检索结果-内蒙古大学图书馆

arXiv 2018年

作者： Chen, Zhibo He, Tianyu CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei China

Surveillance and security scenarios usually require high efficient facial image compression scheme for face recognition and identification. While either traditional general image codecs or special facial image compression schemes only heuristically refine codec separately according to face verification accuracy metric. We propose a Learning based Facial Image Compression (LFIC) framework with a novel Regionally Adaptive Pooling (RAP) module whose parameters can be automatically optimized according to gradient feedback from an integrated hybrid semantic fidelity metric, including a successfully exploration to apply Generative Adversarial Network (GAN) as metric directly in image compression scheme. The experimental results verify the framework’s efficiency by demonstrating performance improvement of 71.41%, 48.28% and 52.67% bitrate saving separately over JPEG2000, WebP and neural network-based codecs under the same face verification accuracy distortion metric. We also evaluate LFIC’s superior performance gain compared with latest specific facial image codecs. Visual experiments also show some interesting insight on how LFIC can automatically capture the information in critical areas based on semantic distortion metrics for optimized compression, which is quite different from the heuristic way of optimization in traditional image compression algorithms. Copyright © 2018, The Authors. All rights reserved.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

Three-Dimensional Point-Cloud Plus Patches: Towards Model-Based Image Coding in the Cloud

Three-Dimensional Point-Cloud Plus Patches: Towards Model-Ba...

引用

IEEE International Conference on Multimedia Big Data (BigMM)

作者： Dong Liu Tong Shao Houqiang Li Feng Wu CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei China

ISBN: (纸本)9781479986897

In the era of cloud computing, there are many correlated images in the cloud, joint compression of these images may provide much higher compression ratio than individual coding. Model-based coding is an appealing approach to image coding in the cloud, as it removes knowledge redundancy among images that share the same model. In this paper, we make an attempt to model-based image coding for landmark images, where our model consists of three-dimensional (3-D) point-cloud plus image patches to describe the geometry and surface color of the landmark respectively. The camera parameters of an input image are estimated based on the 3-D point-cloud and the patches in the model, and then prediction image is generated by selecting, warping, and stitching image patches as well as illuminance compensation, the residue between original and prediction images is compressed by P-frame coding in HEVC encoder. We perform experiments on an Internet photo collection to verify the effectiveness of the proposed scheme. Preliminary results display the superior performance of our scheme that achieves as high as 39.9% bits saving compared to HEVC intra on a single image. The proposed scheme indicates a promising approach to image coding in the cloud and is worthy of in-depth investigation.

关键词： Image coding Solid modeling Cameras Decoding Redundancy Feature extraction Lighting

来源：评论

学校读者我要写书评

暂无评论

Generative Adversarial Network-Based Frame Extrapolation for Video Coding

Generative Adversarial Network-Based Frame Extrapolation for...

引用

IEEE Visual Communications and Image processing (VCIP)

作者： Jianping Lin Dong Liu Houqiang Li Feng Wu CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei China

ISBN: (纸本)9781538644591;9781538644584

Motion estimation and motion compensation are fundamental in video coding to remove the temporal redundancy between video frames. The current video coding schemes usually adopt block-based motion estimation and compensation using simple translational or affine motion models, which cannot efficiently characterize complex motions in natural video signal. In this paper, we propose a frame extrapolation method for motion estimation and compensation. Specifically, based on the several previous frames, our method directly extrapolates the current frame using a trained deep network model. The deep network we adopted is a redesigned Video Coding oriented LAplacian Pyramid of Generative Adversarial Networks (VC-LAPGAN). The extrapolated frame is then used as an additional reference frame. Experimental results show that the VC-LAPGAN is capable in estimating and compensating for complex motions, and extrapolating frames with high visual quality. Using the VC-LAPGAN, our method achieves on average 2.0% BD-rate reduction than High Efficiency Video Coding (HEVC) under low-delay P configuration.

关键词： Video coding Motion estimation Training Computational modeling Extrapolation Laplace equations Convolutional codes

来源：评论

学校读者我要写书评

暂无评论

No-Reference Light Field Image Quality Assessment Based on Micro-Lens Image

No-Reference Light Field Image Quality Assessment Based on M...

