检索结果-内蒙古大学图书馆

LIRA: Lifelong image restoration from unknown blended distortions

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liu, Jianzhao Lin, Jianxin Li, Xin Zhou, Wei Liu, Sen Chen, Zhibo CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

Most existing image restoration networks are designed in a disposable way and catastrophically forget previously learned distortions when trained on a new distortion removal task. To alleviate this problem, we raise the novel lifelong image restoration problem for blended distortions. We first design a base fork-join model in which multiple pre-trained expert models specializing in individual distortion removal task work cooperatively and adaptively to handle blended distortions. When the input is degraded by a new distortion, inspired by adult neurogenesis in human memory system, we develop a neural growing strategy where the previously trained model can incorporate a new expert branch and continually accumulate new knowledge without interfering with learned knowledge. Experimental results show that the proposed approach can not only achieve state-of-the-art performance on blended distortions removal tasks in both PSNR/SSIM metrics, but also maintain old expertise while learning new restoration tasks. Copyright © 2020, The Authors. All rights reserved.

关键词： Image reconstruction

A decomposed dual-cross generative adversarial network for image rain removal 29

学校读者我要写书评

暂无评论

A decomposed dual-cross generative adversarial network for i...

29th British Machine Vision Conference, BMVC 2018

作者： Jin, Xin Chen, Zhibo Lin, Jianxin Chen, Jiale Zhou, Wei Shan, Chaowei CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

Rain removal is important for many computer vision applications, such as surveillance, autonomous car, etc. Traditionally, rain removal is regarded as a signal removal problem which usually causes over-smoothing by removing texture details in non-rain background regions. This paper considers the issue of rain removal from a completely different perspective, to treat rain removal as a signal decomposition problem. Specifically, we decompose the rain image into two components, namely non-rain background image and rain streaks image. Then, we introduce an adversarial training mechanism to synthesize non-rain background image and rain streaks image in a Dual-Cross manner, which makes the two adversarial branches interact with each other, archiving a win-win result ultimately. The proposed Decomposed Dual-Cross Generative Adversarial Network (DDC-GAN) shows significantly performance improvement compared with state-of-the-art methods on both synthetic and real-world images in terms of qualitative and quantitative measures (over 3dB gains in PSNR). © 2018. The copyright of this document resides with its authors.

关键词： Rain

Image super-resolution quality assessment: Structural fidelity versus statistical naturalness

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhou, Wei Wang, Zhou Chen, Zhibo Dept. of Electrical and Computer Engineering University of Waterloo WaterlooONN2L3G1 Canada CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

Single image super-resolution (SISR) algorithms reconstruct high-resolution (HR) images with their low-resolution (LR) counterparts. It is desirable to develop image quality assessment (IQA) methods that can not only evaluate and compare SISR algorithms, but also guide their future development. In this paper, we assess the quality of SISR generated images in a two-dimensional (2D) space of structural fidelity versus statistical naturalness. This allows us to observe the behaviors of different SISR algorithms as a tradeoff in the 2D space. Specifically, SISR methods are traditionally designed to achieve high structural fidelity but often sacrifice statistical naturalness, while recent generative adversarial network (GAN) based algorithms tend to create more natural-looking results but lose significantly on structural fidelity. Furthermore, such a 2D evaluation can be easily fused to a scalar quality prediction. Interestingly, we find that a simple linear combination of a straightforward local structural fidelity and a global statistical naturalness measures produce surprisingly accurate predictions of SISR image quality when tested using public subject-rated SISR image datasets. Code of the proposed SFSN model is publicly available at https://***/weizhou-geek/SFSN. Copyright © 2021, The Authors. All rights reserved.

关键词： Generative adversarial networks

Multi-Aspect SAR Target Recognition Based on Efficientnet and GRU

学校读者我要写书评

暂无评论

Multi-Aspect SAR Target Recognition Based on Efficientnet an...

