2015 12th Conference on Computer and Robot Vision最新文献

筛选
英文 中文
A Method for Global Non-rigid Registration of Multiple Thin Structures 多薄结构的全局非刚性配准方法
2015 12th Conference on Computer and Robot Vision Pub Date : 2015-06-03 DOI: 10.1109/CRV.2015.35
M. Brophy, Ayan Chaudhury, S. Beauchemin, J. Barron
{"title":"A Method for Global Non-rigid Registration of Multiple Thin Structures","authors":"M. Brophy, Ayan Chaudhury, S. Beauchemin, J. Barron","doi":"10.1109/CRV.2015.35","DOIUrl":"https://doi.org/10.1109/CRV.2015.35","url":null,"abstract":"We present a global algorithm for drift free alignment of multiple range scans of \"thin\" data into a single point cloud that is suitable for further processing, such as triangular meshing and volume calculation. We consider two sets of non-rigid data: synthetic vascular data and real Arabidopsis plant data. Our method builds on the coherent point drift algorithm, and aligns multiple point clouds into a single 3D point cloud. The plant data was acquired in a growth chamber, where the fan caused jittering in both the branch and leaf data. For each scan, we construct a target scan from the cancroids of its Mutual Nearest Neighbours (MNN) in all other scans and iteratively register to this, as opposed to registering pair wise scans sequentially. We have have adapted MNN for use in non-rigid scenarios, producing a method that will will not degrade as more scans are registered, and produces better results than sequential pair wise registration.","PeriodicalId":257595,"journal":{"name":"2015 12th Conference on Computer and Robot Vision","volume":"43 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123508912","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
Face Retrieval on Large-Scale Video Data 基于大规模视频数据的人脸检索
2015 12th Conference on Computer and Robot Vision Pub Date : 2015-06-03 DOI: 10.1109/CRV.2015.32
C. Herrmann, J. Beyerer
{"title":"Face Retrieval on Large-Scale Video Data","authors":"C. Herrmann, J. Beyerer","doi":"10.1109/CRV.2015.32","DOIUrl":"https://doi.org/10.1109/CRV.2015.32","url":null,"abstract":"Increasingly large amounts of video data raise the question if large-scale face retrieval is feasible. To find fast and accurate matching strategies, an according face track descriptor is constructed by using local features, extended by an encoding of the respective measurement conditions. The feature encoding allows collecting all features of one face track together in a single feature set, where cumulative descriptors, known from image or object retrieval applications, especially bag of words and fisher vectors, can be applied. These descriptors are known to be viable for large-scale retrieval applications. To explore large-scale video face retrieval, we first evaluate on the largest available public datasets, i.e. You Tube Faces Database (YTF) and Face in Action Database (FiA). Finally, the behaviour of face retrieval for increasing amounts of data is investigated by combining these datasets with 55K face tracks, collected from about 100 hours of TV data, making it the largest collection of face tracks we are aware of.","PeriodicalId":257595,"journal":{"name":"2015 12th Conference on Computer and Robot Vision","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125770693","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: 13
At all Costs: A Comparison of Robust Cost Functions for Camera Correspondence Outliers 不惜一切代价:相机对应异常值的鲁棒代价函数的比较
2015 12th Conference on Computer and Robot Vision Pub Date : 2015-06-03 DOI: 10.1109/CRV.2015.52
K. MacTavish, T. Barfoot
{"title":"At all Costs: A Comparison of Robust Cost Functions for Camera Correspondence Outliers","authors":"K. MacTavish, T. Barfoot","doi":"10.1109/CRV.2015.52","DOIUrl":"https://doi.org/10.1109/CRV.2015.52","url":null,"abstract":"Camera-based localization techniques must be robust to correspondence errors, i.e., when visual features (landmarks)are matched incorrectly. The two primary techniques to address this issue are RANSAC and robust M-estimation -- each more appropriate for different applications. This paper investigates the use of different robust cost functions for M-estimation to deal with correspondence outliers, and assesses their performance under varying degrees of data corruption. Experimental results show that using an aggressive red ascending cost function (e.g., Dynamic Covariance Scaling (DCS) or Geman-McClure (G-M)) best improves accuracy by excluding outliers almost entirely. Additionally, adjusting an error-scaling parameter for the robust cost function over the course of the optimization improves convergence with poor initial conditions.","PeriodicalId":257595,"journal":{"name":"2015 12th Conference on Computer and Robot Vision","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133323437","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: 71