引用

Picture Coding Symposium, PCS

作者： Ziyuan Luo Wei Zhou Likun Shi Zhibo Chen CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei China

Light field image quality assessment (LF-IQA) plays a significant role due to its guidance to Light Field (LF) contents acquisition, processing and application. The LF can be represented as 4-D signal, and its quality depends on both angular consistency and spatial quality. However, few existing LF-IQA methods concentrate on effects caused by angular inconsistency. Especially, no-reference methods lack effective utilization of 2D angular information. In this paper, we focus on measuring the 2-D angular consistency for LF-IQA. The Micro-Lens Image (MLI) refers to the angular domain of the LF image, which can simultaneously record the angular information in both horizontal and vertical directions. Since the MLI contains 2D angular information, we propose a No-Reference Light Field image Quality assessment model based on MLI (LF-QMLI). Specifically, we first utilize Global Entropy Distribution (GED) and Uniform Local Binary Pattern descriptor (ULBP) to extract features from the MLI, and then pool them together to measure angular consistency. In addition, the information entropy of SubAperture Image (SAI) is adopted to measure spatial quality. Extensive experimental results show that LF-QMLI achieves the state-of-the-art performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Tensor oriented no-reference light field image quality assessment

arXiv

引用

arXiv 2019年

作者： Zhou, Wei Shi, Likun Chen, Zhibo Cas Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027

Light field image (LFI) quality assessment is becoming more and more important, which helps to better guide the acquisition, processing and application of immersive media. However, due to the inherent high dimensional characteristics of LFI, the LFI quality assessment turns into a multi-dimensional problem that requires consideration of the quality degradation in both spatial and angular dimensions. Therefore, we propose a novel Tensor oriented No-reference Light Field image Quality evaluator (Tensor-NLFQ) based on tensor theory. Specifically, since the LFI is regarded as a low-rank 4D tensor, the principle components of four oriented sub-aperture view stacks are obtained via Tucker decomposition. Then, the Principal Component spatial Characteristic (PCSC) is designed to measure the spatial-dimensional quality of LFI considering its global naturalness and local frequency properties. Finally, the Tensor Angular Variation Index (TAVI) is proposed to measure angular consistency quality by analyzing the structural similarity distribution between the first principal component and each view in the view stack. Extensive experimental results on four publicly available LFI quality databases demonstrate that the proposed Tensor-NLFQ model outperforms state-of-the-art 2D, 3D, multi-view, and LFI quality assessment algorithms. Copyright © 2019, The Authors. All rights reserved.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

Hierarchical quadtree-based flexible block ordering in HEVC intra coding

Hierarchical quadtree-based flexible block ordering in HEVC ...

引用

IEEE Visual Communications and Image processing (VCIP)

作者： Lei Guo Dong Liu Li Li Feng Wu CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei China

ISBN: (纸本)9781509053179

In all of the existing block-based image and video coding standards, blocks are processed in the fixed scan order. Then in HEVC intra coding, intra prediction is always based on the top and/or left neighboring reconstructed pixels, which incurs less accurate prediction for blocks where the spatial correlation is not along the topleft-to-bottomright direction. To obtain better intra prediction, we propose to flexibly determine the coding order of blocks in HEVC intra coding. Complying with the hierarchical quadtree structure in HEVC, our flexible block ordering (FBO) technique recursively decides the coding order of four sub-blocks when splitting one block. Moreover, we propose new methods to perform inter/extrapolation for intra prediction so as to fully utilize neighboring reconstructed pixels, not always being top/left. Experimental results show that our proposed FBO technique achieves on average 2.9% BD-rate reduction compared to HEVC baseline.

关键词： Encoding High efficiency video coding Image reconstruction Correlation Standards Interpolation Copper

来源：评论

学校读者我要写书评

暂无评论

Reinforced Bit Allocation under Task-Driven Semantic Distortion Metrics

arXiv

引用

arXiv 2019年

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

Rapid growing intelligent applications require optimized bit allocation in image/video coding to support specific task-driven scenarios such as detection, classification, segmentation, etc. Some learning-based frameworks have been proposed for this purpose due to their inherent end-to-end optimization mechanisms. However, it is still quite challenging to integrate these task-driven metrics seamlessly into traditional hybrid coding framework. To the best of our knowledge, this paper is the first work trying to solve this challenge based on reinforcement learning (RL) approach. Specifically, we formulate the bit allocation problem as a Markovian Decision Process (MDP) and train RL agents to automatically decide the quantization parameter (QP) of each coding tree unit (CTU) for HEVC intra coding, according to the task-driven semantic distortion metrics. This bit allocation scheme can maximize the semantic level fidelity of the task, such as classification accuracy, while minimizing the bit-rate. We also employ gradient class activation map (Grad-CAM) and Mask R-CNN tools to extract task-related importance maps to help the agents make decisions. Extensive experimental results demonstrate the superior performance of our approach by achieving 43.1% to 73.2% bit-rate saving over the anchor of HEVC under the equivalent task-related distortions. Copyright © 2019, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

End-to-End Facial Image Compression with Integrated Semantic Distortion Metric

End-to-End Facial Image Compression with Integrated Semantic...

