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

筛选
英文 中文
A Perceptual Depth Shape-based CRF Model for Deformable Surface Labeling 基于感知深度形状的可变形曲面标记CRF模型
2015 12th Conference on Computer and Robot Vision Pub Date : 2015-06-03 DOI: 10.1109/CRV.2015.31
Gang Hu, Derek F. Reilly, Q. Gao, Arthur Bastos, Nhu loan Truong
{"title":"A Perceptual Depth Shape-based CRF Model for Deformable Surface Labeling","authors":"Gang Hu, Derek F. Reilly, Q. Gao, Arthur Bastos, Nhu loan Truong","doi":"10.1109/CRV.2015.31","DOIUrl":"https://doi.org/10.1109/CRV.2015.31","url":null,"abstract":"Real-time deformable scene understanding is a challenging task. In this paper, we address this problem by using Conditional random fields (CRFs) framework and perceptual shape salience occupancy patterns. CRF is a powerful probabilistic model that has been widely used for labelling image segments. It is particularly well-suited to modelling local interactions and global consistency among bottom-up regions (e.g. super pixels). However, its capacity could be limited if the underlying feature potentials are not well reflecting the scene properties. We propose a depth shape-based CRF model for deformable surface (sand in our case) labelling by utilizing expressive novel shape salience occupancy patterns (SOP). Experimental results demonstrate the effectiveness and robustness of the method on recorded video datasets. While our work has concentrated on sand surface labelling, the approach can be applied to other surface materials (e.g. snow, mud), and extended to non-planar surfaces as well (e.g. sculpting blocks).","PeriodicalId":257595,"journal":{"name":"2015 12th Conference on Computer and Robot Vision","volume":"18 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":"114575364","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
Registration of Noisy Point Clouds Using Virtual Interest Points 基于虚拟兴趣点的噪声点云配准
2015 12th Conference on Computer and Robot Vision Pub Date : 2015-06-03 DOI: 10.1109/CRV.2015.12
M. Ahmed, Mustafa Mohamad, J. Marshall, M. Greenspan
{"title":"Registration of Noisy Point Clouds Using Virtual Interest Points","authors":"M. Ahmed, Mustafa Mohamad, J. Marshall, M. Greenspan","doi":"10.1109/CRV.2015.12","DOIUrl":"https://doi.org/10.1109/CRV.2015.12","url":null,"abstract":"A new method is presented for robustly and efficiently registering two noisy point clouds. The registration is driven by establishing correspondences of virtual interest points, which do not exist in the original point cloud data, and redefined by the intersection of parametric surfaces extracted from the data. Parametric surfaces, such as planes, exist in abundance in both natural and artificial scenes, and can lead to regions in the data of relatively low noise. This in turn leads to repeatable virtual interest points, with stable locations across overlapping images. Experiments were run using virtual interest points defined by the intersection of three implicit planes, applied to data sets of four environments comprising100 point clouds. The proposed method outperformed the Iterative Closest Point, Generalized Iterative Closest Point, and a 2.5D SIFT-based RANSAC method in registering overlapping images with a higher success rate, and more efficiently.","PeriodicalId":257595,"journal":{"name":"2015 12th Conference on Computer and Robot Vision","volume":"15 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":"129551605","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
Automated Localization of Brain Tumors in MRI Using Potential-K-Means Clustering Algorithm 利用Potential-K-Means聚类算法在MRI中自动定位脑肿瘤
2015 12th Conference on Computer and Robot Vision Pub Date : 2015-06-03 DOI: 10.1109/CRV.2015.51
I. Cabria, I. Gondra
{"title":"Automated Localization of Brain Tumors in MRI Using Potential-K-Means Clustering Algorithm","authors":"I. Cabria, I. Gondra","doi":"10.1109/CRV.2015.51","DOIUrl":"https://doi.org/10.1109/CRV.2015.51","url":null,"abstract":"The manual localization and precise segmentation of brain tumours from magnetic resonance images (MRI) is time-consuming and error-prone. In T2 and FLAIR MRI, tumours appear as bright areas of higher signal intensity than their surroundings. In this paper we view the intensity of a pixel as equal to its \"workload\" and employ an unsupervised learning algorithm called potential-K-means that generates a balanced distribution of the pixels into clusters of approximately equal total intensity. The algorithm is based on an analogy with the gravitational force exerted by