Click on “Download PDF” for the PDF version or on the title for the HTML version.

If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

Abstract. Most of the traditional picking robots adopt PC as the processor to complete the image processing, target recognition and positioning through the binocular camera system. The whole system is large in size, high in power consumption, expensive in price, and difficult to realize modular application. In this study, a binocular stereo vision system of fruit picking robots based on embedded platform with ARM processor was proposed. Linux was used as the operating system of the whole Binocular stereo vision system. Python was used as the programming language to realize the recognition and extraction of the target fruits, and calculate the spatial position information of the picking point. Finally, a binocular stereo vision system that can be used to identify and locate the target fruits was developed based on the platform of Raspberry Pi 4B, and the whole elapsed time of recognition algorithm for target fruits was calculated using the clock function both in PC and the Raspberry Pi 4B platforms. Compared with the traditional picking robot system, the proposed system has significantly improved the recognition speed and system stability, which can provide the basis for widespread use of agricultural robots.