IEEE International Symposium on geoscience and Remote Sensing (IGARSS)

作者： Pengfei Zhao Lijia Huang Key Laboratory of Technology in Geo-spatial Information Processing and Application System Chinese of Sciences Beijing China

ISBN: (数字)9781728163741

ISBN: (纸本)9781728163758

Automatic target recognition (ATR) in synthetic aperture radar (SAR) has been extensively applied in military and civilian fields recently. However, SAR images are very sensitive to the azimuth of the imaging, and the same target at different aspects differs greatly, thus requiring more reliable and robust multi-aspect ATR recognition performance. In this paper, we propose an end-to-end multi-aspect ATR model based on EfficientNet and GRU, and use island loss as the training loss, which is more suitable for SAR ATR. Experiments show that our proposed method can achieve 100% accuracy for 10-class recognition, and 99.68% for a large depression angle. Besides, the proposed method can achieve satisfactory accuracy even with reduced datasets. Experimental results have shown that our proposed method outperform other state-of-the-art ATR methods.

关键词： Training Synthetic aperture radar Feature extraction Radar polarimetry Target recognition Data models Image sequences

spatial-temporal water area monitoring of Miyun Reservoir using remote sensing imagery from 1984 to 2020

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Liu, Chang Tang, Hairong Ji, Luyan Zhao, Yongchao Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China University of Chinese Academy of Sciences Beijing100049 China Key Laboratory of Technology in Geo-Spatial Information Processing and Application System Beijing100190 China

Miyun Reservoir has produced huge benefits in flood control, agricultural irrigation, power generation, aquaculture, tourism, and urban water supply. Accurately water mapping is of great significance to the ecological environment monitoring of the Miyun Reservoir and the management of the South-to-North Water Diversion Project. On the 60th anniversary of the completion of the Miyun Reservoir, we took the Miyun Reservoir as the study area and collected all the Landsat-5 and Landsat-8 remote sensing images from 1984 to 2020 for water mapping. Based on the spectral, topographical and temporal-spatial characteristics of water, we proposed an automated method for long-term researvoir mapping, which can solve the problems caused by cloud, shadow, ice and snow pixels. Moreover, it can also deal with the "same objects with different spectra" and spectral mixed problems. The overall accuracy is as high as 98.2% for the case with no cloud or snow/ice cover. The landscape division index is introduced to analyze the morphological changes of Miyun Reservoir. Based on the mapping results, it is suggested that the water area change of the reservoir can be divided into five periods: "growth period" (1984-1993), "peak period" (1994-1999), "decline period" (2000-2003), "protection period" "(2004-2014), and "recovery period" (2015-2020), during which the east and west areas of the reservoir have experienced the process of "division-combination-division-combination". The largest reservoir area reached 151.6 km2 (1995), and the smallest area was only 57.3 km2 (2004). Moreover, we also find that the largest area in a year occurs from August to September, and the smallest area occurs in May. In addition, we have found that the changes of water area of Miyun Reservoir are closely connected to urban development, government policies and precipitation varitations. The study shows that our method used here are potentially extendable to other reservoirs for long-term area monitoring. © 2021, CC

关键词： Time series analysis

A Hybrid and Explainable Deep Learning Framework for SAR Images

学校读者我要写书评

暂无评论

A Hybrid and Explainable Deep Learning Framework for SAR Ima...

IEEE International Symposium on geoscience and Remote Sensing (IGARSS)

作者： Zhongling Huang Mihai Datcu Zongxu Pan Bin Lei Key Laboratory of Technology in Geo-spatial Information Processing and Application System CAS Remote Sensing Technology Institute (IMF) German Aerospace Center (DLR)

ISBN: (数字)9781728163741

ISBN: (纸本)9781728163758

Deep learning based patch-wise Synthetic Aperture Radar (SAR) image classification usually requires a large number of labeled data for training. Aiming at understanding SAR images with very limited annotation and taking full advantage of complex-valued SAR data, this paper proposes a general and practical framework for quad-, dual-, and single-polarized SAR data. In this framework, two important elements are taken into consideration: image representation and physical scattering properties. Firstly, a convolutional neural network is applied for SAR image representation. Based on time-frequency analysis and polarimetric decomposition, the scattering labels are extracted from complex SAR data with unsupervised deep learning. Then, a bag of scattering topics for a patch is obtained via topic modeling. By assuming that the generated scattering topics can be regarded as the abstract attributes of SAR images, we propose a soft constraint between scattering topics and image representations to refine the network. Finally, a classifier for land cover and land use semantic labels can be learned with only a few annotated samples. The framework is hybrid for the combination of deep neural network and explainable approaches. Experiments are conducted on Gaofen-3 complex SAR data and the results demonstrate the effectiveness of our proposed framework.

