I'm a researcher in Computer Vision and Computer Science focusing on detection and tracking algorithms. My work involves developing and comparing state-of-the-art methods for detecting and tracking people in security camera footage.
I conducted significant research on video surveillance systems, specifically working on people counting systems using Python 3. My work has involved evaluating various detection algorithms including YOLO, SSD, and OpenPose, as well as multiple tracking algorithms implemented through OpenCV such as Boosting, MIL, KCF, TLD, Median Flow, MOSSE, and CSRT. I'm particularly interested in creating robust systems that minimize overcounting problems in surveillance applications.
My research aims to bridge the gap between traditional video surveillance and advanced data extraction methods. Through my work, I've developed systems that can achieve practical people counting with reasonable error rates, though I continue to work on improving accuracy in challenging scenarios like crowd detection and tracking.
Publications
Comparing state-of-the-art methods of detection and tracking people on security cameras video
Jairo Andres Torregrosa Olivero, Carolina María Burgos Anillo, Juan Pablo Guerrero Barrios, Estephanie Montoya Morales, Emma Julianan Gachancipá, Camilo Andrés Zamora de la Torre
2019 XXII Symposium on Image, Signal Processing and Artificial Vision (STSIVA) 2019