masses. This balancing requirement introduces a search bias that tends to generate either small clusters of higher intensity pixels, which overlap with the tumour area, or large clusters of lower intensity pixels. We evaluate the proposed algorithm on the publicly available brain tumour image segmentation (BRATS) MRI benchmark by comparing the centre of the cluster that overlaps with the tumour, with the centre of the tumour in the corresponding ground truth segmentation. We compare the proposed algorithm with the well-known K-means and with the Force clustering algorithm by Calamari et al. (2009), which follows a different Physics analogy, but it is also based on a balancing criteria. Experimental results show that K-means is not suitable for tumour localization and that potential-K-means and Kalantari's approach are comparable. However, the performance of Kalantari's approach is highly dependent on a parameter whose value needs to be set a priori, but without an informed way of doing so, which makes the present proposed method more practical.","PeriodicalId":257595,"journal":{"name":"2015 12th Conference on Computer and Robot Vision","volume":"70 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":"116278907","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: 12
Out-of-Core Surface Reconstruction from Large Point Sets for Infrastructure Inspection 基于大点集的核外表面重建
2015 12th Conference on Computer and Robot Vision Pub Date : 2015-06-03 DOI: 10.1109/CRV.2015.48
Chen Xu, Simon Frechet, D. Laurendeau, F. Mirallès
{"title":"Out-of-Core Surface Reconstruction from Large Point Sets for Infrastructure Inspection","authors":"Chen Xu, Simon Frechet, D. Laurendeau, F. Mirallès","doi":"10.1109/CRV.2015.48","DOIUrl":"https://doi.org/10.1109/CRV.2015.48","url":null,"abstract":"This paper presents a simple, effective, yet fast out-of-core method for surface reconstruction based on the vector field surface representation. The algorithm is designed to handle massive amount of real-world point clouds representing large infrastructures (e.g. underwater hydroelectric structure) acquired by LiDAR, sonar or laser scanning system using out-of-core techniques. Our method allows performing seamless surface reconstruction from unorganized, unrented, non-uniform and highly noisy data that include outliers. The applicability of the method has been evaluated in the context of hydroelectric infrastructure inspection, and its performance has been tested using synthetically produced data and field data captured on different Hydro-Quebec's sites by laser line scanning, LiDAR and sonar measurement systems.","PeriodicalId":257595,"journal":{"name":"2015 12th Conference on Computer and Robot Vision","volume":"217 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":"122601015","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
Dense Depth Map Reconstruction from Sparse Measurements Using a Multilayer Conditional Random Field Model 基于多层条件随机场模型的稀疏测量数据密集深度图重建
2015 12th Conference on Computer and Robot Vision Pub Date : 2015-06-03 DOI: 10.1109/CRV.2015.20
Francis Li, E. Li, M. Shafiee, A. Wong, J. Zelek
{"title":"Dense Depth Map Reconstruction from Sparse Measurements Using a Multilayer Conditional Random Field Model","authors":"Francis Li, E. Li, M. Shafiee, A. Wong, J. Zelek","doi":"10.1109/CRV.2015.20","DOIUrl":"https://doi.org/10.1109/CRV.2015.20","url":null,"abstract":"Acquiring accurate dense depth maps is crucial for accurate 3D reconstruction. Current high quality depth sensors capable of generating dense depth maps are expensive and bulky, while compact low-cost sensors can only reliably generate sparse depth measurements. We propose a novel multilayer conditional random field (MCRF) approach to reconstruct a dense depth map of a target scene given the sparse depth measurements and corresponding photographic measurements obtained from stereo photogrammetric systems. Estimating the dense depth map is formulated as a maximum posterior (MAP) inference problem where a smoothness prior is assumed. Our MCRF model uses the sparse depth measurement as an additional observation layer and describes relations between nodes with multivariate feature functions based on the depth and photographic measurements. The method is first qualitatively analyzed when performed on data collected with a compact stereo camera, then quantitative performance is measured using the Middlebury stereo vision data for ground truth. Experimental results show our method performs well for reconstructing simple scenes and has lower mean squared error compared to other dense depth map reconstruction methods.","PeriodicalId":257595,"journal":{"name":"2015 12th Conference on Computer and Robot Vision","volume":"6 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":"116616244","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
