检索结果-内蒙古大学图书馆

A convolutional neural network approach for half-pel interpolation in video coding

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Yan, Ning Liu, Dong Li, Houqiang Wu, Feng CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

Motion compensation is a fundamental technology in video coding to remove the temporal redundancy between video frames. To further improve the coding efficiency, sub-pel motion compensation has been utilized, which requires interpolation of fractional samples. The video coding standards usually adopt fixed interpolation filters that are derived from the signal processing theory. However, as video signal is not stationary, the fixed interpolation filters may turn out less efficient. Inspired by the great success of convolutional neural network (CNN) in computer vision, we propose to design a CNN-based interpolation filter (CNNIF) for video coding. Different from previous studies, one difficulty for training CNNIF is the lack of ground-truth since the fractional samples are actually not available. Our solution for this problem is to derive the "ground-truth" of fractional samples by smoothing high-resolution images, which is verified to be effective by the conducted experiments. Compared to the fixed half-pel interpolation filter for luma in High Efficiency Video Coding (HEVC), our proposed CNNIF achieves up to 3.2% and on average 0.9% BD-rate reduction under low-delay P configuration. Copyright © 2017, The Authors. All rights reserved.

关键词： Video signal processing

A New Non-local Video Denoising Scheme Using Low-Rank Representation and Total Variation Regularization

学校读者我要写书评

暂无评论

A New Non-local Video Denoising Scheme Using Low-Rank Repres...

IEEE International Symposium on Circuits and systems

作者： Qingbo Lu Zhenbo Lu Xiaoqing Tao Houqiang Li CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei Anhui China

ISBN: (纸本)9781479934331

In this article, we present a novel non-local video denoising scheme using low-rank representation and total variation regularization. The proposed scheme attempts to make full use of the intrinsic properties that the grouping similar patches not only lie in a low-rank subspace but are also sparse in total variation (TV) domain. For a group of similar patches, we formulate video denoising problem into a concise model that combines nuclear norm, TV regularization and l_1 norm. The experiments demonstrate that the proposed scheme is capable of handling multi-type noise including dense Gaussian noise and random-valued sparse noise, while maintaining the texture information meantime. The results show that our scheme achieves noticeable performance improvement over the state-of-the-art video denoising methods.

关键词： video denoising low-rank representation total variation alternating direction method

A COOPERATIVE MULTITEMPORAL SEGMENTATION METHOD FOR SAR AND OPTICAL IMAGES CHANGE DETECTION

学校读者我要写书评

暂无评论

A COOPERATIVE MULTITEMPORAL SEGMENTATION METHOD FOR SAR AND ...

IEEE International geoscience and Remote Sensing Symposium

作者： Ling Wan Yuming Xiang Hongjian You Key Laboratory of Technology in Geo-spatial Information Processing and Application System Institute of Electronics Chinese Academy of Sciences Beijing China

This paper proposes an extension version of our previous work MS-CC to achieve optical and SAR images change detection. The proposed method introduces a cooperative multitemporal segmentation, whose merging process considers the heterogeneity of SAR and optical images as parallel information, making sure that the multitemporal information can be fully utilized without interfering with each other. Then, the change detection strategy based on compound classification is carried out on the segmentation results, obtaining the multi-scale change detection maps. Experimental validation is conducted with GoaFen3 and Google Earth data.

关键词： Image segmentation Optical imaging Radar polarimetry Optical sensors Compounds Interference Stacking

A STUDY ON THE FREQUENCY AND AZIMUTH COHERENCE OF HIGH-RESOLUTION SAR IMAGE

学校读者我要写书评

暂无评论

A STUDY ON THE FREQUENCY AND AZIMUTH COHERENCE OF HIGH-RESOL...

IEEE International geoscience and Remote Sensing Symposium

作者： Wenji Xing Xiaolan Qiu Chibiao Ding The Key Laboratory of Technology in Geo-spatial Information Processing and Application System Institute of Electronics Chinese Academy of Sciences Beijing China

High-resolution SAR has large transmitting bandwidth and wide synthetic aperture. How to understand and take advantage of the variation characteristics of SAR scattering characteristics with angle and frequency is a topic that worth studying. This article establishes a coherence matrix of sub-band and sub-aperture SAR images, and analyzes its ability to classify scattering mechanism. Experiments are conducted using the TerraSAR-X high-resolution data of different scenarios, and some meaningful results are got, which may provide some support to the analysis and application of high-resolution SAR data.

关键词： Coherence Entropy Azimuth Radar polarimetry Synthetic aperture radar Image resolution

Learned fast HEVC intra coding

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Chen, Zhibo Shi, Jun Li, Weiping CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

In High Efficiency Video Coding (HEVC), excellent rate-distortion (RD) performance is achieved in part by having a flexible quadtree coding unit (CU) partition and a large number of intra-prediction modes. Such an excellent RD performance is achieved at the expense of much higher computational complexity. In this paper, we propose a learned fast HEVC intra coding (LFHI) framework taking into account the comprehensive factors of fast intra coding to reach an improved configurable tradeoff between coding performance and computational complexity. First, we design a low-complex shallow asymmetric-kernel CNN (AK-CNN) to efficiently extract the local directional texture features of each block for both fast CU partition and fast intra-mode decision. Second, we introduce the concept of the minimum number of RDO candidates (MNRC) into fast mode decision, which utilizes AK-CNN to predict the minimum number of best candidates for RDO calculation to further reduce the computation of intra-mode selection. Third, an evolution optimized threshold decision (EOTD) scheme is designed to achieve configurable complexity-efficiency tradeoffs. Finally, we propose an interpolation-based prediction scheme that allows for our framework to be generalized to all quantization parameters (QPs) without the need for training the network on each QP. The experimental results demonstrate that the LFHI framework has a high degree of parallelism and achieves a much better complexity-efficiency tradeoff, achieving up to 75.2% intra-mode encoding complexity reduction with negligible rate-distortion performance degradation, superior to the existing fast intra-coding schemes. Copyright © 2019, The Authors. All rights reserved.

