Israel Mugunga

Papers

Total Citations

H-Index

About

Israel Mugunga is a computer vision researcher whose work focuses on the challenging problem of detecting and identifying transparent and translucent materials. His research addresses a critical gap in autonomous systems: enabling robots and AI to perceive materials like glass and plastic that are notoriously difficult for standard vision algorithms. Mugunga's most influential work, "Leveraging an Instance Segmentation Method for Detection of Transparent Materials" (2019, 11 citations), pioneered automatic detection of transmissive surfaces, with direct applications in domestic service robotics and industrial settings where fragile instruments must be handled without damage. He further advanced the field with "Transmittance Surface Detection and Material Identification Using Multitask ViT-SIFT Fusion" (2022, 8 citations), a novel approach combining Vision Transformers with traditional SIFT features for simultaneous transparency detection and material classification. This fusion technique represents a significant methodological contribution, bridging deep learning and classical computer vision. Mugunga's work has practical implications for robot navigation, automated manufacturing, and laboratory automation, where the ability to see through and identify transparent objects remains a fundamental challenge. His research continues to push the boundaries of what autonomous systems can perceive in complex, real-world environments.