Eco-friendly weeding through precise detection of growing points via efficient multi-branch convolutional neural networks

Arsa, Dewa Made Sri; Ilyas, Talha; Park, Seok-Hwan; Won, Okjae; Kim, Hyongsuk

doi:10.1016/j.compag.2023.107830

Cited by 2 publications

(1 citation statement)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By improving the backbone network, the model has achieved substantial results. Arsa et al [21] proposed a dual decoder branch network to detect weed growth points. The decoder component of the model amalgamates spatial attention and channel attention while introducing a activation gate mechanism to regulate attention allocation.…”

Section: Weed Detectionmentioning

confidence: 99%

Improved Weed Detection in Cotton Fields Using Enhanced YOLOv8s with Modified Feature Extraction Modules

Ren,

Yang,

et al. 2024

Symmetry

View full text Add to dashboard Cite

Weed detection plays a crucial role in enhancing cotton agricultural productivity. However, the detection process is subject to challenges such as target scale diversity and loss of leaf symmetry due to leaf shading. Hence, this research presents an enhanced model, EY8-MFEM, for detecting weeds in cotton fields. Firstly, the ALGA module is proposed, which combines the local and global information of feature maps through weighting operations to better focus on the spatial information of feature maps. Following this, the C2F-ALGA module was developed to augment the feature extraction capability of the underlying backbone network. Secondly, the MDPM module is proposed to generate attention matrices by capturing the horizontal and vertical information of feature maps, reducing duplicate information in the feature maps. Finally, we will replace the upsampling module of YOLOv8 with the CARAFE module to provide better upsampling performance. Extensive experiments on two publicly available datasets showed that the F1, mAP50 and mAP75 metrics improved by 1.2%, 5.1%, 2.9% and 3.8%, 1.3%, 2.2%, respectively, compared to the baseline model. This study showcases the algorithm’s potential for practical applications in weed detection within cotton fields, promoting the significant development of artificial intelligence in the field of agriculture.

show abstract

Section: Weed Detectionmentioning

confidence: 99%

Improved Weed Detection in Cotton Fields Using Enhanced YOLOv8s with Modified Feature Extraction Modules

Ren,

Yang,

et al. 2024

Symmetry

View full text Add to dashboard Cite

show abstract

A Static Laser Weeding Device and System Based on Fiber Laser: Development, Experimentation, and Evaluation

Yu,

He,

et al. 2024

Agronomy

View full text Add to dashboard Cite

To demonstrate the feasibility and improve the implementation of laser weeding, a static movable lift-adjustable closed fiber laser weeding device and system have been developed, followed by experiments and performance evaluations. Physical experiments were conducted on the energy required for laser cutting of weed stems, targeting four common larger weeds (Chenopodium album, Amaranthus spinosus, Setaria viridis, and Eleusine indica) in farmland and orchards. At the same irradiation distances, the energy required to cut the same type of large weed generally increases with increasing distances and stem diameters but decreases with increasing irradiation time. The variance of stems’ power density after irradiation was larger and the values were more dispersed for Chenopodium album and Setaria viridis weeds, and the values were relatively scattered, while the power density values of Amaranthus spinosus and Eleusine indica weeds were more concentrated. When the irradiation time was 10 s, the 3.892 W/mm2 laser was sufficient to eliminate weeds and plants with the irradiation distances of 2 m. The 2.47 W/mm2 laser was more effective, as it killed weeds within a distance of 1 m in less than 1 s. This work demonstrates the feasibility of the laser weeding device and system that can completely cut off the stems of large weeds, and this technology has the potential to promote sustainable agriculture.

show abstract

Eco-friendly weeding through precise detection of growing points via efficient multi-branch convolutional neural networks

Cited by 2 publications

References 31 publications

Improved Weed Detection in Cotton Fields Using Enhanced YOLOv8s with Modified Feature Extraction Modules

Improved Weed Detection in Cotton Fields Using Enhanced YOLOv8s with Modified Feature Extraction Modules

A Static Laser Weeding Device and System Based on Fiber Laser: Development, Experimentation, and Evaluation

Contact Info

Product

Resources

About