Detection of the Grassland Weed Phlomoides umbrosa Using Multi-Source Imagery and an Improved YOLOv8 Network

Abstract

Grasslands are the mainstay of terrestrial ecosystems and crucial ecological barriers, serving as the foundation for the development of grassland husbandry. However, the frequent occurrence of poisonous plants in grasslands weakens the stability of grassland ecosystems and constrains the growth of grassland livestock husbandry. To achieve early detection of the grassland weed Phlomoides umbrosa (Turcz.) Kamelin & Makhm, this study improves the YOLO-v8 model and proposes a BSS-YOLOv8 network model using UAV images. Using UAV, we can obtain early-stage image data of P. umbrosa and build a seedling dataset. To address challenges such as the complex grassland background and the dwarf seedlings of P. umbrosa, this study incorporated the BoTNet module into the backbone network of the YOLO-v8 model. Enhancing the integrity of feature extraction by linking global and local features through its multi-head self-attention mechanism (MHSA). Additionally, a detection layer was added in the model’s neck structure with an output feature map scale of 160 × 160 to further integrate P. umbrosa feature details from the shallow neural network, thereby strengthening the recognition of small target P. umbrosa. The use of GSConv, as a replacement for some standard convolutions, not only reduced model computational complexity but also further improved its detection performance. Ablation test results reveal that the BSS-YOLOv8 network model achieved a precision of 91.1%, a recall rate of 86.7%, an mAP50 of 92.6%, an F1-Score of 88.85%, and an mAP50:95 of 61.3% on the P. umbrosa seedling dataset. Compared with the baseline network, it demonstrated respective improvements of 2.5%, 3.8%, 3.4%, 3.19%, and 4.4%. When compared to other object detection models (YOLO-v5, Faster R-CNN, etc.), the BSS-YOLOv8 model similarly achieved the best detection performance. The BSS-YOLOv8 proposed in this study enables rapid identification of P. umbrosa seedlings in grassland backgrounds, holding significant importance for early detection and control of weeds in grasslands.

Fruits hidden by green: an improved YOLOV8n for detection of young citrus in lush citrus trees

“…In this paper, the target detection model has been comprehensively evaluated using evaluation metrics such as precision rate, recall rate, mAP50 and test time per image. These evaluation metrics comprehensively measure the performance of the model in terms of classification accuracy, localization accuracy and operational efficiency, thus the comprehensive evaluation of these metrics provides important guidance for model optimization ( Guo et al., 2023 ; Huang et al., 2023 ). Precision, Recall, AP, and mAP calculation formulas follow as shown in Equations 4 – 7 below.…”

Study on Diversity of Poisonous Weeds in Grassland of the Ili Region in Xinjiang

“…By optimizing the physical, chemical, and biological control methods for grassland poisonous weeds, addressing the balance of livestock-carrying capacity and agricultural-pastoral equilibrium, implementing grassland restoration through returning cultivated land to pasture, improving the quality of the grassland ecological compensation mechanism, and continuously enhancing the natural recovery capabilities of grasslands while employing artificial restoration methods, it is possible to address the ongoing degradation of the grassland ecological environment. This approach aims at achieving sustainable development for the grasslands [26,[40][41][42].…”

Enhancing Livestock Detection: An Efficient Model Based on YOLOv8

“…By comparison, one-stage models have superior real-time performance due to their ability to recognize and locate items inside the picture. While their accuracy may be somewhat lower than that of two-stage models, they can detect things much faster [17].…”