Matching suitability analysis is a key issue of INS/SAR integrated navigation mode. The existing suitability area selection methods use the simulated real-time image to calculate the matching probability of the scene area and further label it "suitability" or "unsuitability". If the imaging mode of the simulated image is the same as that of the real image, the suitability area selection model based on the simulated real-time image works well. Otherwise, the model is impractical. In order to address this issue, a novel method is proposed in this paper. The sample dataset is built on the actual flight real-time images, and a hybrid feature selection method based on D-Score and SVM is used to select the suitability features and build the suitability area selection model simultaneously. Experimental results show that the consistency between the prediction results of the model and the ones experts label reaches 81.92%.
In order to study the effect of surface roughness on the Elastohydrodynamic Lubrication (EHL) performance of cylindrical roller bearing, an EHL model of cylindrical roller bearing with three dimensional surface cosine roughness based on finite length line contact theory is established.The EHL performance of cylindrical roller bearing is calculated by the Finite Difference Method (FDM) program, with which the effects of surface cosine roughness amplitude, wavelength and texture angle on EHL performance of cylindrical roller bearing are analyzed.The numerical results show that the roughness amplitude, wavelength and texture angle have great influence on the EHL performance in the contact area.The increase of roughness amplitude and wavelength in a reasonable range is beneficial to the enhancement of EHL performance of the cylindrical roller bearing, and the transverse roughness is more favorable to enhance the bearing capacity and reduce the friction coefficient.
Segmentation is the key step in auto-interpretation of high-resolution spaceborne synthetic aperture radar (SAR) images. A novel method is proposed based on integrating the geometric active contour (GAC) and the support vector machine (SVM) models. First, the images are segmented by using SVM and textural statistics. A likelihood measurement for every pixel is derived by using the initial segmentation. The Chan-Vese model then is modified by adding two items: the likelihood and the distance between the initial segmentation and the evolving contour. Experimental results using real SAR images demonstrate the good performance of the proposed method compared to several classic GAC models.
The frequent vibration faults of the feed water pump in large-scale power plants are diagnosed by the integrated neural network based on MATLAB.The integrated neural network for fault diagnosis is established with individual neural network and information integration.The strategies and principles for the realization and formation of integrated neural network are analyzed and a case which is about the fault diagnosis of the feed water pump is given to prove the efficiency of the integrated neural network for fault diagnosis in feed water pump.
A method for accurate fault location on a distribution line with branches using the C-type of traveling wave signal and PNN is presented. The aim is to combine different location methods to improve the accuracy of fault location. In this method, the first step is determining the fault distance by C-type of traveling wave location method, then because branches which have the same distance to the busbar may be more than one, so using PNN neural network's pattern recognition feature to further determine the fault branch, which can achieve precise fault location. Both theoretical analyses and simulation show that this composite location method can be used to determine the single-phase-to-earth fault location accurately in the distribution network.
Offshore and inland river ship detection has been studied on both synthetic aperture radar (SAR) and optical remote sensing imagery. However, the classic ship detection methods based on SAR images can cause a high false alarm ratio and be influenced by the sea surface model, especially on inland rivers and in offshore areas. The classic detection methods based on optical images do not perform well on small and gathering ships. This paper adopts the idea of deep networks and presents a fast regional-based convolutional neural network (R-CNN) method to detect ships from high-resolution remote sensing imagery. First, we choose GaoFen-2 optical remote sensing images with a resolution of 1 m and preprocess the images with a support vector machine (SVM) to divide the large detection area into small regions of interest (ROI) that may contain ships. Then, we apply ship detection algorithms based on a region-based convolutional neural network (R-CNN) on ROI images. To improve the detection result of small and gathering ships, we adopt an effective target detection framework, Faster-RCNN, and improve the structure of its original convolutional neural network (CNN), VGG16, by using multiresolution convolutional features and performing ROI pooling on a larger feature map in a region proposal network (RPN). Finally, we compare the most effective classic ship detection method, the deformable part model (DPM), another two widely used target detection frameworks, the single shot multibox detector (SSD) and YOLOv2, the original VGG16-based Faster-RCNN, and our improved Faster-RCNN. Experimental results show that our improved Faster-RCNN method achieves a higher recall and accuracy for small ships and gathering ships. Therefore, it provides a very effective method for offshore and inland river ship detection based on high-resolution remote sensing imagery.
In unmanned vehicle perception, dynamic object classification is applied to classify objects accurately and timely, providing decision-making for obstacle avoidance and planning. Low-resolution LiDAR is one of the most important sensors for this task. Unfortunately, the existing approaches perform unsatisfactorily due to the huge domain gap between low-resolution and high-resolution point cloud classification. Some schemes try to reduce the gap by fusing multi-scan information through SLAM or completing single-scan point clouds. However, these methods rely on high positioning accuracy or the wholeness of object data. To this end, differently, we propose a dynamic object classification method of low-resolution data from the perspective of time-series fusion. By modeling time series of sparse data, we indicate change rules of separate classification models for object representation. Subsequently, based on ensemble learning, our method performs feature-level fusion on multiple networks to exploit their different expression capabilities. Finally, we utilize long short-term memory to gradually classify dynamic objects. Besides, we also propose a dataset of the low-resolution point clouds and manually annotate the ground truth, which contains abundant samples of cars, pedestrians, and motorcycles. Through testing actual low-resolution data, the accuracy of our method is verified to improve a lot than the state-of-the-art approaches.
BP Neural network classifier based on Levenberg-Marquardt (L-M) algorithm and its application to remote sensing image classification is discussed in this paper. L-M algorithm is a combination of gradient method and Gauss-Newton method. With the aid of the approximate second derivative, the L-M algorithm is more efficient than the gradient method. Concerned with the training process and accuracy, the L-M algorithm is superior to vary-learning\|rate BP method.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)