Search

Cotton bud is one of the most important cash crops with many uses, such as the textile and cotton fabric raw material. However, manual cotton topping cannot fully meet the large-scale production in recent years, due to the efficiency and labor costs. Intelligent mechanical topping can be expected to serve as an inevitable trend during cotton topping. There is a high demand to accurately identify the cotton top bud under the complex environment (such as light and shadow), particularly for the various shape characteristics of cotton top core in the process of cotton cap removal. In this study the accurate recognition was proposed to locate the cotton top bud in the complex environment using an improved YOLOv5s. A dataset was also constructed to contain 3103 cotton top buds with different morphological characteristics under a complex environment. Three categories were divided: single, multi-plant and screened top bud under different occlusion areas, weather and light conditions. Systematic training and analysis were then performed on the data. An improved YOLOv5s model was proposed to reduce the error and leakage detection for the sufficient features of small targets. Multi-scale target features were also effectively extracted using only three detection heads in the original YOLOv5s. At the same time, the ideal extraction of the improved YOLOv5s was obtained with the deepening of the network layer. The object detection and CPP-CBAM attention mechanism were first added to the original structure, in order to improve the shallow and deep feature fusion rate. Secondly, the regression of prediction frame was enhanced to avoid the information loss of the real frame. The loss function SIOU boundary frame regression was added to further accelerate the prediction frame regression speed for the detection accuracy. The SIOU loss function was introduced by the vector angle between the real and predicted frame including angle, distance, and shape loss function. As such, the aspect ratio between the predicted and real frame was considered in the CIOU loss function with the direction between them in the SIOU. The high accuracy of recognition rate was obtained on the top bud, resulting in the less degrading into an IOU loss function. In addition, an accurate identification was performed on the cotton top bud that was seriously obscured by the leaves. The results show that the average accuracy (mAP) reached 92.8% for the recognition of cotton top bud by the improved model. Furthermore, the average accuracy was improved by 2.1, 3.3, 2, and 2.4 percentage points, respectively, compared with Fast R-CNN, YOLOv3, YOLOv5s, and YOLOv6. The improved detection model can be expected to accurately and efficiently identify the cotton top bud under a complex environment in real time. The small size of the model parameters and the high identification speed were suitable for the migration deployment of cotton topping machinery, and the operation of the laser topping robot. The finding can also provide technical and theoretical support to the subsequent operation of cotton laser topping machines, particularly for the mechanized real-time topping. [ABSTRACT FROM AUTHOR]

Safflower silk is one of the most important cash crops in the medical treatment and dye. The manual picking of safflower silk cannot fully meet the large-scale production at present. The mechanized harvesting can be expected to improve the safflower harvesting efficiency and labor cost-saving in the industrial planting. The complex environmental factors have made great difficulty to accurately identify and locate the safflower during mechanical picking, including the natural environment (such as the light and shelter), and the safflower characteristics (such as the small and dense target, as well as the different maturity). In this study, an improved YOLOv7 model was proposed to rapidly and accurately locate the safflower recognition in the complex environment. 1500 safflower images were established to divide into three types of samples, silk, bulb, and decay. The small target was found in the datasets with uneven sample size, especially the data of decay. The safflower sample dataset was produced to build the complex environment data for the real picking. Firstly, the Swin Transformer attention mechanism was added to the YOLOv7 network model, in order to improve the detection accuracy of the model for each classification sample, and the ability of the backbone network, especially to extract the small target features. Secondly, the Focal Loss function of the multi-classification was improved in the recognition rate of unbalanced samples under multi-class tasks, particularly for the target confidence loss and classification loss. The attenuation parameters γ was adjusted to balance the sample. The attenuation parameters were determined after experimental verification. Finally, the safflower detection network model was designed to meet the real-time and accurate detection requirements under the complex environment. The test results show that the best performance of the model was achieved in the attenuation parameters of 1.0, where the position of Swin Transformer was the layer 50. The average precision of the improved model reached 88.5% in each category sample, which was 7.0 percentage points higher than before. The average detection accuracy of the unbalanced category sample decay was 15.9 percentage points higher. Compared with the Faster RCNN model, the detection speed increased by three times, while the average accuracy increased by 9.7 percentage points; Compared with the Deformable DETR model, the detection speed increased by about 5 times, and the average accuracy increased by 16.5 percentage points. The improved model performed the best, in terms of the detection efficiency, detection speed, and model size. The improved model can also be expected to accurately detect the safflower, indicating the smaller parameters and the faster recognition speed suitable for the migration deployment on the safflower picking machinery. The finding can provide the technical support for the mechanized picking in real time. In the future research, the balance between species can be promoted to expand the number of samples from the data level in the harvesting machinery. [ABSTRACT FROM AUTHOR]

Leaf diseases have a severe threat to the quality and yield of grapes. However, there is often difficulty in the disease detection and low application rate of convolutional neural network (CNN) in a complicated field environment. In this study, an accurate and intelligent detection system was established to realize the strong robustness and real-time performance for grape leaf diseases using transfer learning and an updated CNN model. Firstly, 1990 images were captured for the healthy leaves and five types of infected leaves from field conditions. The combined datasets of PlantVillage and AI Challenger were used to pre-train the VGG16 network for the fully trained parameters. Secondly, the batch normalization, global average pooling layer, and Center Loss function were utilized to modify the structure of the pre-trained VGG16 network, where there was no change in the parameters of the thirteen front convolutional layers and pooling layers. The updated CNN was fine-tuned with the augmented images of grape leaves from field conditions. Stochastic gradient descent (SGD) and adaptive moment estimation (Adam) optimizers were adopted at the initial learning rates of 0.01 and 0.001 in the phase of fine-tuning for experimental comparison. Thirdly, different equilibrium parameters of Center Loss function were utilized in Softmax classification layer for optimal performance. The updated CNN model was also compared with the state-of-the-art models. Finally, the optimal CNN model was deployed in mobile phones to carry out in field condition. The experimental results showed that the updated model using Adam optimizer behaved with a higher accuracy and more stable performance than those using the SGD in the fine-tuning training phase. There were a higher accuracy, a lower loss value, and smaller vibration in the trained model with a small initial learning rate of 0.001 than those with a larger initial learning rate of 0.01, indicating that a smaller learning rate was more reasonable for fine-tuning training. In addition, the accuracy of the model was improved by the equilibrium parameter with a certain range in a Center Loss function. When the equilibrium parameter was set as 0.12, optimal performance of the updated CNN model was achieved at the initial learning rate of 0.001, where the average classification precision was 0.980 0, the recall was 0.980 1, the F1 score was 0.980 1, the average accuracy was 98.02%, and the testing time per image was 0.327 s. The accuracy of updated CNN increased by 2.82%, while the detection time was reduced by 66.8%, and the number of parameters decreased by 83.4%, compared with the original VGG16 network. The comprehensive performance of the updated VGG16 model was also better than that of AlexNet, ResNet50, and Inception v3 models, indicating obvious advantages in the accuracy, weight space occupation, and testing time for the detection of grape leaf diseases. It infers that the Batch normalization layer can speed up the learning process, whereas, the Global average pooling layer without fully connected layers can greatly reduce the number of weight parameters of the model. Center Loss function improved the ability of fine classification. After deployed into smart phone platform, the detection system maintained an accuracy of 95.67% and detection time of 0.357 s per image for the portable and intelligent diagnostics of grape leaf diseases. The transfer learning provided the possibility of quickly acquiring high-performance model under the condition of small datasets. The finding can provide precise guide for the prevention and control of grape diseases in fields. [ABSTRACT FROM AUTHOR]