2017 IEEE International Conference on Image Processing (ICIP)最新文献_第5页

Coding sensitive based approximation algorithm for power efficient VBS-DCT VLSI design in HEVC hardwired Intra encoder 基于编码敏感的高效节能VBS-DCT VLSI设计算法

2017 IEEE International Conference on Image Processing (ICIP) Pub Date : 2017-09-17 DOI: 10.1109/ICIP.2017.8296833

Liangliang Chang, Zhenyu Liu, Xiangyang Ji, Dongsheng Wang

{"title":"Coding sensitive based approximation algorithm for power efficient VBS-DCT VLSI design in HEVC hardwired Intra encoder","authors":"Liangliang Chang, Zhenyu Liu, Xiangyang Ji, Dongsheng Wang","doi":"10.1109/ICIP.2017.8296833","DOIUrl":"https://doi.org/10.1109/ICIP.2017.8296833","url":null,"abstract":"High Efficiency Video Coding (HEVC), emerging as the latest video coding standard, obtained a 50% bit-rate reduction while maintaining the competitive visual quality as H.264/AVC. Rate-Distortion Optimization (RDO) is a computation intensive module in HEVC encoding. In specific, during Intra coding, RDO accounts for 62% of the overall encoding time. The 2-dimensional DCT is the most area and power consuming component for VLSI implementation of RDO module. In this paper, we decompose the matrix multiplication of DCT into several sparse butterfly structures in series. In addition, the computation and the storage of 25% high frequency coefficients are dropped by our approximation algorithm. The proposed algorithms are integrated in HM15.0. It is verified that our methods could save 15.9% time with 1.03% BDBR augment. We further implement the DCT VLSI design using TSMC 90nm standard cell library. In worst conditions (125°C, 0.9V), the power dissipation of our DCT is 12.7mW at the 311MHz maximum clock speed. As compared to the primitive design, we achieved 71.9% of hardware and 70.2% of power reductions.","PeriodicalId":229602,"journal":{"name":"2017 IEEE International Conference on Image Processing (ICIP)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127682158","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

Robust linear unmixing with enhanced sparsity 增强稀疏性的鲁棒线性解混

2017 IEEE International Conference on Image Processing (ICIP) Pub Date : 2017-09-17 DOI: 10.1109/ICIP.2017.8296861

Alexandre Tiard, Laurent Condat, Lucas Drumetz, J. Chanussot, W. Yin, Xiaoxiang Zhu

引用次数: 3

High quality reconstruction of dynamic objects using 2D-3D camera fusion 利用2D-3D相机融合实现动态物体的高质量重建

2017 IEEE International Conference on Image Processing (ICIP) Pub Date : 2017-09-17 DOI: 10.1109/ICIP.2017.8296674

Cansen Jiang, Dennis Christie, D. Paudel, C. Demonceaux

引用次数: 5

Age-dependent saccadic models for predicting eye movements 预测眼球运动的年龄依赖的跳眼模型

2017 IEEE International Conference on Image Processing (ICIP) Pub Date : 2017-09-17 DOI: 10.1109/ICIP.2017.8296981

O. Meur, A. Coutrot, Adrien Le Roch, A. Helo, P. Rama, Zhi Liu

引用次数: 4

Deformation transfer of 3D human shapes and poses on manifolds 三维人体形状和姿态在流形上的变形转移

2017 IEEE International Conference on Image Processing (ICIP) Pub Date : 2017-09-17 DOI: 10.1109/ICIP.2017.8296275

Abd El Rahman Shabayek, Djamila Aouada, Alexandre Saint, B. Ottersten

引用次数: 9

On some global topological aspects of manifold learning 流形学习的一些全局拓扑问题

2017 IEEE International Conference on Image Processing (ICIP) Pub Date : 2017-09-17 DOI: 10.1109/ICIP.2017.8296276

J. Manton, N. L. Bihan

引用次数: 0

Accurate tumor segmentation in FDG-PET images with guidance of complementary CT images 在互补CT图像的指导下，FDG-PET图像精确分割肿瘤

2017 IEEE International Conference on Image Processing (ICIP) Pub Date : 2017-09-17 DOI: 10.1109/ICIP.2017.8297123

C. Lian, S. Ruan, T. Denoeux, Yu Guo, P. Vera

引用次数: 4

Accurate dense stereo matching for road scenes 精确密集的立体匹配道路场景

2017 IEEE International Conference on Image Processing (ICIP) Pub Date : 2017-09-17 DOI: 10.1109/ICIP.2017.8296375

Oussama Zeglazi, M. Rziza, A. Amine, C. Demonceaux

引用次数: 5

From neonatal to adult brain MR image segmentation in a few seconds using 3D-like fully convolutional network and transfer learning 使用3d全卷积网络和迁移学习在几秒钟内完成从新生儿到成人的脑MR图像分割

2017 IEEE International Conference on Image Processing (ICIP) Pub Date : 2017-09-17 DOI: 10.1109/ICIP.2017.8297117

Yongchao Xu, T. Géraud, I. Bloch

{"title":"From neonatal to adult brain MR image segmentation in a few seconds using 3D-like fully convolutional network and transfer learning","authors":"Yongchao Xu, T. Géraud, I. Bloch","doi":"10.1109/ICIP.2017.8297117","DOIUrl":"https://doi.org/10.1109/ICIP.2017.8297117","url":null,"abstract":"Brain magnetic resonance imaging (MRI) is widely used to assess brain development in neonates and to diagnose a wide range of neurological diseases in adults. Such studies are usually based on quantitative analysis of different brain tissues, so it is essential to be able to classify them accurately. In this paper, we propose a fast automatic method that segments 3D brain MR images into different tissues using fully convolutional network (FCN) and transfer learning. As compared to existing deep learning-based approaches that rely either on 2D patches or on fully 3D FCN, our method is way much faster: it only takes a few seconds, and only a single modality (T1 or T2) is required. In order to take the 3D information into account, all 3 successive 2D slices are stacked to form a set of 2D “color” images, which serve as input for the FCN pre-trained on ImageNet for natural image classification. To the best of our knowledge, this is the first method that applies transfer learning to segment both neonatal and adult brain 3D MR images. Our experiments on two public datasets show that our method achieves state-of-the-art results.","PeriodicalId":229602,"journal":{"name":"2017 IEEE International Conference on Image Processing (ICIP)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130953403","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: 40

Visual comfort assessment of stereoscopic images using deep visual and disparity features based on human attention 利用基于人类注意力的深度视觉和差异特征评估立体图像的视觉舒适度

2017 IEEE International Conference on Image Processing (ICIP) Pub Date : 2017-09-17 DOI: 10.1109/ICIP.2017.8296374

Hyunwook Jeong, Hak Gu Kim, Yong Man Ro

引用次数: 15