Max Robotics — Global Service Robot Directory + US Certification

About

Miguel Farrajota’s research lies at the intersection of computer vision, biologically inspired perception, and human-robot interaction. His work focuses on developing real-time frameworks for pedestrian detection, hand gesture recognition, and head pose estimation—core components for enabling robots to understand and interact naturally with humans in dynamic environments. A major contribution is his biologically motivated approach to vision, drawing from the human visual system to create efficient, multi-scale feature extraction methods. His most cited paper, “Using Multi-Stage Features in Fast R-CNN for Pedestrian Detection” (2016, 5 citations), advances object detection by integrating hierarchical features, directly supporting applications in smart cities, surveillance, and telecare. Other notable works include frameworks for hand tracking and gesture recognition, as well as bio-inspired pedestrian detection and tracking using monocular moving cameras. Though his citation counts are modest, Farrajota’s work is foundational in bridging biological vision principles with real-time robotic systems, contributing to the development of social robots capable of safe, intuitive human interaction. His research remains relevant for students and engineers working on autonomous systems, assistive robotics, and intelligent surveillance.