Object Detection and Tracking

At AitoeLabs, I worked with a team of engineers to build efficient video analytics solutions for internal security. For ATM security, we developed deep learning models and algorithmic solutions operating on live video streams.
I was part of the object detection and tracking group, working on algorithms for detecting and tracking people in live video streams.

Object tracking assigns unique IDs to detected objects and enables their behavior to be monitored over time. We developed algorithms to identify potentially suspicious situations, such as groups exceeding the permitted number of people inside an ATM or individuals loitering for a prolonged duration. Detected events were used to alert security personnel or the responsible company.

Authors
Robotics Engineer & Researcher
Robotics engineer and researcher with 10+ years of experience specializing in robotics and computer vision.