Michael Felsberg

Papers

Total Citations

H-Index

About

Michael Felsberg is a leading figure in computer vision and machine learning, best known for his pioneering work in visual tracking, image analysis, and robust feature learning. His research has fundamentally advanced how machines interpret dynamic visual data, with a particular focus on correlation filter-based tracking—a technique that has become a cornerstone in real-time object tracking systems. Felsberg’s contributions include the development of the Channel and Spatial Reliability Tracking (CSRT) algorithm, which significantly improved tracking accuracy under challenging conditions like occlusion and deformation. His work has garnered substantial impact, with his most-cited papers collectively accumulating over 10,000 citations, reflecting their influence across both academia and industry. Notably, his research on "Discriminative Scale Space Tracking" and "ECO: Efficient Convolution Operators for Tracking" has set new benchmarks in the field. Felsberg also co-authored the widely used "Computer Analysis of Images and Patterns" (2017), a key resource for practitioners. As a professor at Linköping University, he continues to shape the next generation of vision researchers, bridging theoretical advances with practical applications in robotics, surveillance, and autonomous systems.