发布求助
文献互助 智能选刊 最新文献

2019 IEEE Visual Communications and Image Processing (VCIP)最新文献

筛选
英文 中文
A Progressive Network Based on Residual Multi-scale Aggregation for Image Super-Resolution 基于残差多尺度聚合的图像超分辨率渐进式网络
2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8966039
Anqi Liu, Sumei Li, Sheng Chen
{"title":"A Progressive Network Based on Residual Multi-scale Aggregation for Image Super-Resolution","authors":"Anqi Liu, Sumei Li, Sheng Chen","doi":"10.1109/VCIP47243.2019.8966039","DOIUrl":"https://doi.org/10.1109/VCIP47243.2019.8966039","url":null,"abstract":"In recent years, with the rapid development of deep learning, single image super-resolution based on convolution neural network has achieved extensive research. However, most CNN-based method has difficulty in training and obtaining high quality images for large scale factors. To address these issues, we propose a network, which reconstructs HR images at large factors by progressively performing 2× SR on the input from the previous level. At each level, cascaded residual multi-scale aggregation blocks are used. The U-residual unit in it makes network simplifier and training easier without performance degradation. The multi-scale dilated unit in it provides more comprehensive information for image reconstruction. Before upsampling, the channel attention mechanism is adopted to recalibrate features. We train the network with two-stage training strategy which could accelerate the convergence and achieve better performance. Experiment results show that our proposed method is superior to the state-of-the-art methods on most datasets, especially on Urban100.","PeriodicalId":388109,"journal":{"name":"2019 IEEE Visual Communications and Image Processing (VCIP)","volume":"95 39","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134505401","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
Prediction Refinement with Optical Flow for Affine Motion Compensation 基于光流的仿射运动补偿预测精细化
2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8965942
Jiancong Luo, Yuwen He, Wei Chen
{"title":"Prediction Refinement with Optical Flow for Affine Motion Compensation","authors":"Jiancong Luo, Yuwen He, Wei Chen","doi":"10.1109/VCIP47243.2019.8965942","DOIUrl":"https://doi.org/10.1109/VCIP47243.2019.8965942","url":null,"abstract":"Affine motion compensation (AMC) has been adopted in the latest working draft of the Versatile Video Coding (VVC) standard jointly developed by ITU-T VCEG and ISO/IEC MPEG. The AMC in the VVC working draft is implemented as a sub-block based MC rather than pixel-based MC in order to reduce the memory access bandwidth and computation complexity, which loses prediction efficiency. The proposed algorithm in this paper is to improve the MC granularity by using pixel-based optical flow refinement. The affine prediction efficiency will be close to the pixel-based MC refinement without increasing external memory access. The experiment results show that on average the proposed algorithm can achieve 0.86% and 0.87% BD rate saving for random access and low delay B configurations, respectively, comparing to the VTM-4.0. The BD rate saving is up to 3.10%.","PeriodicalId":388109,"journal":{"name":"2019 IEEE Visual Communications and Image Processing (VCIP)","volume":"122 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133519792","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: 2
Feature-Based Patch Matching for Moving Object Detection 基于特征的补丁匹配运动目标检测
2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8966047
M. Russell, J. Zou, G. Fang, Weidong (Tom) Cai
{"title":"Feature-Based Patch Matching for Moving Object Detection","authors":"M. Russell, J. Zou, G. Fang, Weidong (Tom) Cai","doi":"10.1109/VCIP47243.2019.8966047","DOIUrl":"https://doi.org/10.1109/VCIP47243.2019.8966047","url":null,"abstract":"In this paper, a new background subtraction framework is proposed to deal with possible scenarios occurring in natural scenes. In this method, a combination of two feature descriptors, namely color information in HSV color format and global texture descriptor T, are introduced to effectively identify background points under varying conditions. Using these features, an adaptive background model is constructed to automatically adapt to scene changes. The proposed framework is evaluated on common change detection datasets, showing improved performance compared to three well-known methods.","PeriodicalId":388109,"journal":{"name":"2019 IEEE Visual Communications and Image Processing (VCIP)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116640263","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
Pose Recognition for Dense Vehicles under Complex Street Scenario 复杂街道场景下密集车辆姿态识别
2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8965812
Zhenjia Fan, Z. Chen, Junyi Wu, Chenhao Pei