Simultaneous Scene Reconstruction and Auto-Calibration Using Constrained Iterative Closest Point for 3D Depth Sensor Array 基于约束迭代最近点的三维深度传感器阵列同步场景重建与自动标定
2015 12th Conference on Computer and Robot Vision Pub Date : 2015-06-03 DOI: 10.1109/CRV.2015.13
M. Zhu, C. Scharfenberger, A. Wong, David A Clausi
{"title":"Simultaneous Scene Reconstruction and Auto-Calibration Using Constrained Iterative Closest Point for 3D Depth Sensor Array","authors":"M. Zhu, C. Scharfenberger, A. Wong, David A Clausi","doi":"10.1109/CRV.2015.13","DOIUrl":"https://doi.org/10.1109/CRV.2015.13","url":null,"abstract":"Being able to monitor a large area is essential for intelligent warehouse automation. Complete depth map of a plant floor allows Automated Guided Vehicles (AGV) to navigate the environment and safely interact with nearby people and equipment, eliminating the need for installation of guide tracks and range sensors on individual robots. A single camera does not have sufficient field of view irresolution to monitor a large scene, and a camera mounted on a moving platform introduces delays and blind spots that could put people at risk in busy areas. Multi-camera arrays are needed in order to reconstruct the scene from simultaneous captures. Existing iterative closest point (ICP) based algorithms fail to produce meaningful results due to ICP attempting to minimize Euclidean distance between non-matching pairs. This paper describes a method for accurate and computationally efficient simultaneous scene reconstruction and auto-calibration using depth maps captured with multiple downward looking overhead cameras. The proposed method extends upon standard ICP algorithm by incorporating constraints imposed by the camera setup. The common field of view constraint imposed on the ICP algorithm matches a subset of points that are simultaneously in two camera's field of view. The planar constraint restricts the search space for closest points between 2point clouds to be on a projected planar surface. To simulate a typical warehouse environment, depth maps captured from two overhead Microsoft Kinect cameras were used to evaluate the effectiveness of the proposed algorithm. The results indicate the proposed algorithm successfully reconstructed the scene and produced auto-calibrated extrinsic camera matrix, where as standard ICP algorithm did not generate meaningful results.","PeriodicalId":257595,"journal":{"name":"2015 12th Conference on Computer and Robot Vision","volume":"222 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115067621","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
Drifter Sensor Network for Environmental Monitoring 用于环境监测的漂流式传感器网络
2015 12th Conference on Computer and Robot Vision Pub Date : 2015-06-03 DOI: 10.1109/CRV.2015.10
Daniel Boydstun, Matthew Farich, J. McCarthy, S. Rubinson, Zachary Smith, Ioannis M. Rekleitis
{"title":"Drifter Sensor Network for Environmental Monitoring","authors":"Daniel Boydstun, Matthew Farich, J. McCarthy, S. Rubinson, Zachary Smith, Ioannis M. Rekleitis","doi":"10.1109/CRV.2015.10","DOIUrl":"https://doi.org/10.1109/CRV.2015.10","url":null,"abstract":"This paper presents the design, development, and deployment of a sensor network of drifter nodes. The target domain is coastal water monitoring, and study of LaGrange water dynamics. The nodes are equipped with a camera, inertial measurement unit (IMU), GPS, WiFi, and a computing unit. Each unit is water resistant, with buoyancy characteristics that enable it to float in a vertical position. The sensors are capable of recording relocated visual data at variable rates. They collect LaGrange current observations as they move along the water surface. In addition to the current measurements, the drifters are also recording image data that provide insights about the health of the marine life below the surface. We propose, to utilize the motion generated by the wave action in order to record wider field of view images from the ocean floor. Results from a successful deployment of the coast of Barbados are presented together with a discussion on lessons learned.","PeriodicalId":257595,"journal":{"name":"2015 12th Conference on Computer and Robot Vision","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133218645","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: 17
3D vs. 2D: On the Importance of Registration for Hallucinating Faces Under Unconstrained Poses 3D vs. 2D:关于在不受约束的姿势下产生幻觉的面部注册的重要性
2015 12th Conference on Computer and Robot Vision Pub Date : 2015-06-03 DOI: 10.1109/CRV.2015.26
Chengchao Qu, C. Herrmann, Eduardo Monari, T. Schuchert, J. Beyerer
