Andrew Kalukin | Remote Sensing | Best Researcher Award
Dr. Andrew Kalukin, Through Sensing LLC, United States.
Dr. Andrew Kalukin π is a leading expert in computer vision π€, artificial intelligence π‘, remote sensing π°οΈ, and signal processing π‘. With over two decades of experience across industry and government R&D sectors, he has developed pioneering techniques in machine learning training data simulation, automated target detection, and multimodal data fusion. Currently, he serves as a SAR Scientist at Barone Consulting and Founder of Through Sensing, LLC π. His interdisciplinary work combines AI, radar systems, atmospheric modeling, and computer vision, earning recognition through patents, publications, and collaborations with government, academia, and industry. π§ π¬π
Publication Profiles
Β Education & ExperienceΒ
π Education
-
π§ͺ Ph.D. in Physics β Rensselaer Polytechnic Institute
-
π» M.S. in Computer Science β Rensselaer Polytechnic Institute
-
π¨βπ» B.S. in Computer Science β Central Connecticut State University
-
π§ B.A. in Psychology β University of Dallas
πΌ Experience
-
π°οΈ SAR Scientist, Barone Consulting (2024βPresent)
-
π Founder, Through Sensing, LLC (2023βPresent)
-
π§ Senior Lead Scientist, Booz Allen Hamilton (2014β2023)
-
π Senior Image Scientist, BAE Systems (2005β2014)
-
π Staff Scientist, AretΓ© Associates (2002β2005)
-
π· Image Scientist, Eastman Kodak (2000β2002)
-
π‘οΈ Target Recognition Engineer, SAIC (1999β2000)
-
𧬠Research Associate, NIST/Rensselaer (1995β1999)
Suitability for the Award
Dr. Andrew Kalukin, a seasoned expert in computer vision, artificial intelligence, remote sensing, and data fusion, is an exemplary nominee for the Best Researcher Award. With over 25 years of pioneering contributions across government, industry, and academia, Dr. Kalukinβs research has profoundly influenced applications in defense, environmental monitoring, autonomous systems, and semantic understanding through multi-modal AI.
Β Professional Development
Dr. Kalukin has consistently advanced the frontiers of automated image analysis, presenting at SPIE and IEEE AIPR conferences π€π. He has co-chaired IEEE AIPR and led collaborative projects involving CubeSats π°οΈ, polarimetric radar, and atmospheric simulation for AI detection systems. His efforts have resulted in successful partnerships with academic institutions, government labs, and industry innovators π€. Through both individual research and managing scientific teams, heβs contributed to strategic defense technologies and geospatial intelligence applications. His consulting and entrepreneurship continue to shape future AI-enabled sensing systems. πΌπ¬π
Β Research FocusΒ
Andrew Kalukin’s research is centered on Artificial Intelligence for Remote Sensing Applications ππ€. His work spans machine learning model development, image and video analysis, semantic segmentation, and signal processing using multispectral, radar, and hyperspectral data π°οΈπ§ . Heβs developed AI models for autonomous navigation, wildfire detection, and global deforestation mapping. His interdisciplinary methods combine physics-based modeling with advanced neural networks, enabling AI applications in both defense and environmental monitoring π³π₯. Through simulation, automation, and ontology-based learning, Kalukin is contributing to the evolution of real-world AI for edge platforms like drones and CubeSats ππ§©.
Β Awards & HonorsΒ
-
π§ Patented novel AI-based ontology transformation for multimodal data
-
π Lead Principal Investigator for U.S. Army Phase I AI research project
-
π°οΈ Received AWS Cloud Credit awards for wildfire and deforestation AI research
-
π Multiple IEEE AIPR and SPIE presentations and invited talks
-
π¬ Recognized for generating novel machine learning training datasets simulating real atmospheric and sensor conditions
-
π‘ Developed patented techniques used in satellite and defense AI systems
Publication Top Noted
-
Applications of Deep Learning Neural Networks for Clustering Mesoamerican Historical Art Objects and Documents β 2023 π¨
-
Coβdomain transformation to represent abstract information for machine learning in visual scenes β 2022 π§
-
Modeling and assessing VNIIRS using inβscene metrics β 2019 π°οΈ
-
Automating video interpretability assessment through automatic target recognition β 2018 πΉ
-
Motion image data collection simulation for structureβfromβmotion 3D target reconstruction β 2018 π
-
Automated generation of convolutional neural network training data using video sources β 2017 π€
-
Automated mensuration of inβscene targets for video quality assessment β 2016 π
-
Automated video quality measurement based on manmade object characterization and motion detection β 2016 π§