Machine-Vision-Based Servo Control of a Robotic Sewing System

摘要

This paper proposes a machine-vision-based servo-controlled robotic sewing system. This vision-based robotic sewing system can sew automatically and requires much less manpower than a traditional industrial sewing machine. The robotic sewing system consists of a charge-coupled device camera, a conveyor stage, and a sewing machine. To begin the sewing process, the conveyor stage transfers the fabric or material to the CCD field and guides the fabric to the sewing zone using visual servoing feedback. The Harris corner detection algorithm is then implemented to identify corners in the CCD images. Finally, the stitching entry point and sewing vertex are chosen automatically according to the characteristics of the corner points. The visual servo-controlled sewing system can perform the sewing process correctly and compensate for the dynamic movement of the fabric in real time. The experimental results demonstrate that the proposed system can help to reduce operator fatigue and to achieve high-quality sewing results.