http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
동슈아 ( Xuhua Dong ),김우영 ( Woo-young Kim ),정육 ( Zheng Yu ),오주열 ( Ju-youl Oh ),장제연 ( Je-yeon Jang ),이경환 ( Kyeong-hwan Lee ) 한국농업기계학회 2021 한국농업기계학회 학술발표논문집 Vol.26 No.2
The assessment of 3D fruit phenotyping traits of apple trees can provide management strategies for growers of apple orchards. The estimation of quantitative distribution of apples in orchard is an important parameter for yield estimation. Since it is hard to quantify them manually, resolving apple phenotyping efficiently is critical for monitoring apple yield and promoting a better management system. Thus in current study, we have developed a novel technology for 3D mapping of three types of apple training system fields. The 3D point cloud of apples was reconstructed using high spatial and temporal multi-viewing images collected by unmanned aerial vehicles (UAVs) based multi-camera system. The extraction of information about individual apple in 3D point cloud was executed using 3D instance segmentation algorithm which includes generalized sparse convolutional neural networks, discriminative loss function, and varying density-based 3D clustering method. The developed apple traits extraction algorithm could measure the 3D position of an individual apple by sphere fitting. The accuracy of the technique was evaluated by comparing its results with manual estimates of number of apples. The results obtained from our method are in good agreement with manual estimates. The average accuracy of apple counting in three types of the fields were ~92 % followed by the linear regression (R2) of 0.92 with root-mean-square error (RMSE) value of 13.93. Thus, 3D spatial distribution of apples were achieved and analyzed by above technique. This research proposes a method that combines 3D photography with 3D instance segmentation to accurately extract individual apples from various types of apple training systems in orchards and can also be used to segment and analyze other fruits.
동슈아 ( Xuhua Dong ),김우영 ( Woo-youg Kim ),이경환 ( Kyeong-hwan Lee ) 한국농업기계학회 2022 한국농업기계학회 학술발표논문집 Vol.27 No.1
Pruning operations are necessary for the orchard management to control the apple tree vigor. Owing to the complicated structure of apple trees, the pruning severity can not be estimated quantitatively using any parameter. Therefore, it is necessary to solve the pruning severity estimation effectively to facilitate a better management of apple orchards. In this study, a novel technology for three-dimensional (3D) volume calculation of individual 3D tree was developed to define the pruning severity and make pruning severity mapping for the slender-spindle type of apple trees before and after pruning. The 3D point cloud of apple tree was reconstructed using multi-viewing images collected by a light-weight multi-camera system. The individual apple tree in 3D point cloud was extracted by CloudCompare software. The proposed volume calculation algorithm for apple tree was voxel-based and included interior filling, voxel edge thinning, and interior refilling. The proposed algorithm was experimentally tested on seven apple trees by comparing the tree volume using the proposed algorithm with those calculated using manual measurement, 3D convex hull, 3D alpha shape, concave hull by slices, and normal voxelization methods. The proposed method achieved the smallest mean absolute percentage (MAPE) of 5.6% with a coefficient of determination (R2) of 0.99. Finally, pruning severity mapping of all apple trees in the orchard were obtained. In this study, we proposed an effective method combining 3D photography and volume calculation to accurately estimate the volume of individual apple tree and quantificationally describe the pruning severity.