Domonkos Varga

Hungarian Academy of Sciences, Institute for Computer Science and Control

Papers

Total Citations

H-Index

About

Domonkos Varga is a computer vision researcher whose work centers on pedestrian detection, a critical task for applications in surveillance, robotics, and autonomous driving. His early research focused on developing robust, real-time detection methods for surveillance videos, introducing innovative feature extraction techniques such as the Center-Symmetric Local Binary Pattern (CS-LBP) to improve accuracy under challenging conditions. Varga’s most cited paper, "Robust real-time pedestrian detection in surveillance videos" (2016), has accumulated 23 citations, demonstrating its influence in the field. He further advanced the state of the art by integrating convolutional neural networks with motion cues to address persistent challenges like variations in illumination, scale, and pose. Through his work, Varga has contributed to making pedestrian detection more reliable and efficient, directly impacting the safety and functionality of autonomous systems and video analytics. His research remains a valuable reference for scholars and engineers working on object detection and intelligent surveillance technologies.