关键词： Deep learning Training Annotations Scattering Image representation Radar polarimetry Synthetic aperture radar

A Novel Reconstruction Filter for the Azimuth Multi-Channel SAR

学校读者我要写书评

暂无评论

A Novel Reconstruction Filter for the Azimuth Multi-Channel ...

IEEE International Conference on Radar

作者： Mingyang Shang Xiaolan Qiu Junying Yang Lihua Zhong Yu Xin Chibiao Ding Key Laboratory of Technology in Geo-Spatial Information Processing and Application Systems Aerospace Information Research Institute Chinese Academic of Sciences Beijing China Beijing Institute of Remote Sensing Information Beijing China

ISBN: (纸本)9781665468893

The compensation of channel imbalances plays a vital role in signal processing of the azimuth multi-channel (AMC) synthetic aperture radar (SAR). In the operational AMC SAR system, the channel imbalance is usually considered to be a constant in both the time and frequency domain for one image. However, since the antenna patterns of all channels cannot be strictly consistent, the channel imbalances may vary with the Doppler frequency. This paper establishes the signal model of AMC SAR with channel imbalances changing with Doppler frequency and proposes a novel compensation method during the reconstruction for the echo signals received by all channels. This method has been verified by simulations and real data acquired by Gaofen-3 (GF-3). The result shows that this method has excellent potential for improving the image quality for AMC SAR.

关键词： Image quality Antenna measurements Azimuth Filter banks Receiving antennas Channel estimation Signal processing

Preliminary Analysis of PolInSAR Scattering Mechanism in Urban Areas through UAV-borne PolInSAR system

学校读者我要写书评

暂无评论

Preliminary Analysis of PolInSAR Scattering Mechanism in Urb...

IEEE International Conference on Radar

作者： Zexin Lv Xiaolan Qiu Chibiao Ding Key Laboratory of Technology in Geo-spatial Information Processing and Application System Beijing China Aerospace Information Research Institute (of Chinese Academy of Sciences) Beijing China University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Aerospace Big Dara Application Technology Suzhou China Suzhou Aerospace Information Research Institute Suzhou China

ISBN: (纸本)9781665468893

Polarimetric Interferometric SAR (PolInSAR) can improve the coherence of images and it plays an important role in urban remote sensing. The explanation of its scattering mechanism is concerned by many researchers. It is always explained from the aspect of different polarization decompositions but seldom from the height of scattering centers. In this paper, a Ku-band UAV-borne PolInSAR system is used to compare the relationship of scattering centers between PolInSAR and Pauli decomposition on different artificial targets. The physical meaning of PolInSAR is preliminary analyzed and our conclusion is also verified through a C-band manned airborne PolInSAR system.

关键词： C-band Airborne radar Urban areas Scattering Coherence Radar polarimetry Synthetic aperture radar

Interpreting the Latent Space of GANs via Correlation Analysis for Controllable Concept Manipulation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Li, Ziqiang Tao, Rentuo Niu, Hongjing Li, Bin CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application Systems University of Science and Technology of China Anhui China

Generative adversarial nets (GANs) have been successfully applied in many fields like image generation, inpainting, super-resolution and drug discovery, etc., by now, the inner process of GANs is far from been understood. To get deeper insight of the intrinsic mechanism of GANs, in this paper, a method for interpreting the latent space of GANs by analyzing the correlation between latent variables and the corresponding semantic contents in generated images is proposed. Unlike previous methods that focus on dissecting models via feature visualization, the emphasis of this work is put on the variables in latent space, i.e. how the latent variables affect the quantitative analysis of generated results. Given a pretrained GAN model with weights fixed, the latent variables are intervened to analyze their effect on the semantic content in generated images. A set of controlling latent variables can be derived for specific content generation, and the controllable semantic content manipulation be achieved. The proposed method is testified on the datasets Fashion-MNIST and UT Zappos50K, experiment results show its effectiveness. Copyright © 2020, The Authors. All rights reserved.

关键词： Generative adversarial networks