Search

Unsupervised domain adaptation (UDA) methods have become a research hotspot in remote sensing scene classification to reduce dependence on labeled samples. However, most current methods focus on extracting domain invariant features, ignoring the problem of large intraclass differences and the imbalanced sample numbers between categories in remote sensing images. To address these issues, we propose a remote sensing scene domain adaptive method based on middle-layer feature extraction and nuclear norm maximization (MFE-NM). In the MFE module, the middle-layer features of the feature extractor are randomly extracted and processed. Since the receptive field of the middle-layer features is smaller and the resolution is higher, the effective use of the middle-layer features can reduce the impact of image feature heterogeneity caused by large intraclass differences in remote sensing images. In addition, it can be concluded that the constrained nuclear norm can simultaneously improve the prediction diversity and discriminability of the model through theoretical derivation. Therefore, the NM module is proposed to solve the problem of reduced prediction diversity caused by entropy minimization methods when dealing with scene classification problems with imbalanced sample numbers between categories. Extensive experiments and analyses on three public remote sensing datasets demonstrate the effectiveness and competitiveness of our proposed method. [ABSTRACT FROM AUTHOR]

A miniature ionization vacuum sensor (IVS) based on an on-chip SiOx-based tunneling electron source is reported. The vacuum sensor fabricated by microfabrication technologies exhibits a compact multilayered structure with overall dimensions of $13\times 9\times2.7$ mm3, where the electron source chip, Si layer of the electron collector, Si layer of the ion collector, and glass spacers between them are stacked together by an anodic bonding method. Electron impact ionization occurs in a semiclosed cavity through the electron and ion collector layers and glass spacers. Because of the compact structure, low working voltage of SiOx-based tunneling electron sources, and stable electron emission of the electron sources in a poor vacuum, a wide linear detection range from $1.3\times 10^{-2}$ to 133 Pa and a sensitivity of $8.3\times 10^{-4}$ Pa−1 have been demonstrated for the devices. These advantages, including miniature size, a detection range up to the rough vacuum regime, and the capability of batch fabrication with microfabrication technologies, make our IVSs promising in vacuum measurements. [ABSTRACT FROM AUTHOR]

Extensive convolutional neural network (CNN)-based methods have been widely used in remote sensing scene classification. However, the dense operation and huge memory storage of the state-of-the-art models hinder their deployment on low-power embedded devices. In this letter, we propose a mixed-precision quantization method to compress the model size without accuracy degradation. In this method, we propose a symmetric nonlinear quantization scheme to reduce the quantization error. A corresponding three-step training strategy is proposed to improve the performance of the quantized network. Finally, based on the proposed scheme and training strategy, we propose a neural architecture search (NAS)-based quantization bit-width search (NQBS) method. This method can automatically select a bit width for each quantized layer to obtain a mixed-precision network with an optimal model size. We apply the proposed method to the ResNet-34 and SqueezeNet networks and evaluate the quantized networks on the NWPU-RESISC45 data set. The experimental results show that the mixed-precision quantized networks under the proposed method strike a satisfying tradeoff between classification accuracy and model size. [ABSTRACT FROM AUTHOR]

Thermionic electron sources are scaled down to the microscale on a chip and batch fabricated on 4-in silicon wafers by utilizing microfabrication technologies and exploiting carbon nanotubes as microscopic filaments of thermionic electron emission. The microfabricated on-chip thermionic electron sources not only satisfy the metrics of compactness and ease of batch fabrication, but also exhibit the advantages of good performance reproducibility (±6.9% variation over 100 test cycles under a driven voltage of 3.5 V) and high emission stability (fluctuation < 5% for emission current level of ≈10−8 A over 900 s) under a relatively low vacuum condition (10−4–10−2 Pa). Furthermore, to extract electrons and tune emission current, an extraction gate with a mesh is monolithically integrated with the thermionic electron sources using anodic bonding technique. The integrated electron sources exhibit a strong gate controllability and a considerable electron transmission ratio of ≈76% through the extraction gate. All these results make our devices a promising type of on-chip electron source in the applications of miniature vacuum electronic devices/systems. [ABSTRACT FROM AUTHOR]

Recently, remote sensing image scene classification technology has been widely applied in many applicable industries. As a result, several remote sensing image scene classification frameworks have been proposed; in particular, those based on deep convolutional neural networks have received considerable attention. However, most of these methods have performance limitations when analyzing images with large intraclass variations. To overcome this limitation, this letter presents the marginal center loss with an adaptive margin. The marginal center loss separates hard samples and enhances the contributions of hard samples to minimize the variations in features of the same class. Experimental results on public remote sensing image scene data sets demonstrate the effectiveness of our method. After the model is trained using the marginal center loss, the variations in the features of the same class are reduced. Furthermore, a comparison with state-of-the-art methods proves that our model has competitive performance in the field of remote sensing image scene classification. [ABSTRACT FROM AUTHOR]

