Weed Density Extraction Based on Few-Shot Learning Through UAV Remote Sensing RGB and Multispectral Images in Ecological Irrigation Area

Abstract

With the development of ecological irrigation area, a higher level of detection and control categories for weeds are currently required. In this article, an improved transfer neural network based on bionic optimization to detect weed density and crop growth is proposed, which used the pre-trained AlexNet network for transfer learning. Because the learning rate of the new addition layer is difficult to tune to the best, the weight and bias learning rate of the newly added fully connected layer is set with particle swarm optimization (PSO) and bat algorithm (BA) to find the optimal combination on the small data set. Data are transported to the convolutional neural network (CNN) by collecting red-green-blue (RGB) and 5-band multispectral images of 3 kinds of weeds and 3 kinds of crops as data sets, through cutting, rotating, and other operations. Finally, 6 kinds of classifications are implemented. At the same time, a self-constructed CNN based on model-agnostic meta-learning (MAML) is proposed in order to realize the learning of neural networks with small sample and high efficiency, and its accuracy is verified in the test set. The neural networks optimized by two bionic optimization algorithms are compared with the self-constructed CNN based on MAML and histogram of oriented gradient + support vector machine (HOG + SVM). The experimental results show that the combination of learning rate through BA is the best, and its accuracy can reach 99.39% for RGB images, 99.53% for multispectral images, and 96.02% for a 6-shot small sample. The purpose of the classification proposed in this article is to calculate the growth of various plants (including weeds and crops) in the farmland. And various plant densities can be accurately calculated through the plant density calculation formula and algorithm proposed in this article, which provides a basis for the application of variable herbicides by experimenting in different farmlands. Finally, an excellent cycle of ecological irrigation district can be promoted.

Transfer Learning-Based Lightweight SSD Model for Detection of Pests in Citrus

“…The number of model parameters is one of the important indicators for embedded devices to run deep learning models [35]. The weight parameters of each layer were added to obtain the total number of parameters, in which the model parameters were stored as a floating point type and the model parameters were obtained by calculating with 4 bytes.…”

Identification and Comprehensive Evaluation of Resistant Weeds Using Unmanned Aerial Vehicle-Based Multispectral Imagery

“…In addition, remote sensing imagery is linked to specific farm problems through deep learning for the identification of biological and non-biological stresses in crops ( Francesconi et al, 2021 ; Ishengoma et al, 2021 ; Jiang et al, 2021 ; Zhou et al, 2021 ), segmentation, and classification ( He et al, 2021 ; Osco et al, 2021 ; Vong et al, 2021 ). These studies show that the combination of UAV remote sensing and deep learning provides the scope for large-scale resistant weed evaluation ( Krähmer et al, 2020 ; Wang et al, 2022 ).…”

A Path Planning System for Orchard Mower Based on Improved A* Algorithm

“…Task allocation methods based on [22,23] address the issues of low task allocation efficiency and poor system scalability. When tackling the problem of multi-robot task allocation, swarm intelligence algorithms such as ant colony algorithms [24,25] or neural networks [26,27] exhibit high allocation efficiency, strong applicability, and ease of implementation, garnering significant attention from researchers [28].…”