Salim Zabir

Papers

Total Citations

H-Index

About

Salim Zabir’s research focuses on the intersection of computer vision and assistive robotics, with a particular emphasis on elderly care and fall detection systems. His most cited work, “Lying Pose Recognition for Elderly Fall Detection” (2011), introduced a novel pipeline that enables healthcare robots to identify fallen individuals from single images. The approach combines viewpoint-specific part-based model detectors to locate bounding boxes, followed by detailed estimation of body part configurations—a critical step for distinguishing between intentional lying and dangerous falls. This foundational paper has garnered 30 citations, reflecting its influence on vision-based safety monitoring. Zabir extended this work in a 2012 follow-up, refining the recognition pipeline for greater robustness. His contributions are particularly notable for addressing the real-world challenges of deploying autonomous systems in elderly care settings, where timely and accurate fall detection can prevent serious injuries. By bridging object detection with pose estimation, Zabir’s research provides a practical framework for enhancing the responsiveness and reliability of assistive robots, making him a key figure in the development of intelligent, human-centered healthcare technologies.