关键词： Signal distortion

RC-CNN: Representation-Consistent Convolutional Neural Networks for Achieving Transformation Invariance

学校读者我要写书评

暂无评论

RC-CNN: Representation-Consistent Convolutional Neural Netwo...

IEEE International Conference on systems, Man and Cybernetics

作者： Jun Gu Anfeng He Xinmei Tian CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei Anhui China

Convolutional neural networks (CNNs) are powerful and have achieved state-of-the-art performance in many visual recognition tasks. Despite their impressive performance, CNNs are still unable to remain invariant while some spatial transformations are applied on images. Herein, we propose representation-consistent neural networks to solve this problem. By introducing consistent losses between the representations in different layers of transformed images, the recognition performance of transformed images is significantly improved. This model not only learns to map from the transformed images to the pre-defined labels but each layer also learns to generate invariant representations when the input images are transformed. All the characteristics of transformation invariance are embedded in the model, which means that no extra parameters or computations are introduced in the well-trained model. Comparative experiments demonstrate the superiority of our model when learning invariance to rotation, translation, and scaling on large-scale image recognition and retrieval tasks.

关键词： Computational modeling Feature extraction Training Image recognition Data models Task analysis Kernel

Quality assessment of stereoscopic 360-degree images from multi-viewports

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Xu, Jiahua Luo, Ziyuan Zhou, Wei Zhang, Wenyuan Chen, Zhibo CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

Objective quality assessment of stereoscopic panoramic images becomes a challenging problem owing to the rapid growth of 360-degree contents. Different from traditional 2D image quality assessment (IQA), more complex aspects are involved in 3D omnidirectional IQA, especially unlimited field of view (FoV) and extra depth perception, which brings difficulty to evaluate the quality of experience (QoE) of 3D omnidirectional images. In this paper, we propose a multi-viewport based full-reference stereo 360 IQA model. Due to the freely changeable viewports when browsing in the head-mounted display, our proposed approach processes the image inside FoV rather than the projected one such as equirectangular projection (ERP). In addition, since overall QoE depends on both image quality and depth perception, we utilize the features estimated by the difference map between left and right views which can reflect disparity. The depth perception features along with binocular image qualities are employed to further predict the overall QoE of 3D 360 images. The experimental results on our public Stereoscopic OmnidirectionaL Image quality assessment Database (SOLID) show that the proposed method achieves a significant improvement over some well-known IQA metrics and can accurately reflect the overall QoE of perceived images. Copyright © 2019, The Authors. All rights reserved.

关键词： Quality of service

Unambiguous parameter estimation of radial velocity approach for airborne SAR-GMTI

学校读者我要写书评

暂无评论

Unambiguous parameter estimation of radial velocity approach...

Asian and Pacific Conference on Synthetic Aperture Radar (APSAR)

作者： Ruipeng Xu Dandan Zhang Lijia Huang Donghui Hu Chibiao Ding Key Laboratory of Geo-spatial Information Processing and Application System Technology Institute of Electronics Chinese Academy of Sciences Beijing China

The ambiguous Doppler centroid causes incorrect estimation result of the radial velocity. For moving targets with fast radial velocity, an unambiguous estimation approach of the radial velocity is introduced for the airborne SAR system in this paper. First, two channels carried different wavelength can be constructed by range multilook processing (RMLP). Second, the instantaneous frequency curve of the moving target is obtained by polynomial fitting for each channel, where the linear term denotes the baseband Doppler centroid. Considering the fact that the difference of the estimated baseband Doppler centroid in two channels is equal to the difference of the absolute Doppler centroid, the unambiguous radial velocity can be estimated using it. Third, the range walk and the Doppler shift which are produced by the fast radial velocity can be eliminated by compensating a phase in the range-frequency and azimuth-time domain. As a result, the moving target will be reimaged and relocated after azimuth compression. The proposed approach will be applied to both single — and multi-channel SAR system. The simulation results validate the effectiveness of the proposed method.

关键词： Doppler effect Estimation Baseband Azimuth Accuracy Fitting Polynomials

Two-stream action recognition-oriented video super-resolution

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Zhang, Haochen Liu, Dong Xiong, Zhiwei CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

We study the video super-resolution (SR) problem for facilitating video analytics tasks, e.g. action recognition, instead of for visual quality. The popular action recognition methods based on convolutional networks, exemplified by two-stream networks, are not directly applicable on video of low spatial resolution. This can be remedied by performing video SR prior to recognition, which motivates us to improve the SR procedure for recognition accuracy. Tailored for two-stream action recognition networks, we propose two video SR methods for the spatial and temporal streams respectively. On the one hand, we observe that regions with action are more important to recognition, and we propose an optical-flow guided weighted mean-squared-error loss for our spatial-oriented SR (SoSR) network to emphasize the reconstruction of moving objects. On the other hand, we observe that existing video SR methods incur temporal discontinuity between frames, which also worsens the recognition accuracy, and we propose a siamese network for our temporal-oriented SR (ToSR) training that emphasizes the temporal continuity between consecutive frames. We perform experiments using two state-of-the-art action recognition networks and two well-known datasets–UCF101 and HMDB51. Results demonstrate the effectiveness of our proposed SoSR and ToSR in improving recognition accuracy. Copyright © 2019, The Authors. All rights reserved.

关键词： Optical resolving power