Search Results (2)

Mechanical weed management is a drudging task that requires manpower and has risks when conducted within rows of orchards. However, intrarow weeding must still be conducted by manual labor due to the restricted movements of riding mowers within the rows of orchards due to their confined structures with nets and poles. However, autonomous robotic weeders still face challenges identifying uncut weeds due to the obstruction of Global Navigation Satellite System (GNSS) signals caused by poles and tree canopies. A properly designed intelligent vision system would have the potential to achieve the desired outcome by utilizing an autonomous weeder to perform operations in uncut sections. Therefore, the objective of this study is to develop a vision module using a custom-trained dataset on YOLO instance segmentation algorithms to support autonomous robotic weeders in recognizing uncut weeds and obstacles (i.e., fruit tree trunks, fixed poles) within rows. The training dataset was acquired from a pear orchard located at the Tsukuba Plant Innovation Research Center (T-PIRC) at the University of Tsukuba, Japan. In total, 5000 images were preprocessed and labeled for training and testing using YOLO models. Four versions of edge-device-dedicated YOLO instance segmentation were utilized in this research—YOLOv5n-seg, YOLOv5s-seg, YOLOv8n-seg, and YOLOv8s-seg—for real-time application with an autonomous weeder. A comparison study was conducted to evaluate all YOLO models in terms of detection accuracy, model complexity, and inference speed. The smaller YOLOv5-based and YOLOv8-based models were found to be more efficient than the larger models, and YOLOv8n-seg was selected as the vision module for the autonomous weeder. In the evaluation process, YOLOv8n-seg had better segmentation accuracy than YOLOv5n-seg, while the latter had the fastest inference time. The performance of YOLOv8n-seg was also acceptable when it was deployed on a resource-constrained device that is appropriate for robotic weeders. The results indicated that the proposed deep learning-based detection accuracy and inference speed can be used for object recognition via edge devices for robotic operation during intrarow weeding operations in orchards. Full article

The impact of invasive plant species in national parks and forests in Vietnam is undocumented and management plans have yet to be developed. Ten national parks, ranging from uncut to degraded forests located throughout Vietnam, were surveyed for invasive plant species. Transects were set up along roads, trails where local people access park areas, and also tracks through natural forest. Of 134 exotic weeds, 25 were classified as invasive species and the number of invasive species ranged from 8 to 15 per park. An assessment of the risk of invasive species was made for three national parks based on an invasive species assessment protocol. Examples of highly invasive species were Chromolaena odorata and Mimosa diplotricha in Cat Ba National Park (island evergreen secondary forest over limestone); Mimosa pigra, Panicum repens and Eichhornia crassipes in Tram Chim National Park (lowland wetland forest dominated by melaleuca); and C. odorata, Mikania micrantha and M. diplotricha in Son Tra Nature Conservation area (peninsula evergreen secondary forest). Strategies to monitor and manage invasive weeds in forests and national parks in Vietnam are outlined. Full article