Search

Visual tracking is one of the key research fields in computer vision. Based on the combination of correlation filter tracking (CFT) model and deep convolutional neural networks (DCNNs), deep correlation filter tracking (DCFT) has recently become a critical issue in visual tracking because of CFT’s rapidity and DCNN’s better feature representation. However, DCNNs are often complex in structure, which most possibly results in the conflict between the rapidity and accuracy of DCFT. To reduce such conflict, this paper proposes a model mainly including: (1) Based on the pre-pruning network obtained by feature channel importance, an optimal global tracking pruning rate (GTPR) is determined in terms of the contribution of filter channels to tracking response. (2) Based on (GTPR), an alternative convolutional kernel is defined to replace non-important channel kernels, which leads to the further pruning of the feature network. (3) An online updating pruned feature network with a structural similarity index is employed to adapt the model to tracking scene changes. (4) The proposed model was performed on OTB2013; experimental results demonstrate the model can effectively enhance speed with a 45% increment while guaranteeing tracking accuracy, and improve tracking accuracy with a 4% increment when tracking scene changes take place.

This work aimed to develop and evaluate a post-acquisition data processing strategy, referred to as a mass defect filter (MDF), for rapid target the resin glycosides in root of Convolvulus scammonia by setting mass rang and mass defect range from high-resolution MS data. The full-scan mass data were acquired by high-performance liquid chromatography coupled with Q Exactive Plus hybrid quadrupole-orbitrap mass spectrometer that featured high resolution, mass accuracy, and sensitivity. To screen resin glycosides, three parent filter m/z 871, m/z 853, and m/z 869 combined with diagnostic fragment ions (DFIs) approach were applied to remove the interference from complex herbal extract. The targeted components were characterized based on detailed fragment ions. Using this approach, 80 targeted components, including 22 glycosidic acids and 58 resin glycosides were tentatively identified. The present results suggested that the proposed MDF strategy would be adaptable to the analysis of complex system in relevant filed.

The meningococcal meningitis (MM) vaccine reduces the incidence of MM significantly; however, outbreaks still occur in communities with high vaccine coverage. We aimed to analyze the driving factors of infection from a community outbreak. A total of 266 children aged 9 to 15 years old from the three junior high schools of Tongzi county were identified. We documented infection cases using laboratory tests and analyzed attack rates, infection rates and risk factors for transmission. The index case in School A was identified, and the attack rate in School A was 0.03%. Children showed a significantly low infection rate of MenC in School A (13.2% vs. 19.5% in total children, p = 0.002), while exhibiting significantly high infection rates of MenA in School B (44.1% vs. 24.8% in total children, p < 0.001) and MenB in School C (11.1% vs. 4.1% in total children, p = 0.015). The infection rate of MenA for females (30.0%) was higher (p = 0.055) than for males (19.9%). In School A, 63.19% of children were vaccinated against MenC, while in School B the rate was 42.65% and in School C, it was 59.26%. Three male MenC infection cases were detected as breakthrough infection cases in addition to the index case. The findings suggest that the current full-course immunization has limited long-term effectiveness and is inefficient in preventing the transmission of MM among older children.

Timely and rapidly mapping impervious surface area (ISA) and monitoring its spatial-temporal change pattern can deepen our understanding of the urban process. However, the complex spectral variability and spatial heterogeneity of ISA caused by the increased spatial resolution poses a great challenge to accurate ISA dynamics monitoring. This research selected Jinan City as a case study to boost ISA mapping performance through integrating the dual-attention CBAM module, SE module and focal loss function into the Deeplabv3+ model using Sentinel-2 data, and subsequently examining ISA spatial-temporal evolution using the generated annual time-series ISA data from 2017 to 2021. The experimental results demonstrated that (a) the improved Deeplabv3+ model achieved satisfactory accuracy in ISA mapping, with Precision, Recall, IoU and F1 values reaching 82.24%, 92.38%, 77.01% and 0.87, respectively. (b) In a comparison with traditional classification methods and other state-of-the-art deep learning semantic segmentation models, the proposed method performed well, qualitatively and quantitatively. (c) The time-series analysis on ISA distribution revealed that the ISA expansion in Jinan City had significant directionality from northeast to southwest from 2017 to 2021, with the number of patches as well as the degree of connectivity and aggregation increasing while the degree of fragmentation and the complexity of shape decreased. Overall, the proposed method shows great potential in generating reliable times-series ISA data and can be better served for fine urban research.

