Pedram Ghamisi

University of Iceland, Austrian Research Institute for Artificial Intelligence

Papers

Total Citations

150

H-Index

About

Pedram Ghamisi is a leading researcher at the intersection of evolutionary computation and 3D computer vision. His primary contributions lie in advancing swarm intelligence algorithms, particularly through the development of Fractional Order Darwinian Particle Swarm Optimization (FODPSO). This innovative approach, detailed in his highly cited 2015 paper (89 citations) and accompanying book (29 citations), applies fractional calculus to enhance the exploration and exploitation capabilities of traditional PSO, with demonstrated applications in curve fitting, image segmentation, and swarm robotics. Ghamisi’s work has fundamentally improved how autonomous systems optimize complex, multi-modal problems. In the realm of 3D reconstruction, he has made significant strides with his 2022 study on Normal Assisted Pixel-Visibility Learning with Cost Aggregation for Multiview Stereo (30 citations). This research directly addresses the challenge of accurate depth estimation in low-texture environments, a critical bottleneck for autonomous driving and robotic navigation. By enabling more robust 3D scene reconstruction, Ghamisi’s work is paving the way for more reliable unstructured environment mapping and visual-inertial navigation systems, solidifying his impact on both theoretical optimization and practical robotic perception.