2018 IEEE Visual Communications and Image Processing (VCIP)最新文献_第10页

Compressed Sensing via a Deep Convolutional Auto-encoder 通过深度卷积自编码器压缩感知

2018 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2018-12-01 DOI: 10.1109/VCIP.2018.8698640

Hao Wu, Ziyang Zheng, Yong Li, Wenrui Dai, H. Xiong

{"title":"Compressed Sensing via a Deep Convolutional Auto-encoder","authors":"Hao Wu, Ziyang Zheng, Yong Li, Wenrui Dai, H. Xiong","doi":"10.1109/VCIP.2018.8698640","DOIUrl":"https://doi.org/10.1109/VCIP.2018.8698640","url":null,"abstract":"The nonlinear recovery is not promising in accuracy and speed, which limits the practical usage of compressed sensing (CS). This paper proposes a deep learning-based CS framework which leverages a deep convolutional auto-encoder for image sensing and recovery. The utilized auto-encoder architecture consists of three components: the fully convolutional network acts as an adaptive measurement matrix generator in the encoder; while in the decoder, the deconvolution network and refined reconstruction network are learned for intermediate and final recovery, respectively. Different from most previous work focusing on the block-wise manner to reduce implementation cost but result in blocky artifacts, our adaptive measurement matrix is applicable to any size of scene image and the decoder network reconstructs the whole image efficiently without any blocky artifacts. Moreover, dense connectivity is leveraged to combine multi-level features and alleviate the vanishing-gradient problem in the refined reconstruction network which boosts the performance on image recovery. Compared to the state-of-the-art methods, our algorithm improves more than 0.8 dB in average PSNR.","PeriodicalId":270457,"journal":{"name":"2018 IEEE Visual Communications and Image Processing (VCIP)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133964233","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Voting-based Hand-Waving Gesture Spotting from a Low-Resolution Far-Infrared Image Sequence 低分辨率远红外图像序列中基于投票的手势识别

2018 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2018-12-01 DOI: 10.1109/VCIP.2018.8698650

Yasutomo Kawanishi, Chisato Toriyama, Tomokazu Takahashi, Daisuke Deguchi, I. Ide, H. Murase, Tomoyoshi Aizawa, M. Kawade

引用次数: 4

Fast Korean Text Detection and Recognition in Traffic Guide Signs 交通引导标志中朝鲜语文本的快速检测与识别

2018 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2018-12-01 DOI: 10.1109/VCIP.2018.8698668

Hyunjun Eun, Jonghee Kim, Jinsu Kim, Changick Kim

引用次数: 2

Light Field Image Sparse Coding via CNN-Based EPI Super-Resolution 基于cnn的EPI超分辨率光场图像稀疏编码

2018 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2018-12-01 DOI: 10.1109/VCIP.2018.8698714

Jinbo Zhao, P. An, Xinpeng Huang, Liang Shan, Ran Ma

引用次数: 5

Near-Duplicate Image Retrieval Based on Multiple Features 基于多特征的近重复图像检索

2018 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2018-12-01 DOI: 10.1109/VCIP.2018.8698664

Xueqin Zhang

引用次数: 0

Rate-Distortion Theory for Simplified Affine Motion Compensation Used in Video Coding 用于视频编码的简化仿射运动补偿的率失真理论

2018 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2018-12-01 DOI: 10.1109/VCIP.2018.8698702

H. Meuel, Stephan Ferenz, Yiqun Liu, J. Ostermann

{"title":"Rate-Distortion Theory for Simplified Affine Motion Compensation Used in Video Coding","authors":"H. Meuel, Stephan Ferenz, Yiqun Liu, J. Ostermann","doi":"10.1109/VCIP.2018.8698702","DOIUrl":"https://doi.org/10.1109/VCIP.2018.8698702","url":null,"abstract":"In this work, we derive the rate-distortion function for video coding using the simplified affine, 4-parameter motion compensation model as it is used in the Joint Exploration Model (JEM) by the Joint Video Exploration Team (JVET) on Future Video coding. We model the displacement estimation error during motion estimation and obtain the bit rate by applying the rate-distortion theory. We assume that the displacement estimation error is caused by perturbed parameters of the simplified affine model. These transformation parameters are assumed statistically independent, with each of them having a zero-mean Gaussian distributed estimation error. The joint probability density function (p.d.f.) of the displacement estimation errors is derived and related to the prediction error. We calculate the bit rate as a function of the accuracy of the parameter estimation for the simplified affine motion model. Finally, we compare our results with a translational motion model as used in video coding standards like HEVC as well as with a full affine motion model with 6 degrees of freedom. For aerial sequences containing distinct affine motion, the minimum required bit rate to encode the prediction error can be significantly reduced from 2.5 bit/sample to 0.02 bit/sample for a reasonable operating point and a block size of 64×64 pel2.","PeriodicalId":270457,"journal":{"name":"2018 IEEE Visual Communications and Image Processing (VCIP)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116656038","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Simple Iterative Clustering on Graphs for Robust Model Fitting 图上简单迭代聚类的鲁棒模型拟合

2018 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2018-12-01 DOI: 10.1109/VCIP.2018.8698736

H. Luo, Guobao Xiao, Hanzi Wang

引用次数: 2

Optimized Spatial Recurrent Network for Intra Prediction in Video Coding 基于优化空间循环网络的视频编码内预测

2018 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2018-12-01 DOI: 10.1109/VCIP.2018.8698658

Yueyu Hu, Wenhan Yang, Sifeng Xia, Jiaying Liu

引用次数: 8

Advanced Orientation Robust Face Detection Algorithm Using Prominent Features and Hybrid Learning Techniques 基于突出特征和混合学习技术的高级定向鲁棒人脸检测算法

2018 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2018-12-01 DOI: 10.1109/VCIP.2018.8698649

Chien-Yu Chen, Jian-Jiun Ding, H. Hsu, Yih-Cherng Lee

{"title":"Advanced Orientation Robust Face Detection Algorithm Using Prominent Features and Hybrid Learning Techniques","authors":"Chien-Yu Chen, Jian-Jiun Ding, H. Hsu, Yih-Cherng Lee","doi":"10.1109/VCIP.2018.8698649","DOIUrl":"https://doi.org/10.1109/VCIP.2018.8698649","url":null,"abstract":"Face detection is one of the most popular topics in computer vision. There are several well-known techniques for face detection, such as the Viola-Jones detector. However, the performance of the Viola-Jones detector is limited since it mainly applies the simple Haar-based features. Many advanced methods, especially the convolutional neural network (CNN) based method, have very good performance in face detection. However, they require huge amount of training data. Moreover, most of existing algorithms are not robust to rotation, head-up, and head-down cases. In this paper, we find that, with some modifications, the Viola-Jones detector can also have very good performance in face detection. In addition to the Haar features, we also apply the prominent features and the color information. With the contour information, the edge-aware filter, the background smoother, the fuzzy classifier, and the relative locations, the prominent features, such as eyes, mouths, noses, and ears, can be extracted accurately. With these features, the accuracy of face detection can be much improved. Simulations show that, even if huge amount of training data is not applied, the proposed algorithm has better performance than state-of-the-art face detection methods, including the CNN-based method.","PeriodicalId":270457,"journal":{"name":"2018 IEEE Visual Communications and Image Processing (VCIP)","volume":"315 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132553615","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Weighted Two-Phase Linear Reconstruction Measure-based Classification 基于加权两相线性重构测度的分类方法

2018 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2018-12-01 DOI: 10.1109/VCIP.2018.8698656

Jianping Gou, Jun Song, Heping Song, Liangjun Wang

引用次数: 0