- 标题
- 摘要
- 关键词
- 实验方案
- 产品
过滤筛选
- 2018
- Conditional Random Fields (CRF)
- Convolutional Neural Network (CNN)
- Fine Classification
- Airborne hyperspectral
- green tide
- Elegant End-to-End Fully Convolutional Network (E3FCN)
- deep learning
- remote sensing
- Moderate Resolution Imaging Spectroradiometer (MODIS)
- Optoelectronic Information Science and Engineering
- Ocean University of China
- Wuhan University
- Central South University
- Hubei University
-
[IEEE 2018 IEEE International Conference on Communications (ICC 2018) - Kansas City, MO (2018.5.20-2018.5.24)] 2018 IEEE International Conference on Communications (ICC) - Cognitive Optical Networks
摘要： Future optical networks will have 103-4 increase in rates and highly granular traffic due to large transactions. Cognitive techniques will provide agile automated fast scheduling of resources, topology changes and agile adaptations for congestion control, load balancing and reconfiguration involving all layers.
关键词： Optical network management and control
更新于2025-09-23 15:22:29
-
[IEEE 2018 25th IEEE International Conference on Image Processing (ICIP) - Athens, Greece (2018.10.7-2018.10.10)] 2018 25th IEEE International Conference on Image Processing (ICIP) - Sketchpointnet: A Compact Network for Robust Sketch Recognition
摘要： Sketch recognition is a challenging image processing task. In this paper, we propose a novel point-based network with a compact architecture, named SketchPointNet, for robust sketch recognition. Sketch features are hierarchically learned from three miniPointNets, by successively sampling and grouping 2D points in a bottom-up fashion. SketchPointNet exploits both temporal and spatial context in strokes during point sampling and grouping. By directly consuming the sparse points, SketchPointNet is very compact and efficient. Compared with state-of-the-art techniques, SketchPointNet achieves comparable performance on the challenging TU-Berlin dataset while it significantly reduces the network size.
关键词： point set,stroke pattern,Sketch recognition,deep neural network
更新于2025-09-23 15:22:29
-
Precise Performance Analysis of Dual-Hop Mixed RF/Unified-FSO DF Relaying with Heterodyne Detection and Two IM-DD Channel Models
摘要： This paper provides precise performance analysis of the dual-hop mixed radio frequency (RF)/unified free space optical (FSO) decode-and-forward (DF) relaying system, in which the heterodyne detection (HD) and the intensity modulation-direct detection (IM-DD) are taken into account for FSO detection. To this end, we derive closed-form expressions for the outage probability, average bit error rate (BER), and the ergodic channel capacity of this system. In this analysis, we utilize, for the first time as per our knowledge, a precise channel capacity result for the IM-DD channel. Moreover, this is the first time that not only the (IM-DD input-independent) but also the (IM-DD cost-dependent) AWGN channel is considered in such system analyses. Additionally in this study, we assume that the first hop (RF link) follows Nakagami-m fading, and the second hop (FSO link) follows Málaga (M) turbulence with pointing errors. These fading and turbulence models contain other models (such as Rayleigh and Gamma-Gamma) as special cases, thus our analyses can be seen as a generalized one from the RF and FSO fading models point of view. Also, in BER derivation, we assume that the modulation schemes in the two hops can be different, since not all modulation schemes are suitable for IM-DD FSO links. In addition, the system performance is investigated asymptotically at high signal to noise ratios (SNRs). This investigation leads to new non-reported coding gain and diversity order analyses of such system. Interestingly, we find that in the FSO hop, at high transmitted powers, all the considered FSO detectors result in the same diversity order. Furthermore, we provide simulation results that verify the accuracy of the obtained analytical and asymptotic expressions.
关键词： Nakagami-m fading,Málaga (M) fading,HD,DF,heterodyne detection,Mixed RF/FSO relay network,IM-DD,decode-and-forward,intensity modulation-direct detection
更新于2025-09-23 15:22:29
-
A Compact X-Band Vector Network Analyzer for Microwave Image Sensing
摘要： This work develops a compact and portable X-band vector network analyzer (VNA) for low-cost microwave image sensing applications. Since significant local oscillator (LO) injection pulling and poor LO phase noise performance may reduce the accuracy of measurement, the developed VNA uses the single-conversion technique and the phase noise cancellation technique to suppress the injection pulling effect and the LO phase noise, respectively. A hybrid phase detection algorithm that includes arctangent, arcsine and arccosine functions is proposed to overcome the bottleneck of the distortion of conventional quadrature phase detection in some phase regions. Experimental results demonstrate that the X-band microwave image sensing system that uses the developed VNA, which is highly compact and portable, can effectively yield a contour image of bones in a chicken wing and pork ribs.
