Ghayur Naqvi
Papers
2
Total Citations
33
H-Index
2
About
Ghayur Naqvi’s research lies at the intersection of autonomous robotics and multi-object tracking, with a sharp focus on how we measure and evaluate estimation performance. His most notable contribution is the development of the Cardinalized Optimal Linear Assignment (COLA) metric, a rigorous framework for assessing multi-object error in both robotic mapping and target tracking. This work, alongside his earlier study on metrics for evaluating feature-based mapping performance, addresses a fundamental gap: how to automatically and meaningfully quantify the quality of estimated maps and trajectories when the number of objects is unknown or variable. His 2016 paper on feature-based mapping metrics has garnered 25 citations, reflecting its practical importance for researchers needing reliable benchmarks. Naqvi’s contributions are particularly valuable because they move beyond simple trajectory error to consider the full complexity of spatial estimation, including feature correspondence and cardinality mismatches. For students and researchers working on SLAM or multi-target tracking, his work provides the essential tools for rigorous, automated performance evaluation—a critical step for advancing robust autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1Metrics for Evaluating Feature-Based Mapping Performance25 citations · 2016
- 2