2017 IEEE International Conference on Image Processing (ICIP)最新文献_第10页

An object based graph representation for video comparison 用于视频比较的基于对象的图形表示

2017 IEEE International Conference on Image Processing (ICIP) Pub Date : 2017-09-15 DOI: 10.1109/ICIP.2017.8296742

Xin Feng, Yuanyi Xue, Yao Wang

{"title":"An object based graph representation for video comparison","authors":"Xin Feng, Yuanyi Xue, Yao Wang","doi":"10.1109/ICIP.2017.8296742","DOIUrl":"https://doi.org/10.1109/ICIP.2017.8296742","url":null,"abstract":"This paper develops a novel object based graph model for semantic video comparison. The model describes a video with detected objects as nodes, and relationship between the objects as edges in a graph. We investigated several spatial and temporal features as the graph node attributes, and different ways to describe the spatial-temporal relationship between objects as the edge attributes. To tackle the problem of erratic camera motion on the detected object, a global motion estimation and correction approach is proposed to reveal the true object trajectory. We further propose to evaluate the similarity between two videos by establishing the object correspondence between two object graphs through graph matching. The model is verified on a challenging user generated video dataset. Experiments show that our method outperforms other video representation frameworks in matching videos with the same semantic content. The proposed object graph provides a compact and robust semantic descriptor for a video, which can be used for applications such as video retrieval, clustering and summarization. The graph representation is also flexible to incorporate other features as node and edge attributes.","PeriodicalId":229602,"journal":{"name":"2017 IEEE International Conference on Image Processing (ICIP)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130292437","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

Complex coefficient representation for IIR bilateral filter IIR双边滤波器的复系数表示

2017 IEEE International Conference on Image Processing (ICIP) Pub Date : 2017-09-15 DOI: 10.1109/ICIP.2017.8296724

Norishige Fukushima, Kenjiro Sugimoto, S. Kamata

引用次数: 6

Coupled analysis-synthesis dictionary learning for person re-identification 人再识别的耦合分析-综合字典学习

2017 IEEE International Conference on Image Processing (ICIP) Pub Date : 2017-09-15 DOI: 10.1109/ICIP.2017.8296304

Lingchuan Sun, Yun Zhou, Zhuqing Jiang, Aidong Men

引用次数: 1

3D Mesh coding with predefined region-of-interest 3D网格编码与预定义的兴趣区域

2017 IEEE International Conference on Image Processing (ICIP) Pub Date : 2017-09-15 DOI: 10.1109/ICIP.2017.8296516

Jonas El Sayeh Khalil, A. Munteanu, P. Lambert

引用次数: 2

A hierarchical feature model for multi-target tracking 多目标跟踪的分层特征模型

2017 IEEE International Conference on Image Processing (ICIP) Pub Date : 2017-09-15 DOI: 10.1109/ICIP.2017.8296755

M. Ullah, A. Mohammed, F. A. Cheikh, Zhaohui Wang

引用次数: 32

Content adaptive video summarization using spatio-temporal features 基于时空特征的内容自适应视频摘要

2017 IEEE International Conference on Image Processing (ICIP) Pub Date : 2017-09-15 DOI: 10.1109/ICIP.2017.8297034

Hyunwoo Nam, C. Yoo

引用次数: 4

Deep CNN with color lines model for unmarked road segmentation 用于未标记道路分割的深度CNN彩色线模型

2017 IEEE International Conference on Image Processing (ICIP) Pub Date : 2017-09-15 DOI: 10.1109/ICIP.2017.8296348

Shashank Yadav, Suvam Patra, Chetan Arora, Subhashis Banerjee

{"title":"Deep CNN with color lines model for unmarked road segmentation","authors":"Shashank Yadav, Suvam Patra, Chetan Arora, Subhashis Banerjee","doi":"10.1109/ICIP.2017.8296348","DOIUrl":"https://doi.org/10.1109/ICIP.2017.8296348","url":null,"abstract":"Road detection from a monocular camera is an important perception module in any advanced driver assistance or autonomous driving system. Traditional techniques [1, 2, 3, 4, 5, 6] work reasonably well for this problem, when the roads are well maintained and the boundaries are clearly marked. However, in many developing countries or even for the rural areas in the developed countries, the assumption does not hold which leads to failure of such techniques. In this paper we propose a novel technique based on the combination of deep convolutional neural networks (CNNs), along with color lines model [7] based prior in a conditional random field (CRF) framework. While the CNN learns the road texture, the color lines model allows to adapt to varying illumination conditions. We show that our technique outperforms the state of the art segmentation techniques on the unmarked road segmentation problem. Though, not a focus of this paper, we show that even on the standard benchmark datasets like KITTI [8] and CamVid [9], where the road boundaries are well marked, the proposed technique performs competitively to the contemporary techniques.","PeriodicalId":229602,"journal":{"name":"2017 IEEE International Conference on Image Processing (ICIP)","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115763165","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: 27

