- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Pr-Based Sar Reconstruction Autofocus Algorithm for Persistent Surveillance Change Detection
摘要： Random phase noises arising from frequency jitter of transmit signal and atmospheric turbulence result in corrupted synthetic aperture radar (SAR) imagery, which in turn degrades change detection (CD) performance. In this paper, a phase retrieval (PR) based SAR reconstruction autofocus framework by exploiting the hidden convexity is proposed with the goal of achieving reliable persistent surveillance CD. Firstly the original non-convex quartic SAR reconstruction is reformulated as a convex quadratic program. Under the minimum phase assumption, the auto-correlation retrieval-Kolmogorov factorization (CoRK) algorithm is then utilized to optimally and efficiently retrieve the underlying SAR reflectivity. The devised scheme possesses effective capabilities of phase noise mitigation, thus has a superior CD performance. Experimental results are provided to verify the effectiveness of the proposed method.
关键词： Synthetic aperture radar (SAR),hidden convexity,change detection (CD),phase retrieval (PR),random phase noises
更新于2025-09-23 15:21:21
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - The Influence of Sar Image Quantization Method on Detection Precision
摘要： In this paper, we combine deep learning with radar image processing to explore the influence of different quantization methods on the final detection performance of the radar image subjected to strong points after different quantification methods. Considering problems caused by the characteristics of SAR image data, the LeNet network model in deep learning was used to train and verify the quantified radar images respectively. The impact of different quantization methods on SAR image classification and detection was analyzed. The most friendly way to quantify the actual radar images was explored. Radar image target detection based on depth learning provides the basis for exploration.
关键词： detection,SAR Image,deep learning,quantitative methods
更新于2025-09-23 15:21:21
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Data Augmentation with Gabor Filter in Deep Convolutional Neural Networks for Sar Target Recognition
摘要： Deep Convolutional Neural Networks (DCNNs) have been widely used in target recognition due to the availability of large dataset. The DCNNs have the ability of learning highly hierarchical image feature, which provides great opportunity for synthetic aperture radar automatic target recognition (SAR-ATR). However, when the DCNNs were directly applied to the SAR target recognition, it will result in severe overfitting due to limited SAR image training data. To overcome this problem, we present a Gabor-Deep Convolutional Neural Networks (G-DCNNs). Instead of training a deep network with limited dataset of raw SAR images, Gabor features for multi-scale and multi-direction were used for data augmentation as training dataset at first. Then based on this data augmentation method, we designed a DCNNs for SAR image target recognition. Experimental results on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset prove the effectiveness of our method.
关键词： SAR,Gabor filter,DCNNs,data augmentation
更新于2025-09-23 15:21:21
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Data Augmentation Method of SAR Image Dataset
摘要： Large-scale high-quality, standardized, measurable and accurate data is the key to promote the progress of the algorithm in the radar remote sensing. Data scaling is a widespread technology that increases the size of a labeled training set dataset through specific data transformations. Synthetic Aperture Radar (SAR) image simulators based on computer-aided mapping models play an important role in SAR applications such as automatic target recognition and image interpretation, but the accuracy of this simulator is due to geometric errors and simplification of electromagnetic calculations. In order to achieve a SAR image datasets with the known target and azimuth angles, we can generate the desired image directly from a known image database. We can realize the augmentation of SAR image data set through linear synthesis and Generative Adversarial Networks, which can generate SAR images for the specified azimuth.
关键词： generative adversarial networks,SAR image,linear synthesis
更新于2025-09-23 15:21:21
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - High Resolution SAR Image Classification with Deeper Convolutional Neural Network
摘要： Deeper architectures are proven to be beneficial for the classification performance obviously in computer vision field. Inspired by this, deep CNNs are expected to make progress in the SAR target classification problem as well. However, it is hard to train deeper CNNs for SAR images. Such CNNs have millions of parameters to be determined in the network (for example the VGGNet has more than 130 million parameters), hence large-scale dataset is indispensable when training a deep CNN. But there is no large-scale annotated SAR target dataset, and data acquisition and annotation is much more costly for SAR images. With inadequate data, the network is easy to be overfitting. Several methods based on deep learning have been proposed for SAR image classifications, but they cannot get rid of the aforementioned data limitation of labelled SAR images. To solve this problem, this paper proposes a microarchitecture called CompressUnit (CU). With CU, we design a deeper CNN. Compared with the network with the fewest parameters for SAR image classification in literature so far, our network is 2X deeper with only about 10% of parameters. In this way, we get a deeper network with much fewer parameters. This network is easier to be trained with limited SAR data and is more likely to get rid of overfitting.
