检索结果-内蒙古大学图书馆

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

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

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

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

SIFT-preserving compression of mobile-captured license plate images for recognition

SIFT-preserving compression of mobile-captured license plate...

引用

International Conference on Wireless Communications and Signal processing (WCSP)

作者： Dandan Wang Dong Liu 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)9781479973408

Image compression had been extensively studied for reducing coding rate yet producing acceptable visual quality. However, there are many application scenarios where the compressed images are used for automatic recognition rather than human viewing, thus the visual quality is no longer critical for compression. SIFT features have demonstrated their utility in many recognition scenarios and SIFT-preserving compression is developed recently. In this paper, we firstly study the SIFT-preserving compression of license plate images for recognition accuracy rather than visual quality. According to extracted SIFT features, each image is divided into SIFT coding-units and non-SIFT coding-units. Each coding-unit is assigned with a different quality parameter when using JPEG for compression. We compare our proposed scheme with the standard JPEG that uses a unified quality parameter. Experimental results with manually tuned parameters show that on average 14% bit-rate can be saved by our scheme, without any loss of recognition accuracy.

关键词： Image coding Transform coding Licenses Standards Image recognition Feature extraction Accuracy

来源：评论

学校读者我要写书评

暂无评论

QUERY DIFFICULTY ESTIMATION VIA PSEUDO RELEVANCE FEEDBACK FOR IMAGE SEARCH

QUERY DIFFICULTY ESTIMATION VIA PSEUDO RELEVANCE FEEDBACK FO...

引用

IEEE International Conference on Multimedia and Expo

作者： Qianghuai Jia Xinmei Tian Tao Mei CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Microsoft Research

ISBN: (纸本)9781479947607

Query difficulty estimation (QDE) attempts to automatically predict the performance of the search results returned for a given query. QDE has been widely investigated in text document retrieval for many years. However, few research works have been explored in image retrieval. State-of-the-art QDE methods in image retrieval mainly investigate the statistical characteristics (coherence, robustness, etc.) of the returned images to derive a value for indicating the query difficulty degree. To the best of our knowledge, little research has been done to directly estimate the real retrieval performance of the search results, such as average precision, instead of only an indicator. In this paper, we propose a novel query difficulty estimation approach which automatically estimate the average precision of the image search results. Specifically, we first select a set of query relevant and query irrelevant images for each query via pseudo relevance feedback. Then an efficient and effective voting scheme is proposed to estimate the relevance label of each image in the search results. Based on the images' relevance labels, the average precision of the search results returned for the given query is derived. The experimental results on a benchmark image search dataset demonstrate the effectiveness of the proposed method.

关键词： Query difficulty estimation (QDE) Image retrieval Average precision (AP) Pseudo relevance feedback (PRF) Voting scheme

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

M-LVC: Multiple Frames Prediction for Learned Video Compression

M-LVC: Multiple Frames Prediction for Learned Video Compress...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

We propose an end-to-end learned video compression scheme for low-latency scenarios. Previous methods are limited in using the previous one frame as reference. Our method introduces the usage of the previous multiple frames as references. In our scheme, the motion vector (MV) field is calculated between the current frame and the previous one. With multiple reference frames and associated multiple MV fields, our designed network can generate more accurate prediction of the current frame, yielding less residual. Multiple reference frames also help generate MV prediction, which reduces the coding cost of MV field. We use two deep auto-encoders to compress the residual and the MV, respectively. To compensate for the compression error of the auto-encoders, we further design a MV refinement network and a residual refinement network, taking use of the multiple reference frames as well. All the modules in our scheme are jointly optimized through a single rate-distortion loss function. We use a step-by-step training strategy to optimize the entire scheme. Experimental results show that the proposed method outperforms the existing learned video compression methods for low-latency mode. Our method also performs better than H.265 in both PSNR and MS-SSIM. Our code and models are publicly available.

关键词： Video compression Image coding Motion compensation Entropy Encoding Motion estimation Transforms

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

A CNN-Based In-Loop Filter with CU Classification for HEVC

A CNN-Based In-Loop Filter with CU Classification for HEVC

引用

IEEE Visual Communications and Image processing (VCIP)

作者： Yuanying Dai Dong Liu Zheng-Jun Zha 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

Lossy compression of image and video yields visually annoying artifacts including blocking, blurring, ringing, etc., especially at low bit rates. In-loop filtering techniques can reduce these artifacts, improve quality, and achieve coding gain accordingly. In this paper, we present a convolutional neural network (CNN) based in-loop filter for High Efficiency Video Coding (HEVC). First, we design a new CNN structure that is composed of multiple Variable-filter-size Residue-learning blocks, namely VRCNN-ext, for artifact reduction. VRCNN-ext is trained by natural images as well as their compressed versions at different quality levels. Second, we investigate a new in-loop filter based on the trained VRCNN-ext models. Specifically, we observed that using VRCNN-ext directly on the inter pictures is not effective. To solve this problem, we further train a classifier to decide whether to use VRCNN-ext for each coding unit (CU). The classifier makes decision based on the compressed information, thus avoiding the overhead bits to control the on/off of the CNN-based filter at the CU level. Experimental results show that our scheme achieves significant bits saving than the HEVC anchor, leading to on average 9.2%, 9.6% and 7.4% BD-rate reduction on the HEVC test sequences, under all-intra, low-delay B and random-access configurations, respectively.

关键词： Decoding Encoding Training Image coding Feature extraction Copper Video coding

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：