{"title":"Pose Recognition for Dense Vehicles under Complex Street Scenario","authors":"Zhenjia Fan, Z. Chen, Junyi Wu, Chenhao Pei","doi":"10.1109/VCIP47243.2019.8965812","DOIUrl":"https://doi.org/10.1109/VCIP47243.2019.8965812","url":null,"abstract":"Locating vehicles in the surrounding environment and distinguishing their poses are crucial in autonomous driving systems. An intelligent transportation system expects a vision-based object detector not only to detect and classify vehicles but also to recognize the poses of them in estimating their future movement direction. However, most of the current object detection algorithms only classify different classes of vehicles; and there are rare studies on classifying different poses within the same class of vehicles. In addition, the currently available datasets have no annotation data that are specific to different poses of intra-class vehicles. To achieve the vehicles pose recognition, we build a vehicle pose dataset based on the Cityscapes dataset. Furthermore, we also improve the network model of the YOLO v2 detector to support simultaneous vehicle detection and pose classification with an improvement of 10.71% mean average precision (mAP) comparing to the default network which runs in real-time with 29 FPS.","PeriodicalId":388109,"journal":{"name":"2019 IEEE Visual Communications and Image Processing (VCIP)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122112418","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: 1
Enhanced Intra Prediction Scheme in Point Cloud Attribute Compression 改进的点云属性压缩内部预测方案
2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8966001
Honglian Wei, Yiting Shao, Jing Wang, Shan Liu, Ge Li
{"title":"Enhanced Intra Prediction Scheme in Point Cloud Attribute Compression","authors":"Honglian Wei, Yiting Shao, Jing Wang, Shan Liu, Ge Li","doi":"10.1109/VCIP47243.2019.8966001","DOIUrl":"https://doi.org/10.1109/VCIP47243.2019.8966001","url":null,"abstract":"3D point cloud compression (PCC) has been an attractive field with increasing applications in recent years. Moving Picture Experts Group (MPEG) is building an open standard for point cloud compression, consisting of two solutions, video-based point cloud compression (V-PCC) and geometry-based point cloud compression (G-PCC). As an essential process in G-PCC, K-nearest neighbors (KNN) algorithm is adopted to perform intra prediction, which only considering distance-based local similarity but neglecting the overall geometric distribution of the neighbor set. In this paper, we propose an enhanced intra prediction scheme based on point-cloud geometric distribution. The centroid-based criterion is introduced to measure the uniformity of spatial distribution of predictive reference points. Our scheme is implemented in G-PCC reference software. Experimental results demonstrate that our proposed method can optimize the selection of predictors, which leads to better rate-distortion (R-D) performance than the G-PCC anchor on point cloud datasets under the common test conditions (CTC).","PeriodicalId":388109,"journal":{"name":"2019 IEEE Visual Communications and Image Processing (VCIP)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122190119","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
RGB-thermal Imaging System Collaborated with Marker Tracking for Remote Breathing Rate Measurement rgb热成像系统与远程呼吸率测量的标记跟踪合作
2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8965987
Lushuang Chen, Ning Liu, Menghan Hu, Guangtao Zhai
{"title":"RGB-thermal Imaging System Collaborated with Marker Tracking for Remote Breathing Rate Measurement","authors":"Lushuang Chen, Ning Liu, Menghan Hu, Guangtao Zhai","doi":"10.1109/VCIP47243.2019.8965987","DOIUrl":"https://doi.org/10.1109/VCIP47243.2019.8965987","url":null,"abstract":"The pixel variation signal extracted from the nasal region of RGB-thermal images can be used to achieve breathing rate (BR) measurement. However, this method fails when the nasal region is not detected in complicated motion scenarios. In this paper, we develop an RGB-thermal imaging system collaborated with marker sticker to achieve unobtrusive and accurate BR measurement. Pixel variation signal of Regions of interest (ROI) is extracted from the thermal video and chest movement signal is extracted from the RGB video with the assistance of marker stickers. Subsequently, a custom-made time-domain signal processing approach is developed for determining BR. We further propose a method of splicing computation to measure the BR after separate processing of signal segments. We construct an RGB-thermal video dataset with different head and body movements to evaluate the effectiveness of the proposed algorithm. After linear regression analysis, the determination coefficient (R2) of 0.905 has been observed for the estimated and reference BRs, indicating the feasibility of our proposed method in complex motion scenarios.","PeriodicalId":388109,"journal":{"name":"2019 IEEE Visual Communications and Image Processing (VCIP)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123770923","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: 9
Morphology Reconstruction of Obstructed Coronary Artery in Angiographic Images 冠脉造影图像中冠脉阻塞的形态重建
2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8966015
Tianming Du, Xiaotong Shi, Ruijia Wu, Honggang Zhang, Xiaolin Song, Jin Feng, Fuzhuo Sun
{"title":"Morphology Reconstruction of Obstructed Coronary Artery in Angiographic Images","authors":"Tianming Du, Xiaotong Shi, Ruijia Wu, Honggang Zhang, Xiaolin Song, Jin Feng, Fuzhuo Sun","doi":"10.1109/VCIP47243.2019.8966015","DOIUrl":"https://doi.org/10.1109/VCIP47243.2019.8966015","url":null,"abstract":"In cardiac arterial interventional therapy, coronary angiograms provides key information to physicians for treatment strategy selection. However, it is hard to extract the information about arteries with CTO lesion in absence of contrast opacification and visualization of the CTO coronary arteries in angiograms. In this paper, we present an algorithm, which can predict the extension direction of artery with CTO and reconstruct the morphology of blocked artery in coronary angiograms. First, our algorithm segment the CTO artery angiogram and extract the artery skeleton. Second, an iterative approach is preformed to reconstruct the skeleton of blocked artery. Finally, our algorithm generates the simulated postoperative angiogram according to the skeleton image. The results demonstrate that automatic morphology reconstructing of CTO coronary artery with high accuracy and reliability is feasible.","PeriodicalId":388109,"journal":{"name":"2019 IEEE Visual Communications and Image Processing (VCIP)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121939316","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