关键词： Deeper CNN,CompressUnit,SAR images
更新于2025-09-23 15:21:21
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Imaging of Moving Target for Cooperative Sar Between High-Orbit and Low-Orbit Satellites
摘要： When synthetic aperture radar (SAR) imaging is applied to observe ground scene containing a moving target, the imagery of moving target will be typically smeared due to range cell-migration and Doppler spectrum broadening caused by the target motions, especially for the accelerating targets within a long observation time. To eliminate these effects, a novel imaging algorithm using cooperative between SAR under high-orbit and low-orbit satellites is proposed. The range migration including range walk and range curvature within the coherent integration period has been corrected via the third-order keystone transform. Then, by estimating and compensating the phase errors and the fold factor terms, the target’s resolution is improved and the motion parameters are correctly estimated. The effectiveness of the proposed algorithm is demonstrated by simulations.
关键词： clutter suppression,Ground moving target detection (GMTI),space-borne SAR imaging,third-order keystone transform
更新于2025-09-23 15:21:21
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Digital Beamforming Based RFI Mitigation for Synthetic Aperture Radar
摘要： An increasing challenge for P-band Synthetic Aperture Radar (SAR) is Radio Frequency Interference (RFI). RFI results in image distortions and degrades the derived science products. This makes it critical to apply RFI removal techniques to restore the image quality. New advanced techniques can be achieved with Digital Beamforming (DBF) radars such as EcoSAR. In this paper, we present a Range-Dependent Time Minimum Variance Distortionless Response (RDTMVDR) Beamformer and apply it to EcoSAR flight data during post-processing. The antenna pattern (AP) is adaptively changed for each range line which increases the RFI suppression compared to a fixed AP for each pulse. The interferometric image quality is assessed before and after RFI suppression.
关键词： RFI,SAR,Digital Beamforming
更新于2025-09-23 15:21:21
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Achieving Sar Target Configuration Recognition By Combining Sparse Graph And Locality Preserving Projections
摘要： Synthetic aperture radar (SAR) target configuration recognition is a challenging task, and the key point is to realize effective feature extraction. An algorithm combing the advantages of sparse graph and locality preserving projections (LPP) is proposed to achieve SAR target configuration recognition. Taking the merits of sparse representation (SR) into consideration, an affinity matrix is established to realize effective structure preserving of the dataset. Besides, the problem of matrix singularity in LPP is effectively resolved by diagonal loading. Experimental results on the moving and stationary target acquisition and recognition (MSTAR) database validate the effectiveness and superiority of the proposed algorithm.
关键词： Synthetic aperture radar (SAR) images,sparse representation (SR),locality preserving projections (LPP),target configuration recognition
更新于2025-09-23 15:21:21
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Speckle Noise Reduction of Time Series Sar Images Based on Wavelet Transform and Kalman Filter
摘要： Synthetic Aperture Radar (SAR) imaging systems can provide valuable sources of earth observation data for various applications. Speckle noise reduction of images produced by these systems is a challenging issue. In this paper, a novel method is proposed for reducing the speckle noise from time series SAR images. This method is mainly based on wavelet transform and Kalman filter. The proposed method is applied to a time series SAR images acquired by Sentinel-1 over Tehran, Iran. To demonstrate the performance of the proposed method, both qualitative and quantitative evaluations are reported compared to those of conventional speckle filtering methods. The experimental results show the good performance and efficiency of the proposed method for the speckle reduction of multitemporal SAR images. As well, the results show that the proposed method can preserve the major edge structures and the spatial resolution while reducing the time of processing.
关键词： wavelet transform,speckle noise reduction,kalman filter,Time series SAR images
更新于2025-09-23 15:21:21
-
Lower Power, Better Uniformity, and Stability CBRAM Enabled by Graphene Nanohole Interface Engineering
摘要： With the steadily increasing spatial resolution of synthetic aperture radar images, the need for a consistent but locally adaptive image enhancement rises considerably. Numerous studies already showed that adaptive multilooking, able to adjust the degree of smoothing locally to the size of the targets, is superior to uniform multilooking. This study introduces a novel approach of multiscale and multidirectional multilooking based on intensity images exclusively but applicable to an arbitrary number of image layers. A set of 2-D circular and elliptical filter kernels in different scales and orientations (named Schmittlets) is derived from hyperbolic functions. The original intensity image is transformed into the Schmittlet coefficient domain where each coefficient measures the existence of Schmittlet-like structures in the image. By estimating their significance via the perturbation-based noise model, the best-fitting Schmittlets are selected for image reconstruction. On the one hand, the index image indicating the locally best-fitting Schmittlets is utilized to consistently enhance further image layers, e.g., multipolarized, multitemporal, or multifrequency layers, and on the other hand, it provides an optimal description of spatial patterns valuable for further image analysis. The final validation proves the advantages of the Schmittlets over six contemporary speckle reduction techniques in six different categories (preservation of the mean intensity, equivalent number of looks, and preservation of edges and local curvature both in strength and in direction) by the help of four test sites on three resolution levels. The additional value of the Schmittlet index layer for automated image interpretation, although obvious, still is subject to further studies.
关键词： image reconstruction,image representations,Adaptive filters,image edge analysis,image enhancement,synthetic aperture radar (SAR),image analysis,digital filters
更新于2025-09-23 15:21:01