Saqib Muhammad Ali, Aqib Muhammad, Tahir Muhammad Naveed, Hafeez Yaser
University Institute of Information Technology (UIIT), Pir Mehr Ali Shah (PMAS)-Arid Agriculture University Rawalpindi, Rawalpindi, Punjab, Pakistan.
National Center of Industrial Biotechnology, Pir Mehr Ali Shah (PMAS)-Arid Agriculture University Rawalpindi, Rawalpindi, Punjab, Pakistan.
Front Plant Sci. 2023 Jul 28;14:1211235. doi: 10.3389/fpls.2023.1211235. eCollection 2023.
Deep learning (DL) is a core constituent for building an object detection system and provides a variety of algorithms to be used in a variety of applications. In agriculture, weed management is one of the major concerns, weed detection systems could be of great help to improve production. In this work, we have proposed a DL-based weed detection model that can efficiently be used for effective weed management in crops.
Our proposed model uses Convolutional Neural Network based object detection system You Only Look Once (YOLO) for training and prediction. The collected dataset contains RGB images of four different weed species named Grass, Creeping Thistle, Bindweed, and California poppy. This dataset is manipulated by applying LAB (Lightness A and B) and HSV (Hue, Saturation, Value) image transformation techniques and then trained on four YOLO models (v3, v3-tiny, v4, v4-tiny).
The effects of image transformation are analyzed, and it is deduced that the model performance is not much affected by this transformation. Inferencing results obtained by making a comparison of correctly predicted weeds are quite promising, among all models implemented in this work, the YOLOv4 model has achieved the highest accuracy. It has correctly predicted 98.88% weeds with an average loss of 1.8 and 73.1% mean average precision value.
In the future, we plan to integrate this model in a variable rate sprayer for precise weed management in real time.
深度学习（DL）是构建目标检测系统的核心组成部分，并提供了多种可用于各种应用的算法。在农业中，杂草管理是主要关注点之一，杂草检测系统对提高产量可能会有很大帮助。在这项工作中，我们提出了一种基于深度学习的杂草检测模型，该模型可有效地用于作物的有效杂草管理。
我们提出的模型使用基于卷积神经网络的目标检测系统“你只看一次”（YOLO）进行训练和预测。收集的数据集包含四种不同杂草物种的RGB图像，分别是禾本科杂草、田蓟、旋花和加利福尼亚罂粟。通过应用LAB（明度A和B）和HSV（色调、饱和度、明度）图像变换技术对该数据集进行处理，然后在四个YOLO模型（v3、v3-tiny、v4、v4-tiny）上进行训练。
分析了图像变换的效果，推断出该变换对模型性能影响不大。通过比较正确预测的杂草获得的推理结果很有前景，在这项工作中实现的所有模型中，YOLOv4模型达到了最高准确率。它正确预测了98.88%的杂草，平均损失为1.8，平均精度均值为73.1%。
未来，我们计划将该模型集成到变量喷雾器中，以实时进行精确的杂草管理。
