文献类型：期刊文献

英文题名：Detection and counting of banana bunches by integrating deep learning and classic image-processing algorithms

作者：Wu, Fengyun[1];Yang, Zhou[1,2,3];Mo, Xingkang[1];Wu, Zihao[1];Tang, Wei[4];Duan, Jieli[1,2];Zou, Xiangjun[1,4]

机构：[1]South China Agr Univ, Coll Engn, Guangzhou 510642, Peoples R China;[2]Guangdong Lab Lingnan Modern Agr, Guangzhou 510642, Peoples R China;[3]Guangdong Ocean Univ, Sch Mech Engn, Zhanjiang 524088, Peoples R China;[4]Foshan Zhongke Innovat Res Inst Intelligent Agr &, Guangzhou 510000, Peoples R China

年份：2023

卷号：209

外文期刊名：COMPUTERS AND ELECTRONICS IN AGRICULTURE

收录：SCI-EXPANDED(收录号：WOS:000981649300001)、、EI(收录号：20231513877515)、Scopus(收录号：2-s2.0-85152111271)、WOS

基金：This work was supported by the National Natural Science Foundation of China (Grant No. 32271996) , Guangdong Laboratory for Lingnan Modern Agriculture Project (Grant No. NT2021009) , the open compe- tition program of top ten critical priorities of Agricultural Science and Technology Innovation for the 14th Five-Year Plan of Guangdong Province (Grant No.2022SDZG03) , China Agriculture Research System of MOF and MARA (Grant No. CARS-31-10) .

语种：英文

外文关键词：Banana fruit cluster; Sterile bud removal; Machine vision; Recognition of number of fruit bunches; Edge detection; Image segmentation

外文摘要：Robots must first detect the number of banana bunches when making judgements on sterile bud removal and estimating weight for harvest in the field environment. Banana bunches are complex in shape, arranged in a nonlinear helical curve along the stalk, and have different growth states in different periods, with bunches widely spaced in the early period and densely arranged in the harvest period. Deep learning nor classical imageprocessing algorithms alone can detect and count bunches in both periods. Therefore, these algorithms were combined to calculate the number of bunches in the two periods. For counting bunches in the debudding period, the convolutional neural network Deeplab V3 + model and classic image-processing algorithm were combined to finely segment bunches and calculate bunch numbers, providing intelligent decision-making for judgment on the timing for debudding. To count bunches during harvest, based on deep learning to identify the overall banana fruit cluster, the edge detection algorithm was employed to extract the centroid points of fruit fingers, and the clustering algorithm was used to determine the optimal number of bunches on the visual detection surface. An estimation model for the total number of bunches, including hidden ones, was created based on their helical curve arrangement. The results indicated a target segmentation MIoU of 0.878 during the debudding period, a mean pixel precision of 0.936, and a final bunch detection accuracy rate of 86%. Bunch detection was highly challenging during the harvest period, with a detection accuracy rate of 76% and a final overall bunch counting accuracy rate of 93.2%. Software was designed to estimate banana fruit weight during the harvest period. This research method provided a theoretical basis and experimental data support for automatic sterile bud removal and weight estimation for bananas.