CPS: 3D Compositional Part Segmentation through Grasping CPS:三维构件抓取分割
2015 12th Conference on Computer and Robot Vision Pub Date : 2015-06-03 DOI: 10.1109/CRV.2015.24
Safoura Rezapour Lakani, M. Popa, A. Rodríguez-Sánchez, J. Piater
{"title":"CPS: 3D Compositional Part Segmentation through Grasping","authors":"Safoura Rezapour Lakani, M. Popa, A. Rodríguez-Sánchez, J. Piater","doi":"10.1109/CRV.2015.24","DOIUrl":"https://doi.org/10.1109/CRV.2015.24","url":null,"abstract":"Most objects are composed of parts which have a semantic meaning. Ahandle can have many different shapes and can be present in quite different objects, but there is only one semantic meaning to a handle, which is \"a part that is designed especially to be grasped by the hand\". We introduce here a novel 3D algorithm named CPS for the decomposition of objects into their semantically meaningful parts. These meaningful parts are learned from experiments where robot grasps different objects. Objects are represented in compositional graph hierarchy where their parts are represented as the relationship between subparts, which are in turn represented based on the relationships between small adjacent regions. Unlike other compositional approaches, our method relies on learning semantically meaningful parts which are learned from grasping experience. This compositional part representation provides generalization for part segmentation. We evaluated our method in this respect, by training ion one dataset and evaluating it on another. We achieved on average78% part overlap accuracy for segmentation of novel part instances.","PeriodicalId":257595,"journal":{"name":"2015 12th Conference on Computer and Robot Vision","volume":"56 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":"127251993","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
Preprocessing Realistic Video for Contactless Heart Rate Monitoring Using Video Magnification 使用视频放大技术预处理非接触式心率监测的逼真视频
2015 12th Conference on Computer and Robot Vision Pub Date : 2015-06-03 DOI: 10.1109/CRV.2015.41
Ahmed Alzahrani, A. Whitehead
{"title":"Preprocessing Realistic Video for Contactless Heart Rate Monitoring Using Video Magnification","authors":"Ahmed Alzahrani, A. Whitehead","doi":"10.1109/CRV.2015.41","DOIUrl":"https://doi.org/10.1109/CRV.2015.41","url":null,"abstract":"This research seeks to improve the outcomes of Eulerian Video Magnification in real life scenarios. We address the core requirement in Eulerian Magnification that the person in the video be completely still. The proposed system pre-processes the video in multiple stages using subject targeting and stabilization. The resulting video is better suited to Eulerian Magnification restrictions. Our method enables the use of magnification in a variety of applications where motion is present such as monitoring the heart rate of a person using a treadmill. Stabilization, which is the core element of our research, was achieved through two methods. First, we used face tracking to generate a stabilized video with limited motion. Second, feature detection, extraction, and matching with skin selection were used to produce a stabilized video that is ready to be processed for measuring heart rate. However, skin tone and illumination in the environment adversely affected the results. Since heart rate is monitored by counting the subtle changes in skin redness related to blood flow, managing the skin's redness helps to produce more accurate results.","PeriodicalId":257595,"journal":{"name":"2015 12th Conference on Computer and Robot Vision","volume":"124 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":"121395274","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
A Solution to Face-to-Face Contact in Tele-presence Systems 远程呈现系统中面对面接触的解决方案
2015 12th Conference on Computer and Robot Vision Pub Date : 2015-06-03 DOI: 10.1109/CRV.2015.37
Xiaozhou Zhou, P. Boulanger
