Optimization of greenhouse tomato localization in overlapping areas

Tomato localization is the main difficulty of tomato picking robots vision system. To provide robots vision system with the accurate position of tomatoes, this paper collects images with a binocular camera, provides the principle of binocular ranging, and improves the census stereo matching algorithm. The improved algorithm betters the area matching process: only the areas con-taining tomatoes are matched, more constraints are applied on the area matching, and the Local-ization of tomatoes in overlapping areas is optimized. Compared with stereo processing by semiglobal matching and mutual information (SGBM) algorithm and pyramid stereo matching net-work (PSMnet), the improved algorithm achieved an extremely small disparity error. The absolute error maximized at 4 pixels. The matching time for a single image was 10 ms at the most. In this way, the matching time is improved significantly. Experimental results show that the improved cen-sus matching algorithm provided tomato picking robots vision system with more accurate localiza-tion information, and greatly improved the picking efficiency.(c) 2022 THE AUTHORS. Published by Elsevier BV on behalf of Faculty of Engineering, Alexandria University. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/ licenses/by-nc-nd/4.0/).

Automated summary

This paper focuses on the tomato localization issue in the vision system of tomato picking robots. It uses a binocular camera to collect images, improves the principle of binocular ranging, and enhances the census stereo matching algorithm. The improved algorithm optimizes the area matching process, applies more constraints, and achieves an extremely small disparity error. The matching time is significantly improved, and experimental results show that the improved algorithm provides more accurate localization information.