A fast nursery plug tray images sequence mosaic technique

Abstract

A machine vision based system to estimate the nursery plug tray sowing quantity is necessary in the rice seedling nursery. Because the super hybrid rice is of small diameter, in order to obtain better estimation results of sowing quantity, only part of the tray scene is captured by machine vision system. Therefore, nursery tray image sequence mosaic algorithm is required so as to obtain the whole nursery tray sowing performance. In this paper, a fast nursery plug tray image mosaic technique based on Phase Correlation and Speeded up Robust Features (the PC-SURF) algorithm was introduced. To reduce huge computational complexity in feature extraction and avoid wrong match points from non-overlapping regions between two adjacent images, firstly the proposed method used Phase Correlation to approximately locate the overlapping regions between two sequential images so as to narrow down the processing area for further feature extraction. Then, the SURF algorithm was implemented in the overlapping region of the images to perform image registration and image blending. Image registration and blending were then performed using the RANSAC algorithm and transition smoothing method. Finally, sequential images were warped into a single frame to produce a panoramic tray image with high resolution and better quality. The test results showed that the PC-SURF algorithm greatly outperforms the SURF algorithm in point matching accuracy, time consumption, and image mosaic accuracy. The average feature point matching accuracy of the PC-SURF algorithm was improved by approximately 7.14%. The implementation time was almost three times faster. The Root Mean Squared Error (RMSE) of image blending in the R, G, B channels (RMSEr, RMSEg, and RMSEb) decreased by approximately 8.4%, 6.9%, 6.9% respectively. The RMSE of image registration RMSEreg decreased by 33.8%. In addition, the speed of the nursery tray image mosaic technology could meet the requirements for real-time implementation in super hybrid rice automated sowing machines.

Detection of Performance of Hybrid Rice Pot-Tray Sowing Utilizing Machine Vision and Machine Learning Approach

“…Qi [10] used machine vision and LabVIEW software to realize the detection of seeding cavities in hybrid rice seeding. Tan [11,12,13] used machine vision and MATLAB to detect the performance of hybrid rice seeding. Most of the studies using machine vision mentioned above were based on the Windows platform.…”