中国农业期刊集成服务平台

当前位置: 首页 > 文章 > Enhancing Rangeland Weed Detection through Convolutional Neural Networks and Transfer Learning 作物设计(英文) 2024,3 (3)

Position: Home > Articles > Enhancing Rangeland Weed Detection through Convolutional Neural Networks and Transfer Learning Crop Design 2024,3 (3)

Enhancing Rangeland Weed Detection through Convolutional Neural Networks and Transfer Learning

作者：

Christian Shackleton;Raja Hashim Ali;Talha Ahmed Kha

关键词：

Convolutional neural network;Transfer learning;Deep learning;Weed species detection;Multiclass classification;Computer visio

摘要：

The detection of weed species in rangeland environments is a challenging task due to various factors such as dense, variable species vegetation, ocular occlusion, and a wide variety of plant morphology. Most research in weed detection, however, focuses on croplands. This research addresses the need for accurate rangeland weed detection models by leveraging convolutional neural network (CNN) models enhanced with transfer learning applied to the DeepWeeds data set taken in situ in regional North Eastern Australia. It investigates the effectiveness of transfer learning across seven popular models, utilizing data augmentation and fine-tuning. The performance of these models was evaluated using accuracy metrics and compared against each other. The results demonstrated that transfer learning, coupled with fine tuning, could be a viable solution for generating efficient weed plant detection models with lower demands on computational resources and smaller datasets, despite the challenging conditions of rangeland environments. EfficientNetV2B1 had the highest classification accuracy of 94.2 %, and lowest training times. Moreover, high levels of accuracy were also achieved using InceptionV3, VGG16, and Densenet121, albeit with a training time penalty. This research provides insights into the performance of CNN models in challenging rangeland environments, demonstrates the potential of using transfer learning to enhance weed detection models, and underscores the significance of model selection in agricultural applications of CNNs.

相似文章

Forest fire smoke recognition based on convolutional neural network [Xuejun Sun, Lin Sun, Yating Huan] 林业研究(英文版) 2020,32 (5)
A Real Time Monitoring System for Accurate Plant Leaves Disease Detection Using Deep Learning [Kazi Naimur Rahman, Sajal Chandra Banik, Raihan Ul Islam, Arafath Al Fahi] 作物设计(英文) 2025,4 (1)
Automatic segmentation of stem and leaf components and individual maize plants in field terrestrial LiDAR data using convolutional neural networks [Zurui Ao, Fangfang Wu, Saihan Hu, Ying Sun, Yanjun Su, Qinghua Guo, Qinchuan Xi] 作物学报(英文版) 2022,10 (5)
Tree species classification using deep learning and RGB optical images obtained by an unmanned aerial vehicle [Chen Zhang, Kai Xia, Hailin Feng, Yinhui Yang, Xiaochen D] 林业研究(英文版) 2020,32 (5)
Temporal sequence Object-based CNN (TS-OCNN) for crop classification from fine resolution remote sensing image time-series [Huapeng Li, Yajun Tian, Ce Zhang, Shuqing Zhang, Peter M. Atkinso] 作物学报(英文版) 2022,10 (5)
Stacked spectral feature space patch: An advanced spectral representation for precise crop classification based on convolutional neural network [Hui Chen, Yuean Qiu, Dameng Yin, Jin Chen, Xuehong Chen, Shuaijun Liu, Licong li] 作物学报(英文版) 2022,10 (5)

导出引用

计量

文章访问数: 7

HTML全文浏览量: 0

PDF下载量: 0

Enhancing Rangeland Weed Detection through Convolutional Neural Networks and Transfer Learning

相似文章

所属期刊

作物设计(英文)

推荐期刊

林业研究(英文版)

作物学报(英文版)