{"title":"3D vs. 2D: On the Importance of Registration for Hallucinating Faces Under Unconstrained Poses","authors":"Chengchao Qu, C. Herrmann, Eduardo Monari, T. Schuchert, J. Beyerer","doi":"10.1109/CRV.2015.26","DOIUrl":"https://doi.org/10.1109/CRV.2015.26","url":null,"abstract":"Face Hallucination (FH) differs from generic single-image super-resolution (SR) algorithms in its specific domain of application. By exploiting the common structures of human faces, magnification of lower resolution images can be achieved. Despite the growing interest in recent years, considerably less attention is paid to a crucial step in FH -- registration of facial images. In this work, registration techniques employed in the literature are first summarized and the importance of using well-aligned training and test images is demonstrated. A novel method to inversely map the high-resolution (HR) 3D training texture to the low-resolution (LR) 2D test image in arbitrary poses is then presented, which prevents information loss in LR images and is thus beneficial to SR. The effectiveness of our 3D approach is evaluated on the Multi-PIE and the PUT face databases. Superior qualitative and quantitative FH results to the state-of-the-art methods in all tested poses prove the necessity of accurate registration in FH. The merit of 3D FH in generating super-resolved frontal faces is also verified, revealing 30% improvement in face recognition over the 2D approach under 30° of yaw rotation on the Multi-PIE dataset.","PeriodicalId":257595,"journal":{"name":"2015 12th Conference on Computer and Robot Vision","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133479550","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: 4
Deep Learning Architectures for Soil Property Prediction 土壤性质预测的深度学习架构
2015 12th Conference on Computer and Robot Vision Pub Date : 2015-06-03 DOI: 10.1109/CRV.2015.15
M. Veres, Griffin Lacey, Graham W. Taylor
{"title":"Deep Learning Architectures for Soil Property Prediction","authors":"M. Veres, Griffin Lacey, Graham W. Taylor","doi":"10.1109/CRV.2015.15","DOIUrl":"https://doi.org/10.1109/CRV.2015.15","url":null,"abstract":"Advances in diffuse reflectance infra-red spec-cryoscopy measurements have made it possible to estimate number of functional properties of soil inexpensively and accurately. Core to such techniques are machine learning methods that can map high-dimensional spectra to real-valued outputs. While previous works have considered predicting each property individually using simple regression methods, the correlation structure present in the output variables prompts us to consider methods that can leverage this structure to make more accurate predictions. In this paper, we leverage advances in deep learning architectures, specifically convolution neural networks and conditional restricted Boltzmann machines for structured output prediction for soil property prediction. We evaluate our methods on two recent spectral datasets, where output soil properties are shown to have a measurable degree of correlation.","PeriodicalId":257595,"journal":{"name":"2015 12th Conference on Computer and Robot Vision","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129429689","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: 31
Improving Segmentation Boundaries with Nonparametric Image Parsing 用非参数图像解析改进分割边界
2015 12th Conference on Computer and Robot Vision Pub Date : 2015-06-03 DOI: 10.1109/CRV.2015.50
Hong Pan, J. Lang
{"title":"Improving Segmentation Boundaries with Nonparametric Image Parsing","authors":"Hong Pan, J. Lang","doi":"10.1109/CRV.2015.50","DOIUrl":"https://doi.org/10.1109/CRV.2015.50","url":null,"abstract":"Semantic segmentation, or segmenting all the objects in an image is one of the core problems of computer vision. In order to achieve an object-level semantic segmentation, we propose to label image regions and to improve the segmentation result based on these labels. We build upon the recent super parsing approach, which is a nonparametric solution to the image labelling problem. We propose to initialize the segmentation with SLICO super pixels because SLICO is able to produce accurate boundaries and offers control over size, shape and compactness of the super pixels. These super pixels are labelled with super parsing but an optimization step is required for the large number of small super pixels. We formulate a Conditional Random Field (CRF) using a novel pair wise cost depending on local features and computed in a nonparametric estimation. This results in stronger semantic contextual constraints. We evaluate our improvements to the super parsing approach using segmentation evaluation measures as well as the per-pixel rate and average per-class rate in a labelling evaluation. We demonstrate the success of our modified approach on the SIFT Flow dataset.","PeriodicalId":257595,"journal":{"name":"2015 12th Conference on Computer and Robot Vision","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128715321","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