Stereo Image Quality Assessment Based on Sparse Binocular Fusion Convolution Neural Network 基于稀疏双目融合卷积神经网络的立体图像质量评价
2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8965994
Sumei Li, Xuyang Han, Muhammad Zubair, Shuai Ma
{"title":"Stereo Image Quality Assessment Based on Sparse Binocular Fusion Convolution Neural Network","authors":"Sumei Li, Xuyang Han, Muhammad Zubair, Shuai Ma","doi":"10.1109/VCIP47243.2019.8965994","DOIUrl":"https://doi.org/10.1109/VCIP47243.2019.8965994","url":null,"abstract":"In this paper, a sparse binocular fusion convolution neural network is proposed to evaluate the quality of stereo image. In order to simulate the long-term fusion and processing of the left and right views in the brain visual pathway, the network combines the two views of the stereo image four times, and the information processing is carried out through convolution together with the fusion operation. In addition, in order to overcome the computational-intensive and memory-intensive problems of convolution neural networks, a structural sparsity learning (SSL) method is used to regularize the proposed convolution neural network. The experimental results demonstrate that our proposed method performs effectively and efficiently. And the proposed method can achieve 2.0× speedups on LIVE I database and 2.3× speedup on LIVE II database on the basis of improved performance.","PeriodicalId":388109,"journal":{"name":"2019 IEEE Visual Communications and Image Processing (VCIP)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122313675","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: 2
Semantic Segmentation via Domain Adaptation with Global Structure Embedding 基于全局结构嵌入的领域自适应语义分割
2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8965764
Tianyi Zhang, Guosheng Lin, Jianfei Cai, A. Kot
{"title":"Semantic Segmentation via Domain Adaptation with Global Structure Embedding","authors":"Tianyi Zhang, Guosheng Lin, Jianfei Cai, A. Kot","doi":"10.1109/VCIP47243.2019.8965764","DOIUrl":"https://doi.org/10.1109/VCIP47243.2019.8965764","url":null,"abstract":"In this paper we focus on the problem of unsupervised domain adaptation for semantic segmentation. The previous works usually focus on adversarial learning either in pixel-level or feature-level. However, global structure knowledge is often neglected in the adversarial learning due to the possible reasons: First, the result of pixel-level adversarial learning does not necessarily preserve the semantic consistency of the input image. Second, global structure knowledge is not embedded to regularize the feature-level adversarial learning. In this work, we propose a framework for unsupervised domain adaptation in semantic segmentation which effectively incorporates pixel- level, feature-level adversarial learning and self-training strategy. Our framework embeds the global structure knowledge into the adversarial training step to tackle the problem of structure misalignment. Consequently, our proposed framework achieves the state-of-the-art semantic segmentation domain adaptation results on the task of transferring GTA5 to Cityscapes.","PeriodicalId":388109,"journal":{"name":"2019 IEEE Visual Communications and Image Processing (VCIP)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129986899","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: 1
Edge-Detection Based Fast Intra-Mode Selection for Depth Map Coding in 3D-HEVC 基于边缘检测的3D-HEVC深度图编码快速模内选择
2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8966012
Ruyi Zhang, Ke-bin Jia, Pengyu Liu, Zhonghua Sun
{"title":"Edge-Detection Based Fast Intra-Mode Selection for Depth Map Coding in 3D-HEVC","authors":"Ruyi Zhang, Ke-bin Jia, Pengyu Liu, Zhonghua Sun","doi":"10.1109/VCIP47243.2019.8966012","DOIUrl":"https://doi.org/10.1109/VCIP47243.2019.8966012","url":null,"abstract":"3D-High Efficiency Video Coding (3D-HEVC) contains more encoding viewpoints than traditional HEVC, resulting in a significant increase of coding complexity. In this paper, we propose a low complexity intra-mode selection algorithm to reduce the number of intra-modes by detecting the flat area and texture direction of the depth map. The corresponding intra-prediction modes are skipped when the flat region condition is satisfied. Otherwise, the direction of the edge is detected to decrease the number of angle modes in RMD, which can reduce the intra-coding complexity and coding time cost. Experimental results demonstrate that the proposed algorithm achieves on average 36.48% time saving with negligible degradation of coding performance.","PeriodicalId":388109,"journal":{"name":"2019 IEEE Visual Communications and Image Processing (VCIP)","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123169453","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: 5
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信
小红书