关键词： transceiver,microwave image sensing,vector network analyzer,phase noise,frequency synthesizer
更新于2025-09-23 15:22:29
-
Domain Adaptation With Discriminative Distribution and Manifold Embedding for Hyperspectral Image Classification
摘要： Hyperspectral remote sensing image classification has drawn a great attention in recent years due to the development of remote sensing technology. To build a high confident classifier, the large number of labeled data is very important, e.g., the success of deep learning technique. Indeed, the acquisition of labeled data is usually very expensive, especially for the remote sensing images, which usually needs to survey outside. To address this problem, in this letter, we propose a domain adaptation method by learning the manifold embedding and matching the discriminative distribution in source domain with neural networks for hyperspectral image classification. Specifically, we use the discriminative information of source image to train the classifier for the source and target images. To make the classifier can work well on both domains, we minimize the distribution shift between the two domains in an embedding space with prior class distribution in the source domain. Meanwhile, to avoid the distortion mapping of the target domain in the embedding space, we try to keep the manifold relation of the samples in the embedding space. Then, we learn the embedding on source domain and target domain by minimizing the three criteria simultaneously based on a neural network. The experimental results on two hyperspectral remote sensing images have shown that our proposed method can outperform several baseline methods.
关键词： neural network,hyperspectral image classification,maximum mean discrepancy (MMD),remote sensing,Domain adaptation,manifold embedding
更新于2025-09-23 15:22:29
-
[IEEE 2018 5th NAFOSTED Conference on Information and Computer Science (NICS) - Ho Chi Minh, Vietnam (2018.11.23-2018.11.24)] 2018 5th NAFOSTED Conference on Information and Computer Science (NICS) - Joint Image Deblurring and Binarization for License Plate Images using Deep Generative Adversarial Networks
摘要： Image deblurring is a highly ill-posed inverse problem where it aims to estimate the sharp image from blurred image with or without the knowledge about the blurring process. Despite the success of model-based image deblurring methods where the deconvolution is a major step to recover the sharp image, its usage in practice is still limited, especially when many factors such as object motion, camera motion, non-uniform sensitivity of the imaging device contribute to imaging process. In automatic license plate recognition (ALPR) of moving vehicle, the blurred image severely reduces the accuracy of recognition. Meanwhile, though the binarized image of license plate has an important role in ALPR systems, its accuracy is largely affected by the blurred image. In this paper, we use a deep architecture based on Generative Adversarial Networks to jointly perform image deblurring and image binarization for license plate images. Our model directly maps from blurred image to binary image without going through the deblurring as in conventional method. The proposed method is benefited from the fact that the ground-truth, sharp license plates are difficult to acquire for moving object, while the accurate binary images can be manually derived from blurred ones.
关键词： Inverse Problems,License Plate Deblurring,Image Deblurring,Generative Adversarial Network (GAN)
更新于2025-09-23 15:22:29
-
[IEEE 2018 OCEANS - MTS/IEEE Kobe Techno-Ocean (OTO) - Kobe, Japan (2018.5.28-2018.5.31)] 2018 OCEANS - MTS/IEEE Kobe Techno-Oceans (OTO) - Deep Neural Network for Source Localization Using Underwater Horizontal Circular Array
摘要： This paper applies deep neural network (DNN) to source localization in a shallow water environment using underwater horizontal circular array. The proposed method can discriminate source locations in a three-dimension space. The proposed method adopts a two-stage scheme, incorporating feature extraction and DNN analysis. In feature extraction step, the eigenvectors corresponding to the modal signal space, which are shown to be able to represent the propagating modes of the sound source, are extracted as the input feature of DNN. The eigenvectors are obtained by applying eigenvalue decomposition (EVD) of the covariance matrix of the received multi-channel signal. In DNN analysis step, time delay neural network (TDNN) is used to construct the mapping relationship between the eigenvectors and the source locations, because it is capable of making use of sequential information of the source signal. The output of the network is the source location estimates. Several experiments are conducted to demonstrate the effectiveness of the proposed method.
