Evaluation of a new apple in-field sorting system for fruit singulation, rotation and imaging

Authors: POTHULA, ANAND - University Of Southern Queensland; ZHANG, ZHAO - China Agricultural University; Lu, Renfu

Submitted to: Computers and Electronics in Agriculture
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 3/17/2023
Publication Date: 3/23/2023
Citation: Pothula, A., Zhang, Z., Lu, R. 2023. Evaluation of a new apple in-field sorting system for fruit singulation, rotation and imaging. Computers and Electronics in Agriculture. 208. Article 107789. https://doi.org/10.1016/j.compag.2023.107789.
DOI: https://doi.org/10.1016/j.compag.2023.107789

Interpretive Summary: In the United States, apples are still manually harvested, and all harvested fruit are kept in cold or controlled atmosphere storage in the same containers regardless of their quality grade. This postharvest handling practice is not cost effective because of high postharvest storage and packing cost. Pre-sorting of apples at the time of harvest can help growers segregate low-quality or inferior apples that are not suitable for the fresh market, so that these apples do not need to be kept for long-term postharvest storage, thus reducing postharvest handling cost. We have recently developed a new automated apple in-field sorting system, which consists of a compact computer vision-based inspection unit, pairs of multi-stage helical conveyance drives to singulate, rotate and transport apples for quality grading, and an automated sorter. To ensure satisfactory quality grading of apples, individual apples need to rotate continuously and consistently, so that the entire surface of the apples can be imaged by the imaging unit for at least once at a given sorting speed. This study evaluated the performance of the sorting system for automatic inspection and grading of apples in terms of conveying speed, fruit size and the rotation characteristics of apples for imaging. Two apple varieties, ‘Delicious’ and ‘Golden Delicious’, were used in the experiment. To study the rotational performance of the system, each quadrant of the test apples of three different sizes was painted in different colors. Approximately 5400 images were acquired of the test apples at 15 frames per second for the single-lane sorting speeds of 1, 2 and 3 apples per second, respectively. The acquired images were then processed to determine the exposure area of each color section in terms of image pixels. It was found that the number of images acquired for each fruit varied from 24 to 9 images when the single-lane sorting speed was changed from 1 to 3 apples per second. The sorting system was found to provide continuous and relatively even or consistent rotation of apples, based on the analysis of cumulative percentages of the four-color areas of the apples. At a single-lane sorting speed of 1 apple per second, the entire surface of each fruit was imaged for more than 4 times, while at 3 apples per second, the surface of the apples was imaged for at least 1.4 times. Hence, the 3-lane sorting system can meet our requirements for in-field quality grading of apples at an overall throughput of 9 or more apples per second. The sorting system has been integrated with a self-propelled apple harvesting machine to help growers enhance harvest efficiency and achieve cost savings in postharvest handling.

Technical Abstract: Automated, computer-imaging based in-field grading and sorting of apples at the time of harvest has the potential to help growers achieve significant cost savings in postharvest storage and packing. Singulation and rotation of fruit are essential steps for a computer imaging-based grading/sorting system. We have recently developed a novel compact, low-cost in-field apple sorting system, which consists of pairs of multi-stage helical conveyance drives to singulate, rotate and advance apples so that they can be inspected by a computer vision unit for quality grading. This study was aimed at evaluating the singulating and rotating performance of the sorting system for automatic inspection and grading of apples, in terms of conveying speed, fruit size, and the percentage of apple exposure area for imaging. Two apple varieties (i.e., ‘Golden Delicious’ and ‘Delicious’) were used for experimental evaluations. To determine the rotational behavior of apples, each quadrant of the apple surface was painted with different colors. Images were acquired for the apples at 15 frames per second and then automatically segmented for the estimation of exposed areas in terms of pixels. It was found that the number of images acquired for each fruit varied from 24 to 9 images when the speed of the sorting system was changed from 1 to 3 apples per second per lane. The singulating and rotating mechanism (SRM) provided continuous and relatively even rotation of the apples while conveying, which was confirmed by cumulative percentages of the four colored areas of ‘Golden Delicious’ and ‘Delicious’ apples at the three sorting speeds. At the sorting speed of 1 apple/s, the entire surface of each fruit was imaged for more than 4 times, while at 3 apples/s, the surface of the apples was imaged for at least 1.4 times. Hence, the sorting system with 3 sorting lanes is able to perform in-field quality grading of apples at a throughput of 9 or more apples/s.