Cotton flow velocity measurement based on image cross-correlation and Kalman filtering algorithm for foreign fibre elimination

Abstract

Velocity estimation of cotton flow is usually used to improve the accuracy of foreign fibre elimination machines. A hybrid approach based on image cross-correlation and Kalman filter is presented in this paper. Two linear CCD cameras at different locations were used to capture the images of the cotton flow synchronously. Afterwards, the captured images were preprocessed and segmented by connected region method to obtain separated cotton images. Subsequently, image cross-correlation registration technology was used to calculate the coordinate transformation parameters. For image registration, the Kalman filter tracking method was utilized to predict the possible location to speed up the image registration and solve the problem when the image registration fails. Lastly, the velocity was calculated by the pixel difference and the actual distance of two cameras. The experiment setup was designed to validate the proposed method. The hybrid approach based on image cross-correlation and Kalman filter algorithm measure the dynamic cotton flow velocity with the average 3.31% error. Moreover, the executing efficiency is prior to regular cross-correlation without Kalman filter prediction.