efficient and effective nonlinear aggregation via fuzzy integrals at the levels of signal, spectrum, feature, and decision-level in computer vision. Specifically, I focus on a few of our recently established extensions for spatial or distribution uncertainty. Applications are discussed for multi-sensor humanitarian demining, hyperspectral image analysis and remote sensing.
 
Biography:  Derek T. Anderson received his PhD in Electrical and Computer Engineering (ECE) from the University of Missouri in 2010. He is an Assistant Professor in ECE at Mississippi State University (MSU). Prof. Anderson also holds an Intermittent Faculty Appointment with the U.S. Naval Research Laboratory, he is an IEEE Senior Member and Associate Editor for the IEEE Trans. on Fuzzy Systems. His research interests include new frontiers in data/information fusion for pattern recognition and automated decision making in signal/image understanding and computer vision with an emphasis on uncertainty and heterogeneity. Prof. Anderson’s primary research contributions to date include multi-source (meaning sensor, algorithm and human) fusion, Choquet integrals (extensions, embedding’s, learning), signal/image feature learning, multi-kernel learning, cluster validation, hyperspectral image understanding and linguistic summarization of video. He has been funded by the U.S. Air Force Research Laboratory (AFRL), Camgian, U.S. Army and Night Vision and Electronics Sensors Directorate (NVESD), U.S. Army Engineering Research and Development Center (ERDC), Pacific Northwest National Laboratory (PNNL), the National Institute of Justice (NIJ), and DARPA. Prof. Anderson is also the co-Director of the Sensor Analysis and Intelligence Laboratory (SAIL) in the Center for Advanced Vehicular Systems (CAVS) at MSU, a multi-disciplinary collaborative research laboratory with sensors ranging from hyperspectral in the visible and near, mid and long infrared to radar, lidar, stereoscopic, and light field cameras. SAIL is focused on fusion and scene/environment understanding in the areas of robotics, autonomous systems and ground/aerial vehicles, and remote sensing from UAVs for agriculture and biological earth observations. Derek has published over 90 articles; book chapters, journal manuscripts and conference proceedings. More details can be found at: http://www.derektanderson.com.