Plant stress is one of major issues that cause significant economic loss for growers. The labor-intensive conventional methods for identifying the stressed plants constrain their applications. To address this issue, rapid methods are in urgent needs. Developments of advanced sensing and machine learning techniques trigger revolutions for precision agriculture based on deep learning and big data. In this paper, we reviewed the latest deep learning approaches pertinent to the image analysis of crop stress diagnosis. We compiled the current sensor tools and deep learning principles involved in plant stress phenotyping. In addition, we reviewed a variety of deep learning applications/functions with plant stress imaging, including classification, object detection, and segmentation, of which are closely intertwined. Furthermore, we summarized and discussed the current challenges and future development avenues in plant phenotyping.

Deep learning is thought of as a promising mean to identify maize diseases. However, the drawback of deep learning is the huge sample data and low accuracy. In this paper, we proposed a multi-scale convolutional global pooling neural network to improve the accuracy of maize diseases identification. Firstly, on the basis of the AlexNet model, a convolutional layer and new Inception module are added to enhance the ability of AlexNet features extraction. Then, in order to avoid the over-fitting problem caused by too many parameters, we use the global pooling layer to replace the original fully-connected layer. Besides, we also adopt the transfer learning method to solve the over-fitting problem caused by insufficient sample data. The improved model can reduce over-fitting and epochs to enhance the performance of maize diseases recognition. From the considerable experimental results, we can conclude that the proposed model has better performance compared with convolutional neural network models VGGNet-16, DenseNet, ResNet-50 and AlexNet in recognition accuracy.

This study developed and field tested an automated weed mapping and variable-rate herbicide spraying (VRHS) system for row crops. Weed detection was performed through a machine vision sub-system that used a custom threshold segmentation method, an improved particle swarm optimum (IPSO) algorithm, capable of segmenting the field images. The VRHS system also used a lateral histogram-based algorithm for fast extraction of weed maps. This was the basis for determining real-time herbicide application rates. The central processor of the VRHS system had high logic operation capacity, compared to the conventional controller-based systems. Custom developed monitoring system allowed real-time visualization of the spraying system functionalities. Integrated system performance was then evaluated through field experiments. The IPSO successfully segmented weeds within corn crop at seedling growth stage and reduced segmentation error rates to 0.1% from 7.1% of traditional particle swarm optimization algorithm. IPSO processing speed was 0.026 s/frame. The weed detection to chemical actuation response time of integrated system was 1.562 s. Overall, VRHS system met the real-time data processing and actuation requirements for its use in practical weed management applications.

Moisture content is an important index to assess the grain quality and food processing conditions. A measurement system based on the traveling–standing microwave attenuation method is designed for a fast and nondestructive grain moisture content determination. The proposed system consists of a microwave cavity oscillator, microwave transmitting and receiving horn antennas, microwave detector, slide rail, sample container, weight sensor, temperature sensor, and controller. The traveling–standing wave caused by free space microwave multiple reflection is discussed. The moisture content calibration functions eliminated the interference of bulk density and temperature are proposed based on the attenuation of the maximum field strength of the transmission traveling–standing wave. The moisture content of rice, which ranges from 10.75% to 27.62%, is obtained with a standard error of prediction (SEP) of 0.586% and a coefficient of determination ( R²) of 0.988, whereas the moisture content of corn, which ranges from 7.72% to 24.46%, is obtained with a SEP of 0.340% and R² of 0.991. The main results might provide technical support for the development of accurate and intelligent grain quality detection equipment.

Accurate identification of rice diseases is crucial for controlling diseases and improving rice yield. To improve the classification accuracy of rice diseases, this paper proposed a classification and identification method based on an improved ShuffleNet V2 (GE-ShuffleNet) model. Firstly, the Ghost module is used to replace the convolution in the two basic unit modules of ShuffleNet V2, and the unimportant convolution is deleted from the two basic unit modules of ShuffleNet V2. The Hardswish activation function is applied to replace the ReLU activation function to improve the identification accuracy of the model. Secondly, an effective channel attention (ECA) module is added to the network to avoid dimension reduction, and the correlation between channels is effectively extracted through 1D convolution. Besides, L2 regularization is introduced to fine-tune the training parameters during training to prevent overfitting. Finally, the considerable experimental and numerical results proved the advantages of our proposed model in terms of model size, floating-point operation per second (FLOPs), and parameters (Params). Especially in the case of smaller model size (5.879 M), the identification accuracy of GE-ShuffleNet (96.6%) is higher than that of ShuffleNet V2 (94.4%), MobileNet V2 (93.7%), AlexNet (79.1%), Swim Transformer (88.1%), EfficientNet V2 (89.7%), VGG16 (81.9%), GhostNet (89.3%) and ResNet50 (92.5%).