In the fault diagnosis of UAVs, extremely imbalanced data distribution and vast differences in effects of fault modes can drastically affect the application effect of a data-driven fault diagnosis model under the limitation of computing resources. At present, there is still no credible approach to determine the cost of the misdiagnosis of different fault modes that accounts for the interference of data distribution. The performance of the original cost-insensitive flight data-driven fault diagnosis models also needs to be improved. In response to this requirement, this paper proposes a two-step ensemble cost-sensitive diagnosis method based on the operation and maintenance data of UAV. According to the fault criticality from FMECA information, we defined a misdiagnosis hazard value and calculated the misdiagnosis cost. By using the misdiagnosis cost, a static cost matrix could be set to modify the diagnosis model and to evaluate the performance of the diagnosis results. A two-step ensemble cost-sensitive method based on the MetaCost framework was proposed using stratified bootstrapping, choosing LightGBM as meta-classifiers, and adjusting the ensemble form to enhance the overall performance of the diagnosis model and reduce the occupation of the computing resources while optimizing the total misdiagnosis cost. The experimental results based on the KPG component data of a large fixed-wing UAV show that the proposed cost-sensitive model can effectively reduce the total cost incurred by misdiagnosis, without putting forward excessive requirements on the computing equipment under the condition of ensuring a certain overall level of diagnosis performance.

With the rapid process of both urban sprawl and urban renewal, large numbers of old buildings have been demolished in China, leading to wide spread construction sites, which could cause severe dust contamination. To alleviate the accompanied dust pollution, green plastic mulch has been widely used by local governments of China. Therefore, timely and accurate mapping of urban green plastic covered regions is of great significance to both urban environmental management and the understanding of urban growth status. However, the complex spatial patterns of the urban landscape make it challenging to accurately identify these areas of green plastic cover. To tackle this issue, we propose a deep semi-supervised learning framework for green plastic cover mapping using very high resolution (VHR) remote sensing imagery. Specifically, a multi-scale deformable convolution neural network (CNN) was exploited to learn representative and discriminative features under complex urban landscapes. Afterwards, a semi-supervised learning strategy was proposed to integrate the limited labeled data and massive unlabeled data for model co-training. Experimental results indicate that the proposed method could accurately identify green plastic-covered regions in Jinan with an overall accuracy (OA) of 91.63%. An ablation study indicated that, compared with supervised learning, the semi-supervised learning strategy in this study could increase the OA by 6.38%. Moreover, the multi-scale deformable CNN outperforms several classic CNN models in the computer vision field. The proposed method is the first attempt to map urban green plastic-covered regions based on deep learning, which could serve as a baseline and useful reference for future research.

Saltation and reputation (creep) dominate proppant transport rather than suspension during slickwater fracturing, due to the low sand-carrying capacity of the slickwater. Thus, the interaction parameters between proppants and fracture walls, which affect saltation and reputation, play a more critical role in proppant transport. In this paper, a calibration method for the interaction parameters between proppants and walls is built. A three-dimensional coupled computational fluid dynamics–discrete element method (CFD–DEM) model is established to study the effects of the interaction parameters on proppant migration, considering the wall roughness and unevenly distributed diameters of proppants. The simulation results show that a lower static friction coefficient and rolling friction coefficient can result in a smaller equilibrium height of the sand bank and a smaller build angle and drawdown angle, which is beneficial for carrying the proppant to the distal end of the fracture. The wall roughness and the unevenly distributed diameter of the proppants increase the collision between proppant and proppant or the wall, whereas the interactions have little impact on the sandbank morphology, slightly increasing the equilibrium height of the sandbank.