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.

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.

Field weeds identification is challenging for precision spraying, i.e., the automation identification of the weeds from the crops. For rapidly obtaining weed distribution in field, this study developed a weed density detection method based on absolute feature corner point (AFCP) algorithm for the first time. For optimizing the AFCP algorithm, image preprocessing was firstly performed through a sub-module processing capable of segmenting and optimizing the field images. The AFCP algorithm improved Harris corner to extract corners of single crop and weed and then sub-absolute corner classifier as well as absolute corner classifier were proposed for absolute corners detection of crop rows. Then, the AFCP algorithm merged absolute corners to identify crop and weed position information. Meanwhile, the weed distribution was obtained based on two weed density parameters (weed pressure and cluster rate). At last, the AFCP algorithm was validated based on the images that were obtained using one typical digital camera mounted on the tractor in field. The results showed that the proposed weed detection method manifested well given its ability to process an image of 2748 × 576 pixels using 782 ms as well as its accuracy in identifying weeds reaching 90.3%. Such results indicated that the weed detection method based on AFCP algorithm met the requirements of practical weed management in field, including the real-time images computation processing and accuracy, which provided the theoretical base for the precision spraying operations.

Tomato is generally cultivated by transplanting seedlings in ridges and furrows. During growth, there are various types of tomato pests and diseases, making it challenging to identify them simultaneously. To address this issue, conventional convolutional neural networks have been investigated, but they have a large number of parameters and are time-consuming. In this paper, we proposed a lightweight multi-scale tomato pest and disease classification network, called CNNA. Firstly, we constructed a dataset of tomato diseases and pests consisting of 27,193 images with 18 categories. Then, we compressed and optimized the ConvNeXt-Tiny network structure to maintain accuracy while significantly reducing the number of parameters. In addition, we proposed a multi-scale feature fusion module to improve the feature extraction ability of the model for different spot sizes and pests, and we proposed a global channel attention mechanism to enhance the sensitivity of the network model to spot and pest features. Finally, the model was trained and deployed to the Jetson TX2 NX for inference of tomato pests and diseases in video stream data. The experimental results showed that the proposed CNNA model outperformed the pre-trained lightweight models such as MobileNetV3, MobileVit, and ShuffleNetV2 in terms of accuracy and all parameters, with a recognition accuracy of 98.96%. Meanwhile, the error rate, inference time for a single image, network parameters, FLOPs, and model size were only 1%, 47.35 ms, 0.37 M, 237.61 M, and 1.47 MB, respectively.

Crop disease has been a severe issue for agriculture, causing economic loss for growers. Thus, disease identification urgently needs to be addressed, especially for precision agriculture. As of today, deep learning has been widely used for crop disease identification combined with optical imaging sensors. In this study, a lightweight convolutional neural network model is designed and validated on two publicly available imaging datasets and one self-built dataset with 28 types of leaf and leaf disease images of 6 crops as the research object. This model is an improvement of the existing convolutional neural network, reducing the floating-point operations by 65%. In addition, dilated depth-wise convolutions were used to increase the network receptive field and improve the model recognition accuracy without affecting the network computational speed. Meanwhile, two attention mechanisms are optimized to reduce attention module computation, improving the capability of the model to select the correct regions of interest. After training, this model achieved an average accuracy of 99.86%, and the image calculation speed was 0.173 s. Comparing with 11 backbone models and 5 latest crop leaf disease identification studies, the proposed model achieved the highest accuracy. Therefore, this model with an advantage of balancing between the calculation speed and recognition accuracy. Furthermore, the proposed model provides a theoretical basis and technical support for the practical application and mobile terminal applications of crop disease recognition in precision agriculture.

At present, picking Sichuan pepper is mainly undertaken by people, which is inefficient and presents the possibility of workers getting hurt. It is necessary to develop an intelligent robot for picking Sichuan peppers in which the key technology is accurate segmentation by means of mechanical vision. In this study, we first took images of Sichuan peppers (Hanyuan variety) in an orchard under various conditions of light intensity, cluster numbers, and image occlusion by other elements such as leaves. Under these various image conditions, we compared the ability of different technologies to segment the images, examining both traditional image segmentation methods (RGB color space, HSV color space, k-means clustering algorithm) and deep learning algorithms (U-Net convolutional network, Pyramid Scene Parsing Network, DeeplabV3+ convolutional network). After the images had been segmented, we compared the effectiveness of each algorithm at identifying Sichuan peppers in the various types of image, using the Intersection Over Union(IOU) and Mean Pixel Accuracy(MPA) indexes to measure success. The results showed that the U-Net algorithm was the most effective in the case of single front-lit clusters light without occlusion, with an IOU of 87.23% and an MPA of 95.95%. In multiple front-lit clusters without occlusion, its IOU was 76.52% and its MPA was 94.33%. Based on these results, we propose applicable segmentation methods for an intelligent Sichuan pepper-picking robot which can identify the fruit in images from various growing environments. The research showed good accuracy for the recognition and segmentation of Sichuan peppers, which suggests that this method can provide technical support for the visual recognition of a pepper-picking robot in the field.