This technology is a system and method that maintains vision tracking accuracy for a target by detecting the real-time movement of a mobile robot's primary body via indoor GPS, using this as a feedforward signal, and inputting it into a controller along with feedback signals from a vision sensor to actively drive the secondary body, which serves as the camera mount.
Existing systems faced issues where the vision sensor would move along with the robot body during driving or vibration, causing the target to exit the recognition range or resulting in motion blur in the video signal, which degraded recognition rates and accuracy.
This technology proposes an active vision tracking system that acquires movement and rotation data of the primary body through indoor GPS triangulation and compensates by driving the secondary body in the opposite direction of the primary body's movement via a controller. By combining inertial sensors and encoders to correct motion detection errors, it achieves precise tracking. It can be applied to indoor surveillance robots, automated logistics equipment, and precision imaging devices, ensuring steady video tracking even while in motion through precise, indoor GPS-based compensation control.
This invention was developed with support from the Ministry of Knowledge Economy for the development of u-Robot HRI solutions and core component technologies.
N/A