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]