Search

Efficient detection of pepper clusters can be crucial to realize the automated harvesting in the development of pepper industry. However, the existing detection of pepper cluster cannot fully meet the large-scale in recent years, due to the low efficiency, generalization, and real-time algorithm. In this study, an improved YOLOv5s model was proposed to accurately detect the pepper clusters in real time. 400 images were collected from the Xuande Pepper Industrial Park, Qinglong County, Guizhou Province, Qianxinan Buyi and Miao Autonomous Prefecture, Guizhou Province, China. 148 images were also downloaded from the Internet, and then screened to enhance data diversity. The collected 548 images were then labeled using the LabelImg tool. In addition, the data enhancement was performed on each image and labeled bounding box. Two new images were randomly generated using random rotation and brightness adjustment. As such, a total of 1644 images were obtained as the dataset. Firstly, the EfficientViT network was optimized using the lightweight convolutional neural network (CNN) MobileNetV3 Block Convolution (MBConv) module and the ReLU with lightweight self-attention mechanism. CSPDarkNet53 network was used to replace the backbone of YOLOv5s. The global receptive field of model was enhanced to extract the important features. The better performance was suitable for the targets with the different scales, shapes, and background information. Secondly, Optimal Transport Assignment (OTA) was selected as the label assignment strategy. The optimal label assignment plan was obtained from the global perspective to achieve the effective label assignment. The robustness and accuracy of the model were improved for the complex scenes and target distribution. The WIoU loss function was also used as the bounding box localization of the detector, instead of the CIoU one. At the same time, the high-quality anchor frames were achieved to generate the benefit gradients for the better overall performance of the detector. A common experiment of target detection was performed on a homemade dataset, in order to verify the effectiveness of the improved model. The experimental results show that the improved model was achieved in a mean accuracy (mAP) of 97.3%, a parameter count of 5.9 M, and a detection speed of 131.6 frames per second (FPS). Specifically, the mAP and detection speed of the improved YOLOv5s model increased by 1.9 percentage points, and 14.5%, respectively, whereas, the number of parameters decreased by 15.7%, compared with the original. In addition, the mAP of the improved YOLOv5s model was 8, 16.9, 8.6, and 1.5 percentage points higher than that of EffcientDet-D1, SSD512, RetineNet-R50, and YOLOXs, respectively. The better performance of the improved YOLOv5s was achieved in terms of detection accuracy, detection speed, and number of model parameters. Therefore, the improved YOLOv5s model can be expected to accurately and rapidly detect the pepper clusters. [ABSTRACT FROM AUTHOR]

A shale lithofacies scheme is commonly used to characterize source rock reservoirs of the Lower Cambrian Niutitang Formation. However, this classification ignores that individual components such as quartz may have different origins, potentially affecting reservoir quality. The main objective of this article is, therefore, to present a refined scheme for lithofacies and an image processing workflow for the detection of quartz types in the Niutitang Formation shales from the Jiumen outcrop in the Guizhou Province (Upper Yangtze Basin, SW China). In order to do so, a combination of bulk density, optical and scanning electron microscopy and image analysis was used. The shale lithology was macroscopically classified into seven major categories and nineteen subcategories. Subsequently, the shales were investigated at the microscopic level, mainly focusing on quartz types and microstructural variations. Afterwards, the workflow to calculate the weight per unit volume (1 cm3) of the quartz types was presented, i.e., firstly, by calculating the weight of mineral matter by subtraction of the measured weight of organic matter from the bulk shale; secondly, by calculating the weight of total quartz in bulk shale from the weight of mineral matter and its proportion calculated from X-ray diffraction data; thirdly, by calculating the weight of detrital quartz and non-detrital quartz with energy dispersive X-ray mapping, image processing and quartz density; finally, by calculating the weight of clay-sized quartz by subtracting of the weight of detrital and non-detrital quartz from the weight of the total quartz. The bulk quartz content was found to be dominated by clay-sized quartz, which may mainly control the mesopore volume available for gas storage and, hence, the shale gas reservoir development. [ABSTRACT FROM AUTHOR]

Winter fallow farmland is increasing dramatically in some regions in China. Our goal was three-fold: (1) to develop a consistent procedure to identify winter fallow farmland from satellite images; (2) to examine the driving factors of winter fallow farmland; and (3) to identify additional determinants affecting the spatial distribution of winter fallow farmland. We applied geographically weighted regression to examine the spatial interactions of these driving factors. High percentages of winter fallow farmland in the north-eastern region were largely attributed to elevation, income, farmland area, and slope. Geography had a strong impact on the occurrence of fallow farmland. [ABSTRACT FROM AUTHOR]

Monitoring of subgrade settlement in railway and highway helps to maintain traffic safety and reduce infrastructure losses. When an excess subgrade settlement is detected, maintenances of the unqualified subgrade will be processed in time, and early warning of constructions will be processed to prevent the occurrence of safety accident. In this article, a noncontact, real-time, and unattended system based on optical method is introduced to monitor the subgrade settlement remotely. Several high-power infrared LED targets are mounted on the subgrade and they will move as the subgrade subsides. The movements of the LED targets are detected by an optical detection device based on the principle of optical imaging. The displacement data is remotely transmitted to a server for analysis via GPRS. The remote monitoring system has been applied to the monitoring of subgrade settlement of Zhensheng highway in Guizhou province of China in 2014. This technology helped to detect the subgrade settlement that was caused by the construction of Beiyinpo railway tunnel. Four test points on road surface were monitored at a sampling rate every 20 minutes. The effectiveness of the system has been verified by the practical application. [ABSTRACT FROM AUTHOR]