RKLT: 8 DOF Real-Time Robust Video Tracking Combing Coarse Ransac Features and Accurate Fast Template Registration RKLT: 8 DOF实时鲁棒视频跟踪结合粗Ransac特征和准确的快速模板配准
2015 12th Conference on Computer and Robot Vision Pub Date : 2015-06-03 DOI: 10.1109/CRV.2015.18
Xi Zhang, Abhineet Singh, Martin Jägersand
{"title":"RKLT: 8 DOF Real-Time Robust Video Tracking Combing Coarse Ransac Features and Accurate Fast Template Registration","authors":"Xi Zhang, Abhineet Singh, Martin Jägersand","doi":"10.1109/CRV.2015.18","DOIUrl":"https://doi.org/10.1109/CRV.2015.18","url":null,"abstract":"The performance of a tracker can be measured by two often conflicting criteria - robustness and accuracy. Recently researchers have focused on improving robustness, using adaptive appearance models. However updating the appearance model can cause drift and lower the accuracy of motion (state) estimation. These trackers generally compute 2 degree of freedom(DOF) image translation of the object, and are suited for applications such as surveillance. In contrast, we are interested in tracking objects using high DOF motion models - especially 8DOF homograph models that allow tracking of precise state information (projective 8D or calibrated 3Dworld translations and 3D rotations of the tracked object). Such precise state is required for visual motion control of e.g. robot arms, hands and UAV. To this end, we propose a novel tracking algorithm that combines KLT [8], RANSAC [21] and Inverse Compositional tracker [7]. First we sample a large patch into a set of small patches and track each one using frame-to-frame 2D KLT trackers. An 8 DOF homograph describing the large patch motion is then estimated from the current locations of these KLT trackers using RANSAC while also discarding lost trackers as outliers. Finally, using the RANSAC 8DOF motion estimate as the initial guess, we perform a few iterations of an IC registration tracker. This refines the patch motion to sub-pixel accuracy and avoids drift by registering to the original template. We perform three sets of experiments - one is the standard synthetic Lena convergence benchmark and two use real image sequences from recent datasets - to show that our tracker compares favourably with the state-of-the-art.","PeriodicalId":257595,"journal":{"name":"2015 12th Conference on Computer and Robot Vision","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116706766","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
Image Sensor Modeling: Noise and Linear Transformation Impacts on the Color Gamut 图像传感器建模:噪声和线性变换对色域的影响
2015 12th Conference on Computer and Robot Vision Pub Date : 2015-06-03 DOI: 10.1109/CRV.2015.29
Mehdi Rezagholizadeh, James J. Clark
{"title":"Image Sensor Modeling: Noise and Linear Transformation Impacts on the Color Gamut","authors":"Mehdi Rezagholizadeh, James J. Clark","doi":"10.1109/CRV.2015.29","DOIUrl":"https://doi.org/10.1109/CRV.2015.29","url":null,"abstract":"Linear transformations are widely used in the color science. Linear transformation can not ideally map the source and destination color matching functions and this issue induces some errors in the process of conversion. This error is usually deemed negligible for a noise-free system. However, in practice, imaging devices, displays, and printers employ linear transformations to move between color spaces and at the same time they are subject to noise which might magnify the linear transformation errors. The induced error by this phenomenon can bring about colorcasts and hampering the image quality. In this study, the effects of noise and linear transformation on the colorgamut are investigated. In this regard, a typical image sensor is modelled and employed for this study. A detailed model of noise is considered in the process of implementing the image sensor model to guarantee the precision of the results. Several experiments have been performed over the implemented framework and the results show that the imperfections of linear transformation combined with the image sensor noise shrinks the gamut area of output images.","PeriodicalId":257595,"journal":{"name":"2015 12th Conference on Computer and Robot Vision","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131655236","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
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
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