Rahul Dutt Sharma
Papers
1
Total Citations
17
H-Index
1
About
Rahul Dutt Sharma is a computer vision researcher whose work focuses on advancing moving object detection and tracking for real-world applications in video surveillance and robotics. His most-cited paper, "Optimized dynamic background subtraction technique for moving object detection and tracking" (2017, 17 citations), addresses a fundamental challenge in the field: accurately isolating moving objects from complex, changing backgrounds. Sharma demonstrated that three-frame differencing significantly outperforms traditional two-frame methods by reducing the problem of "holes" in detected objects, while his dynamic background detection technique proved far more robust than static approaches. This work has practical implications for human-computer interaction and automated monitoring systems. By optimizing background subtraction—a core preprocessing step in video analytics—Sharma has contributed to making object tracking more reliable in real-world conditions where lighting, weather, and scene changes occur. His research bridges the gap between theoretical computer vision algorithms and deployable systems, offering solutions that balance computational efficiency with detection accuracy. For students and researchers exploring video analysis, Sharma's work provides a clear example of how incremental improvements to foundational techniques can yield significant practical benefits.
Research Focus
Key Achievements
Top Papers
- 1