2013 IEEE Conference on Computer Vision and Pattern Recognition最新文献

Segment-Tree Based Cost Aggregation for Stereo Matching 基于分割树的成本聚合立体匹配

2013 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2017-02-27 DOI: 10.1109/ICASSP.2017.7952512

Peng Yao, Hua Zhang, Yanbing Xue, Mian Zhou, Guangping Xu, Zan Gao, Shengyong Chen

{"title":"Segment-Tree Based Cost Aggregation for Stereo Matching","authors":"Peng Yao, Hua Zhang, Yanbing Xue, Mian Zhou, Guangping Xu, Zan Gao, Shengyong Chen","doi":"10.1109/ICASSP.2017.7952512","DOIUrl":"https://doi.org/10.1109/ICASSP.2017.7952512","url":null,"abstract":"This paper presents a novel tree-based cost aggregation method for dense stereo matching. Instead of employing the minimum spanning tree (MST) and its variants, a new tree structure, \"Segment-Tree\", is proposed for non-local matching cost aggregation. Conceptually, the segment-tree is constructed in a three-step process: first, the pixels are grouped into a set of segments with the reference color or intensity image, second, a tree graph is created for each segment, and in the final step, these independent segment graphs are linked to form the segment-tree structure. In practice, this tree can be efficiently built in time nearly linear to the number of the image pixels. Compared to MST where the graph connectivity is determined with local edge weights, our method introduces some 'non-local' decision rules: the pixels in one perceptually consistent segment are more likely to share similar disparities, and therefore their connectivity within the segment should be first enforced in the tree construction process. The matching costs are then aggregated over the tree within two passes. Performance evaluation on 19 Middlebury data sets shows that the proposed method is comparable to previous state-of-the-art aggregation methods in disparity accuracy and processing speed. Furthermore, the tree structure can be refined with the estimated disparities, which leads to consistent scene segmentation and significantly better aggregation results.","PeriodicalId":6343,"journal":{"name":"2013 IEEE Conference on Computer Vision and Pattern Recognition","volume":"76 1","pages":"313-320"},"PeriodicalIF":0.0,"publicationDate":"2017-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87048196","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: 137

Tag Taxonomy Aware Dictionary Learning for Region Tagging 基于标签分类的区域标注字典学习

2013 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2013-06-23 DOI: 10.1109/CVPR.2013.54

Jingjing Zheng, Zhuolin Jiang

引用次数: 9

Simultaneous Super-Resolution of Depth and Images Using a Single Camera 同时超分辨率的深度和图像使用一个单一的相机

2013 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2013-06-23 DOI: 10.1109/CVPR.2013.43

Hee Seok Lee, Kyoung Mu Lee

引用次数: 21

Probabilistic Label Trees for Efficient Large Scale Image Classification 基于概率标记树的高效大规模图像分类

2013 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2013-06-23 DOI: 10.1109/CVPR.2013.114

Baoyuan Liu, Fereshteh Sadeghi, M. Tappen, O. Shamir, Ce Liu

引用次数: 82

Subspace Interpolation via Dictionary Learning for Unsupervised Domain Adaptation 基于字典学习的无监督域自适应子空间插值

2013 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2013-06-23 DOI: 10.1109/CVPR.2013.95

Jie Ni, Qiang Qiu, R. Chellappa

引用次数: 188

Manhattan Junction Catalogue for Spatial Reasoning of Indoor Scenes 室内场景空间推理曼哈顿枢纽目录

2013 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2013-06-23 DOI: 10.1109/CVPR.2013.394

S. Ramalingam, Jaishanker K. Pillai, Arpit Jain, Yuichi Taguchi

引用次数: 59

Robust Multi-resolution Pedestrian Detection in Traffic Scenes 交通场景中鲁棒多分辨率行人检测

2013 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2013-06-23 DOI: 10.1109/CVPR.2013.390