{"title":"A Solution to Face-to-Face Contact in Tele-presence Systems","authors":"Xiaozhou Zhou, P. Boulanger","doi":"10.1109/CRV.2015.37","DOIUrl":"https://doi.org/10.1109/CRV.2015.37","url":null,"abstract":"In tele-presence systems, direct face-to-face contact, is essential for emotional communication as it carries non-verbal clues. In commercial products, face-to-face contact is approximated by using either a large semi-transparent mirror to project an image of the remote participant and capture the local participant image by using a video camera aiming at the centre of the screen or by using low profile cameras. These systems are very cumbersome and require complex hardware and software setups. In this paper, we propose a low cost solution to face-to-face contact correction problem in tele-presence systems using active stereo triangulation.","PeriodicalId":257595,"journal":{"name":"2015 12th Conference on Computer and Robot Vision","volume":"23 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":"125938595","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
Orbital SLAM 轨道大满贯
2015 12th Conference on Computer and Robot Vision Pub Date : 2015-06-03 DOI: 10.1109/CRV.2015.47
Corinne Vassallo, Wennie Tabib, K. Peterson
{"title":"Orbital SLAM","authors":"Corinne Vassallo, Wennie Tabib, K. Peterson","doi":"10.1109/CRV.2015.47","DOIUrl":"https://doi.org/10.1109/CRV.2015.47","url":null,"abstract":"This paper demonstrates infrastructure-free orbital Simultaneous Localization and Mapping (SLAM). Individual surface landmarks are tracked through images taken in orbit and the filter receives measurements of these landmarks in the form of bearing angles. The filter then updates the spacecraft's position and velocity as well as landmark locations, thus building a map of the orbited body. In contrast to other approaches that use an IMU, which doesn't work in orbit, to resolve scale, the contribution of this paper is to demonstrate that scale can be resolved using orbital dynamics. Radio localization can be replaced with onboard localization, enabling truly autonomous missions to both under-mapped and unmapped planetary bodies. Overall system convergence is shown by simulating landmark detection from an orbit of the Clementine Mission on a Moon model constructed using Lunar Reconnaissance Orbiter (LRO) digital elevation data in conjunction with the filter. The techniques developed in this work demonstrate that when combined with a gravity model, visual SLAM converges to a full scale solution.","PeriodicalId":257595,"journal":{"name":"2015 12th Conference on Computer and Robot Vision","volume":"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":"127724381","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
Eyes in the Back of Your Head: Robust Visual Teach & Repeat Using Multiple Stereo Cameras 后脑勺上的眼睛:强大的视觉教学& &;重复使用多个立体相机
2015 12th Conference on Computer and Robot Vision Pub Date : 2015-06-01 DOI: 10.1109/CRV.2015.16
M. Paton, F. Pomerleau, T. Barfoot
{"title":"Eyes in the Back of Your Head: Robust Visual Teach & Repeat Using Multiple Stereo Cameras","authors":"M. Paton, F. Pomerleau, T. Barfoot","doi":"10.1109/CRV.2015.16","DOIUrl":"https://doi.org/10.1109/CRV.2015.16","url":null,"abstract":"Autonomous path-following robots that use vision-based navigation are appealing for a wide variety of tedious and dangerous applications. However, a reliance on matching point-based visual features often renders vision-based navigation unreliable over extended periods of time in unstructured, outdoor environments. Specifically, scene change caused by lighting, weather, and seasonal variation lead to changes in visual features and result in a reduction of feature associations across time. This paper presents an autonomous, path-following system that uses multiple stereo cameras to increase the algorithm field of view and reliably navigate in these feature-limited scenarios. The addition of a second camera in the localization pipeline greatly increases the probability that a stable feature will be in the robot's field of view at any point in time, extending the amount of time the robot can reliably navigate. We experimentally validate our algorithm through a challenging winter field trial, where the robot autonomously traverses a 250m path six times with an autonomy rate of 100% despite significant changes in the appearance of the scene due to lighting and melting snow. We show that the addition of a second stereo camera to the system significantly increases the autonomy window when compared to current state-of-the-art path-following methods.","PeriodicalId":257595,"journal":{"name":"2015 12th Conference on Computer and Robot Vision","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124901094","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: 12
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