Veena Sharma
Papers
1
Total Citations
19
H-Index
1
About
Veena Sharma is a computer vision researcher whose work centers on motion detection and background subtraction, with a particular emphasis on real-time surveillance applications. Her most cited paper, “Foreground detection of moving object using Gaussian mixture model” (2017, 19 citations), tackles a fundamental challenge in the field: accurately segmenting moving objects from static backgrounds in dynamic environments. Sharma’s contribution lies in refining the Gaussian Mixture Model (GMM) for robust foreground detection, addressing issues like illumination changes and repetitive motion that often confound simpler methods. This work has direct implications for traffic monitoring, autonomous navigation, and medical imaging, where reliable object segmentation is critical. While her citation count reflects a focused, early-career impact, the paper’s practical relevance to computer vision pipelines—from surveillance systems to robot vision—demonstrates her ability to solve persistent, industry-relevant problems. Sharma’s research bridges theoretical modeling and applied engineering, offering a scalable solution for real-time scene analysis. For students and researchers exploring background subtraction techniques, her work provides a clear, implementation-focused entry point into one of vision’s foundational tasks.
Research Focus
Key Achievements
Top Papers
- 1Foreground detection of moving object using Gaussian mixture model19 citations · 2017