Aiming at the automation measurement problem of aircraft skin seam gaps and step differences, a skin seam autonomous tracking method is studied based on line structured light visual detection technology. By combining traditional image morphology based processing methods with optical flow methods, real-time tracking of skin seam features is achieved, thereby determining the measurement positions of gaps and step differences. The accuracy of seam tracking was improved by correcting the eye-in-hand calibration parameters based on measured data. The experimental results show that when the tracking speed is 7 mm/s, the position accuracy of seam tracking is higher than 0.500 mm, and the attitude accuracy of seam tracking is higher than 0.5°. This tracking system has good accuracy and stability and can meet the requirements of aircraft skin seam tracking.