Junjie Yan, Xucong Zhang, Zhen Lei, Shengcai Liao, S. Li

{"title":"Robust Multi-resolution Pedestrian Detection in Traffic Scenes","authors":"Junjie Yan, Xucong Zhang, Zhen Lei, Shengcai Liao, S. Li","doi":"10.1109/CVPR.2013.390","DOIUrl":"https://doi.org/10.1109/CVPR.2013.390","url":null,"abstract":"The serious performance decline with decreasing resolution is the major bottleneck for current pedestrian detection techniques. In this paper, we take pedestrian detection in different resolutions as different but related problems, and propose a Multi-Task model to jointly consider their commonness and differences. The model contains resolution aware transformations to map pedestrians in different resolutions to a common space, where a shared detector is constructed to distinguish pedestrians from background. For model learning, we present a coordinate descent procedure to learn the resolution aware transformations and deformable part model (DPM) based detector iteratively. In traffic scenes, there are many false positives located around vehicles, therefore, we further build a context model to suppress them according to the pedestrian-vehicle relationship. The context model can be learned automatically even when the vehicle annotations are not available. Our method reduces the mean miss rate to 60% for pedestrians taller than 30 pixels on the Caltech Pedestrian Benchmark, which noticeably outperforms previous state-of-the-art (71%).","PeriodicalId":6343,"journal":{"name":"2013 IEEE Conference on Computer Vision and Pattern Recognition","volume":"1 1","pages":"3033-3040"},"PeriodicalIF":0.0,"publicationDate":"2013-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72675360","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: 187

Blur Processing Using Double Discrete Wavelet Transform 基于双离散小波变换的模糊处理

2013 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2013-06-23 DOI: 10.1109/CVPR.2013.145

Yi Zhang, Keigo Hirakawa

引用次数: 51

Dense Non-rigid Point-Matching Using Random Projections 使用随机投影的密集非刚性点匹配

2013 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2013-06-23 DOI: 10.1109/CVPR.2013.375

Raffay Hamid, D. DeCoste, Chih-Jen Lin

{"title":"Dense Non-rigid Point-Matching Using Random Projections","authors":"Raffay Hamid, D. DeCoste, Chih-Jen Lin","doi":"10.1109/CVPR.2013.375","DOIUrl":"https://doi.org/10.1109/CVPR.2013.375","url":null,"abstract":"We present a robust and efficient technique for matching dense sets of points undergoing non-rigid spatial transformations. Our main intuition is that the subset of points that can be matched with high confidence should be used to guide the matching procedure for the rest. We propose a novel algorithm that incorporates these high-confidence matches as a spatial prior to learn a discriminative subspace that simultaneously encodes both the feature similarity as well as their spatial arrangement. Conventional subspace learning usually requires spectral decomposition of the pair-wise distance matrix across the point-sets, which can become inefficient even for moderately sized problems. To this end, we propose the use of random projections for approximate subspace learning, which can provide significant time improvements at the cost of minimal precision loss. This efficiency gain allows us to iteratively find and remove high-confidence matches from the point sets, resulting in high recall. To show the effectiveness of our approach, we present a systematic set of experiments and results for the problem of dense non-rigid image-feature matching.","PeriodicalId":6343,"journal":{"name":"2013 IEEE Conference on Computer Vision and Pattern Recognition","volume":"17 1","pages":"2914-2921"},"PeriodicalIF":0.0,"publicationDate":"2013-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79342251","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: 11

Axially Symmetric 3D Pots Configuration System Using Axis of Symmetry and Break Curve 利用对称轴和断裂曲线的轴对称三维罐形系统

2013 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2013-06-23 DOI: 10.1109/CVPR.2013.40

Kilho Son, Eduardo B. Almeida, D. Cooper

{"title":"Axially Symmetric 3D Pots Configuration System Using Axis of Symmetry and Break Curve","authors":"Kilho Son, Eduardo B. Almeida, D. Cooper","doi":"10.1109/CVPR.2013.40","DOIUrl":"https://doi.org/10.1109/CVPR.2013.40","url":null,"abstract":"This paper introduces a novel approach for reassembling pot sherds found at archaeological excavation sites, for the purpose of reconstructing clay pots that had been made on a wheel. These pots and the sherds into which they have broken are axially symmetric. The reassembly process can be viewed as 3D puzzle solving or generalized cylinder learning from broken fragments. The estimation exploits both local and semi-global geometric structure, thus making it a fundamental problem of geometry estimation from noisy fragments in computer vision and pattern recognition. The data used are densely digitized 3D laser scans of each fragment's outer surface. The proposed reassembly system is automatic and functions when the pile of available fragments is from one or multiple pots, and even when pieces are missing from any pot. The geometric structure used are curves on the pot along which the surface had broken and the silhouette of a pot with respect to an axis, called axis-profile curve (APC). For reassembling multiple pots with or without missing pieces, our algorithm estimates the APC from each fragment, then reassembles into configurations the ones having distinctive APC. Further growth of configurations is based on adding remaining fragments such that their APC and break curves are consistent with those of a configuration. The method is novel, more robust and handles the largest numbers of fragments to date.","PeriodicalId":6343,"journal":{"name":"2013 IEEE Conference on Computer Vision and Pattern Recognition","volume":"32 1","pages":"257-264"},"PeriodicalIF":0.0,"publicationDate":"2013-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85487967","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: 43