Vision Tracking System and Method Using Drive Commands

This technology is a vision tracking system that separates and controls a first body responsible for the mobile robot's movement and a second body equipped with a vision sensor. It calculates predicted movement information from the first body's drive commands and uses this to calibrate the orientation of the second body in real time.

Existing systems, where the mobile robot's drive unit and vision sensor are fixed to the same body, often suffer from reduced recognition rates and accuracy because the target can move out of the field of view or the image can become blurred during robot movement.

This technology proposes a method of generating control signals for the second body by combining predicted movement information derived from the first body's drive commands with actual movement information from sensors such as inertial sensors. It also utilizes image information as a feedback signal to measure disturbances and actively calibrate the orientation of the second body. It can be applied to mobile surveillance robots, camera drones, and autonomous vehicles, significantly improving image recognition accuracy by stably tracking targets even while in motion.

‍

‍

Key Features:

• Separated configuration of a first body for movement and a second body equipped with a vision sensor
• Configuration that calculates predicted movement information from the first body's drive commands
• Configuration that acquires actual movement information through sensors such as inertial sensors
• Control signal generator that calibrates the orientation of the second body by combining predicted and actual movement information