Efficient cloud detection in remote sensing images using edge-aware segmentation network and easy-to-hard training strategy 基于边缘感知分割网络和易难训练策略的遥感图像云检测

2017 IEEE International Conference on Image Processing (ICIP) Pub Date : 2017-09-15 DOI: 10.1109/ICIP.2017.8296243

Kun Yuan, Gaofeng Meng, D. Cheng, Jun Bai, Shiming Xiang, Chunhong Pan

{"title":"Efficient cloud detection in remote sensing images using edge-aware segmentation network and easy-to-hard training strategy","authors":"Kun Yuan, Gaofeng Meng, D. Cheng, Jun Bai, Shiming Xiang, Chunhong Pan","doi":"10.1109/ICIP.2017.8296243","DOIUrl":"https://doi.org/10.1109/ICIP.2017.8296243","url":null,"abstract":"Detecting cloud regions in remote sensing image (RSI) is very challenging yet of great importance to meteorological forecasting and other RSI-related applications. Technically, this task is typically implemented as a pixel-level segmentation. However, traditional methods based on handcrafted or low-level cloud features often fail to achieve satisfactory performances from images with bright non-cloud and/or semitransparent cloud regions. What is more, the performances could be further degraded due to the ambiguous boundaries caused by complicated textures and non-uniform distribution of intensities. In this paper, we propose a multi-task based deep neural network for cloud detection in RSIs. Architecturally, our network is designed to combine the two tasks of cloud segmentation and cloud edge detection together to encourage a better detection near cloud boundaries, resulting in an end-to-end approach for accurate cloud detection. Accordingly, an efficient sample selection strategy is proposed to train our network in an easy-to-hard manner, in which the number of the selected samples is governed by a weight that is annealed until the entire training samples have been considered. Both visual and quantitative comparisons are conducted on RSIs collected from Google Earth. The experimental results indicate that our method can yield superior performance over the state-of-the-art methods.","PeriodicalId":229602,"journal":{"name":"2017 IEEE International Conference on Image Processing (ICIP)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123893505","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: 16

Demonstration of rapid frequency selective reconstruction for image resolution enhancement 快速频率选择性重建增强图像分辨率的演示

2017 IEEE International Conference on Image Processing (ICIP) Pub Date : 2017-09-15 DOI: 10.1109/ICIP.2017.8297158

Nils Genser, Jürgen Seiler, Markus Jonscher, André Kaup

引用次数: 9

Cascaded temporal spatial features for video action recognition 视频动作识别的级联时空特征

2017 IEEE International Conference on Image Processing (ICIP) Pub Date : 2017-09-15 DOI: 10.1109/ICIP.2017.8296542

Tingzhao Yu, Huxiang Gu, Lingfeng Wang, Shiming Xiang, Chunhong Pan

{"title":"Cascaded temporal spatial features for video action recognition","authors":"Tingzhao Yu, Huxiang Gu, Lingfeng Wang, Shiming Xiang, Chunhong Pan","doi":"10.1109/ICIP.2017.8296542","DOIUrl":"https://doi.org/10.1109/ICIP.2017.8296542","url":null,"abstract":"Extracting spatial-temporal descriptors is a challenging task for video-based human action recognition. We decouple the 3D volume of video frames directly into a cascaded temporal spatial domain via a new convolutional architecture. The motivation behind this design is to achieve deep nonlinear feature representations with reduced network parameters. First, a 1D temporal network with shared parameters is first constructed to map the video sequences along the time axis into feature maps in temporal domain. These feature maps are then organized into channels like those of RGB image (named as Motion Image here for abbreviation), which is desired to preserve both temporal and spatial information. Second, the Motion Image is regarded as the input of the latter cascaded 2D spatial network. With the combination of the 1D temporal network and the 2D spatial network together, the size of whole network parameters is largely reduced. Benefiting from the Motion Image, our network is an end-to-end system for the task of action recognition, which can be trained with the classical algorithm of back propagation. Quantities of comparative experiments on two benchmark datasets demonstrate the effectiveness of our new architecture.","PeriodicalId":229602,"journal":{"name":"2017 IEEE International Conference on Image Processing (ICIP)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127524294","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