Institut für Agrartechnik

Permanent URI for this collectionhttps://hohpublica.uni-hohenheim.de/handle/123456789/19

Browse

Now showing 1 - 2 of 2

Development of multifunctional unmanned aerial vehicles versus ground seeding and outplanting: What is more effective for improving the growth and quality of rice culture?
(2022) Qi, Peng; Wang, Zhichong; Wang, Changling; Xu, Lin; Jia, Xiaoming; Zhang, Yang; Wang, Shubo; Han, Leng; Li, Tian; Chen, Bo; Li, Chunyu; Mei, Changjun; Pan, Yayun; Zhang, Wei; Müller, Joachim; Liu, Yajia; He, Xiongkui
The agronomic processes are complex in rice production. The mechanization efficiency is low in seeding, fertilization, and pesticide application, which is labor-intensive and time-consuming. Currently, many kinds of research focus on the single operation of UAVs on rice, but there is a paucity of comprehensive applications for the whole process of seeding, fertilization, and pesticide application. Based on the previous research synthetically, a multifunctional unmanned aerial vehicle (mUAV) was designed for rice planting management based on the intelligent operation platform, which realized three functions of seeding, fertilizer spreading, and pesticide application on the same flight platform. Computational fluid dynamics (CFD) simulations were used for machine design. Field trials were used to measure operating parameters. Finally, a comparative experimental analysis of the whole process was conducted by comparing the cultivation patterns of mUAV seeding (T1) with mechanical rice direct seeder (T2), and mechanical rice transplanter (T3). The comprehensive benefit of different rice management processes was evaluated. The results showed that the downwash wind field of the mUAV fluctuated widely from 0 to 1.5 m, with the spreading height of 2.5 m, and the pesticide application height of 3 m, which meet the operational requirements. There was no significant difference in yield between T1, T2, and T3 test areas, while the differences in operational efficiency and input labor costs were large. In the sowing stage, T1 had obvious advantages since the working efficiency was 2.2 times higher than T2, and the labor cost was reduced by 68.5%. The advantages were more obvious compared to T3, the working efficiency was 4 times higher than in T3, and the labor cost was reduced by 82.5%. During the pesticide application, T1 still had an advantage, but it was not a significant increase in advantage relative to the seeding stage, in which operating efficiency increased by 1.3 times and labor costs were reduced by 25%. However, the fertilization of T1 was not advantageous due to load and other limitations. Compared to T2 and T3, operational efficiency was reduced by 80% and labor costs increased by 14.3%. It is hoped that this research will provide new equipment for rice cultivation patterns in different environments, while improving rice mechanization, reducing labor inputs, and lowering costs.
Effects of different ground segmentation methods on the accuracy of UAV-based canopy volume measurements
(2024) Han, Leng; Wang, Zhichong; He, Miao; He, Xiongkui; Han, Leng; College of Science, China Agricultural University, Beijing, China; Wang, Zhichong; Tropics and Subtropics Group, Institute of Agricultural Engineering, University of Hohenheim, Stuttgart, Germany; He, Miao; College of Science, China Agricultural University, Beijing, China; He, Xiongkui; College of Science, China Agricultural University, Beijing, China
The nonuniform distribution of fruit tree canopies in space poses a challenge for precision management. In recent years, with the development of Structure from Motion (SFM) technology, unmanned aerial vehicle (UAV) remote sensing has been widely used to measure canopy features in orchards to balance efficiency and accuracy. A pipeline of canopy volume measurement based on UAV remote sensing was developed, in which RGB and digital surface model (DSM) orthophotos were constructed from captured RGB images, and then the canopy was segmented using U-Net, OTSU, and RANSAC methods, and the volume was calculated. The accuracy of the segmentation and the canopy volume measurement were compared. The results show that the U-Net trained with RGB and DSM achieves the best accuracy in the segmentation task, with mean intersection of concatenation (MIoU) of 84.75% and mean pixel accuracy (MPA) of 92.58%. However, in the canopy volume estimation task, the U-Net trained with DSM only achieved the best accuracy with Root mean square error (RMSE) of 0.410 m 3 , relative root mean square error (rRMSE) of 6.40%, and mean absolute percentage error (MAPE) of 4.74%. The deep learning-based segmentation method achieved higher accuracy in both the segmentation task and the canopy volume measurement task. For canopy volumes up to 7.50 m 3 , OTSU and RANSAC achieve an RMSE of 0.521 m 3 and 0.580 m 3 , respectively. Therefore, in the case of manually labeled datasets, the use of U-Net to segment the canopy region can achieve higher accuracy of canopy volume measurement. If it is difficult to cover the cost of data labeling, ground segmentation using partitioned OTSU can yield more accurate canopy volumes than RANSAC.

Browse

Browsing Institut für Agrartechnik by Journal "Frontiers in plant science"