关键词： shallow water environment,modal signal space,Deep neural network,horizontal circular array,source localization
更新于2025-09-23 15:22:29
-
[IEEE 2018 China International SAR Symposium (CISS) - Shanghai (2018.10.10-2018.10.12)] 2018 China International SAR Symposium (CISS) - An Automatically Steering Optical Beam-Forming Network for Phased Array Antenna Based on Dense Wavelength Division Multiplexing
摘要： It is proposed an automatically steering optical beam-forming network (OBFN), which is consisted of an optical fiber loop structure. The loop structure is composed by an optical switch, an optical fiber splitter, and an optical true time delay lines based on dense wavelength division multiplexing (DWDM). The channel number of the DWDM is matched with the number of the phased array antennas (PAA). The true time delay difference between two adjacent channels is set as a basic step. And the optical wave modulated by radio frequency (RF) signal can run into the loop and suffer increased delay with increased circles. Thus the PAA is steered automatically without additional controlling and programming. The performance of this design is analyzed with its maximal circle numbers and the splitting ratio of the optical splitter in theory. The concept-proof experiments with 8 optical channels for DWDM are carried out and the simulation of the PAA radiation pattern is given.
关键词： optical switch,optical beam-forming network,optical fiber loop,optical controlled phased array radar,wavelength division multiplexing
更新于2025-09-23 15:22:29
-
Achieving Super-Resolution Remote Sensing Images via the Wavelet Transform Combined With the Recursive Res-Net
摘要： Deep learning (DL) has been successfully applied to single image super-resolution (SISR), which aims at reconstructing a high-resolution (HR) image from its low-resolution (LR) counterpart. Different from most current DL-based methods, which perform reconstruction in the spatial domain, we use a scheme based in the frequency domain to reconstruct the HR image at various frequency bands. Further, we propose a method that incorporates the wavelet transform (WT) and the recursive Res-Net. The WT is applied to the LR image to divide it into various frequency components. Then, an elaborately designed network with recursive residual blocks is used to predict high-frequency components. Finally, the reconstructed image is obtained via the inverse WT. This paper has three main contributions: 1) an SISR scheme based on the frequency domain is proposed under a DL framework to fully exploit the potential to depict images at different frequency bands; 2) recursive block and residual learning in global and local manners are adopted to ease the training of the deep network, and the batch normalization layer is removed to increase the flexibility of the network, save memory, and promote speed; and 3) the low-frequency wavelet component is replaced by an LR image with more details to further improve performance. To validate the effectiveness of the proposed method, extensive experiments are performed using the NWPU-RESISC45 data set, and the results demonstrate that the proposed method outperforms state-of-the-art methods in terms of both objective evaluation and subjective perspective.
关键词： residual learning,wavelet transform (WT),remote sensing image,super resolution,Recursive network
更新于2025-09-23 15:22:29
-
[IEEE 2018 41st International Conference on Telecommunications and Signal Processing (TSP) - Athens, Greece (2018.7.4-2018.7.6)] 2018 41st International Conference on Telecommunications and Signal Processing (TSP) - Modeling Electromagnetic Wireless Nanonetworks in Terahertz Band within NS-3 Platform
摘要： The wireless nanosensor network paradigm has seen a dramatic increase over the last decade. The envisioned concept uses the integrated machines (devices) at the nano-scale level. Those devices interact on a cooperative basis by means of principles known in wireless communication networks. Today, the design of the protocol stack for wireless nanosensor networks represents the crucial issue to be addressed. Currently available tools only support molecular-based approaches without the ability to account for the relevant impact that electromagnetic communications may have in this field. To cover this white spot, in this paper, the theoretical comparison of available simulation tools is given. Further, we focus on the Nano-Sim tool and create the scenario for wireless sensor networks (WNSN) based on electromagnetic communication in terahertz band.
关键词： Nanonetworks,Network Simulator 3,Simulation tools,Performance evaluation,Molecular communication
更新于2025-09-23 15:22:29