Camera-Robot Calibration Method and Apparatus for Automatic Label Application

Camera-Robot Calibration Method for Automated Labeling

This technology is a camera-robot calibration algorithm that estimates the transformation matrix between the vision sensor's image coordinate system and the robot arm's world coordinate system, improving the precision of coordinate transformation through projection error calculation and updating processes.

Conventional manual calibration methods are time-consuming and prone to errors, as they require repetitive manual tasks to acquire hundreds of feature point pairs.

This technology estimates an initial transformation matrix through primary labeling and performs conditional automated secondary labeling and data association based on projection error, iteratively optimizing the transformation matrix with minimal manual intervention. It can be applied to robot gripping, precision measurement, and automated equipment, thereby improving the accuracy and efficiency of automated labeling systems by implementing a calibration method for precise coordinate estimation and transformation.

‍

‍

Key Features:

• A camera-robot calibration method for automated labeling, comprising the step of analyzing a received image to acquire first center coordinates of labels attached to a first number of objects among a plurality of objects, and first world coordinates for the first center coordinates.
• Based on conditions regarding the magnitude of a first projection error, the step of acquiring second-a center coordinates for a second number of objects among the plurality of objects, and acquiring second world coordinates for the second-a center coordinates using the estimated first transformation matrix.
• The step of analyzing an image received from a vision sensor regarding an attached label to estimate second-b center coordinates of the attached label in the image coordinate system.
• The step of automatically moving a robot arm to the estimated second world coordinates to attach a label to the object at that position.

‍

This invention was developed with support from the Ministry of Science and ICT for the development of a deep learning-based collaborative robot automated round bar labeling system with worker proximity detection.