引用

IEEE Visual Communications and Image processing (VCIP)

作者： Tianyu He Zhibo Chen CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei China

ISBN: (纸本)9781538644591;9781538644584

High efficient facial image compression is broadly required and challenging for surveillance and security scenarios, while either traditional general image codecs or special facial image compression schemes only heuristically refine codec separately according to face verification accuracy metric. We propose an End-to-End Facial Image Compression (E2EFIC) framework with a novel variable block size Regionally Adaptive Pooling (RAP) module whose parameters can be automatically optimized according to gradient feedback from an integrated semantic distortion metrics, including a successful exploration to apply Generative Adversarial Network (GAN) as metric directly in image compression scheme. The experimental results verify the framework's efficiency by demonstrating performance improvement of 71.41%, 48.28% and 52.67% bitrate saving separately over JPEG2000, WebP and neural network-based codecs under the same face verification accuracy distortion metric. We also evaluate E2EFIC's superior performance gain compared with latest specific facial image codecs.

关键词： Image coding Distortion Semantics Face Bit rate Codecs

来源：评论

学校读者我要写书评

暂无评论

Hybrid transform for HEVC-based lossless coding

Hybrid transform for HEVC-based lossless coding

引用

IEEE International Symposium on Circuits and systems (ISCAS)

作者： Fangdong Chen Jinlei Zhang Houqiang Li CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei China

ISBN: (纸本)9781479934331

The High Efficiency Video Coding (HEVC) with the transform bypass mode is simple but inefficient for lossless coding. For this reason, we propose a novel transform to further eliminate the redundancy between residues of different blocks in intra prediction. Dependent on intra prediction modes, the proposed transform is adaptable to exploit correlations of residues formed by different modes. In order to accurately obtain parameters of the transform matrix, an approach similar to the Wiener filtering method is adopted. Experimental results show that on top of the lossless coding mode in HEVC, our method offers the performance with a 7.4% bit-rate reduction on average for All Intra Main configuration. Compared with other representative algorithms, our proposal still shows an improvement in the compression ratio, without substantial increases of computational complexity in the encoder or decoder.

关键词： Encoding Transforms Video coding Redundancy Prediction algorithms Proposals Standards

来源：评论

学校读者我要写书评

暂无评论

Passive Super-Low Frequency electromagnetic prospecting technique

引用

Frontiers of Earth Science 2017年第2期11卷 248-267页

作者： Nan WANG Shanshan ZHAO Jian HUI Qiming QIN Institute of Remote Sensing and GIS School of Earth and Space Sciences Peking University Beijing 100871 China Key Laboratory of Technology in Geospatial Information Processing and Application System Institute of Electronics Chinese Academy of Sciences Beijing 100190 China

The Super-Low Frequency （SLF） electromag- netic prospecting technique, adopted as a non-imaging remote sensing tool for depth sounding, is systematically proposed for subsurface geological survey. In this paper, we propose and theoretically illustrate natural source magnetic amplitudes as SLF responses for the first step. In order to directly calculate multi-dimensional theoretical SLF responses, modeling algorithms were developed and evaluated using the finite difference method. The theore- tical results of three-dimensional （3-D） models show that the average normalized SLF magnetic amplitude responses were numerically stable and appropriate for practical interpretation. To explore the depth resolution, three-layer models were configured. The modeling results prove that the SLF technique is more sensitive to conductive objective layers than high resistive ones, with the SLF responses of conductive objective layers obviously show- ing uprising amplitudes in the low frequency range. Afterwards, we proposed an improved Frequency-Depth transformation based on Bostick inversion to realize the depth sounding by empirically adjusting two parameters. The SLF technique has already been successfully applied in geothermal exploration and coalbed methane （CBM） reservoir interpretation, which demonstrates that the proposed methodology is effective in revealing low resistive distributions. Furthermore, it siginificantly contributes to reservoir identification with electromagnetic radiation anomaly extraction. Meanwhile, the SLF inter- pretation results are in accordance with dynamic production status of CBM reservoirs, which means it could provide an economical, convenient and promising method for exploring and monitoring subsurface geo-objects.

关键词： Super-Low Frequency （SLF） three-dimen-sional modeling frequency-depth transformation geother-mal exploration coalbed methane （CBM） electromagneticradiation （EMR）

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：