Object detection in complex optical remote sensing images is a challenging problem due to the wide variety of scales, densities, and shapes of object instances on the earth surface. In this letter, we focus on the wide-scale variation problem of multiclass object detection and propose an effective object detection framework in remote sensing images based on YOLOv2. To make the model adaptable to multiscale object detection, we design a network that concatenates feature maps from layers of different depths and adopt a feature introducing strategy based on oriented response dilated convolution. Through this strategy, the performance for small-scale object detection is improved without losing the performance for large-scale object detection. Compared to YOLOv2, the performance of the proposed framework tested in the DOTA (a large-scale data set for object detection in aerial images) data set improves by 4.4% mean average precision without adding extra parameters. The proposed framework achieves real-time detection for $1024\times 1024$ image using Titan Xp GPU acceleration. 1 https://github.com/WenchaoliuMUC/Detection-of-Multiclass-Objects-in-Optical-Remote-Sensing-Images [ABSTRACT FROM AUTHOR]

In recent times, many efforts have been made to improve remote sensing image scene classification, especially using popular deep convolutional neural networks. However, most of these methods do not consider the specific scene orientation of the remote sensing images. In this letter, we propose the improved oriented response network (IORN), which is based on the ORN, to handle the orientation problem in remote sensing image scene classification. We propose average active rotating filters (A-ARFs) in the IORN. While IORNs are being trained, A-ARFs are updated by a method that is different from the ARFs of the ORN, without additional computations. This change helps IORN improve its ability to encode orientation information and speeds up optimization during training. We also propose Squeeze-ORAlign (S-ORAlign) by adding a squeeze layer to ORAlign of ORN. With the squeeze layer, S-ORAlign can address large-scale images, unlike ORAlign. An ablation study and comparison experiments are designed on a public remote sensing image scene classification data set. The experimental results demonstrate the effectiveness and better performance of the proposed model over that of other state-of-the-art models. [ABSTRACT FROM AUTHOR]

Ship detection is a challenging problem in complex optical remote-sensing images. In this letter, an effective ship detection framework in remote-sensing images based on the convolutional neural network is proposed. The framework is designed to predict bounding box of ship with orientation angle information. Note that the angle information which is added to bounding box regression makes bounding box accurately fit into the ship region. In order to make the model adaptable to the detection of multiscale ship targets, especially small-sized ships, we design the network with feature maps from the layers of different depths. The whole detection pipeline is a single network and achieves real-time detection for a $704 \times 704$ image with the use of Titan X GPU acceleration. Through experiments, we validate the effectiveness, robustness, and accuracy of the proposed ship detection framework in complex remote-sensing scenes. [ABSTRACT FROM PUBLISHER]

Sea–land segmentation is a key step for some important applications of panchromatic remote sensing image processing. However, robust and effective sea–land segmentation for high-resolution panchromatic remote sensing images is still a challenging problem. This letter presents an accurate and robust approach by integrating the improved multiscale normalized cut (IMNcut) method and improved Chan–Vese model for sea–land segmentation. At first, the image is downsampled and segmented into multiple regions by the IMNcut method. Next, the homogeneous regions are merged to obtain a coarse segmentation result. Finally, gray intensity and local entropy features are integrated as discriminants of the improved Chan–Vese model, which is used to obtain the final segmentation result through a low- to high-resolution segmentation scheme. Experimental results performed on several real data sets demonstrate the effectiveness of the proposed model in terms of visual and objective evaluations. [ABSTRACT FROM PUBLISHER]

A technique for reduction of the dc-link capacitance in a capacitor-supported system is presented. The concept is based on connecting a voltage source in series with the dc bus line to compensate the ripple voltage on the dc-link capacitor, so as to make the output have a near zero ripple voltage. Since the voltage compensator processes small ripple voltage on the dc link and reactive power only, it can be implemented with low-voltage devices. The overall required energy storage of the dc-link, formed by a reduced value of dc-link capacitor and the voltage compensator, is reduced, allowing the replacement of popularly used electrolytic capacitors with alternatives of longer lifetime, like power film capacitors, or extending the system lifetime even if there is a significant reduction in the capacitance of electrolytic capacitors due to the aging effect. Comprehensive analysis on the static and dynamic characteristics of the system, and hold-up time requirement will be discussed. The proposed technique is exemplified on an ac–dc–dc power conversion system. Theoretical predictions are favorably verified by experimental results. [ABSTRACT FROM AUTHOR]