2018 15th Conference on Computer and Robot Vision (CRV)最新文献_第4页

Spatiotemporal KSVD Dictionary Learning for Online Multi-target Tracking 面向在线多目标跟踪的时空KSVD字典学习

2018 15th Conference on Computer and Robot Vision (CRV) Pub Date : 2018-05-01 DOI: 10.1109/CRV.2018.00030

H. Manh, G. Alaghband

{"title":"Spatiotemporal KSVD Dictionary Learning for Online Multi-target Tracking","authors":"H. Manh, G. Alaghband","doi":"10.1109/CRV.2018.00030","DOIUrl":"https://doi.org/10.1109/CRV.2018.00030","url":null,"abstract":"In this paper, we present a new spatiotemporal discriminative KSVD dictionary algorithm (STKSVD) for learning target appearance in online multi-target tracking system. Different from other classification/recognition tasks (e.g. face, image recognition), learning target's appearance in online multi-target tracking is impacted by factors such as: posture/articulation changes, partial occlusion by background scene or other targets, background changes (human detection bounding box covers both human parts and part of the scene), etc. However, we observe that these variations occur gradually relative to spatial and temporal dynamics. We characterize the spatial and temporal information between target's samples through a new STKSVD appearance learning algorithm to better discriminate targets. Our STKSVD method is able to learn discriminative sparse code, linear classifier parameters, and minimize reconstruction error in single optimization system. Our appearance learning algorithm and tracking framework employs two different methods of calculating appearance similarity score in each stage of a two-stage association: a linear classifier in the first stage, and minimum residual errors in the second stage. The results tested using 2DMOT2015 dataset and its public Aggregated Channel Features (ACF) human detection for all comparisons show that our method outperforms the existing related learning methods.","PeriodicalId":281779,"journal":{"name":"2018 15th Conference on Computer and Robot Vision (CRV)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127132804","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

Fast Unsynchronized Unstructured Light 快速非同步非结构光

2018 15th Conference on Computer and Robot Vision (CRV) Pub Date : 2018-05-01 DOI: 10.1109/CRV.2018.00046

Chaima El Asmi, S. Roy

引用次数: 5

Semantic Scene Models for Visual Localization under Large Viewpoint Changes 大视点变化下视觉定位的语义场景模型

2018 15th Conference on Computer and Robot Vision (CRV) Pub Date : 2018-05-01 DOI: 10.1109/CRV.2018.00033

J. Li, Zhaoqi Xu, D. Meger, G. Dudek

引用次数: 10

Manifold Geometry with Fast Automatic Derivatives and Coordinate Frame Semantics Checking in C++ 具有快速自动导数和坐标框架语义检查的流形几何

2018 15th Conference on Computer and Robot Vision (CRV) Pub Date : 2018-05-01 DOI: 10.1109/CRV.2018.00027

Leonid Koppel, Steven L. Waslander

引用次数: 5

Disparity Filtering with 3D Convolutional Neural Networks 用三维卷积神经网络进行视差滤波

2018 15th Conference on Computer and Robot Vision (CRV) Pub Date : 2018-05-01 DOI: 10.1109/CRV.2018.00042

W. Mao, Minglun Gong

引用次数: 7

Data-Driven Multispectral Image Registration 数据驱动的多光谱图像配准

2018 15th Conference on Computer and Robot Vision (CRV) Pub Date : 2018-05-01 DOI: 10.1109/CRV.2018.00040

Rahat Yasir, M. Eramian, I. Stavness, S. Shirtliffe, H. Duddu

{"title":"Data-Driven Multispectral Image Registration","authors":"Rahat Yasir, M. Eramian, I. Stavness, S. Shirtliffe, H. Duddu","doi":"10.1109/CRV.2018.00040","DOIUrl":"https://doi.org/10.1109/CRV.2018.00040","url":null,"abstract":"Multispectral imaging is widely used in remote sensing applications from UAVs and ground-based platforms. Multispectral cameras often use a physically different camera for each wavelength causing misalignment in the images for different imaging bands. This misalignment must be corrected prior to concurrent multi-band image analysis. The traditional approach for multispectral image registration process is to select a target channel and register all other image channels to the target. There is no objective evidence-based method to select a target. The possibility of registration to some intermediate channel to the target is not usually considered, but could be beneficial if there is no target channel for which direct registration performs well for every other channel. In this paper, we propose an automatic data-driven multispectral image registration framework that determines a target channel, and possible intermediate registration steps based on the assumptions that 1) some reasonable minimum number of control points correspondences between two channels is needed to ensure a low-error registration; and 2) a greater number of such correspondences generally results in lower registration error. Our prototype is tested on three multispectral datasets captured with UAV-mounted multispectral cameras. The resulting registration schemes had more control point correspondences on average than the traditional register-all-to-one-target-channel approach in all of our experiments. For most channels in our three datasets, our registration schemes produced lower back-projection error than the direct-to-target-channel based registration approach.","PeriodicalId":281779,"journal":{"name":"2018 15th Conference on Computer and Robot Vision (CRV)","volume":"2010 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121347556","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: 7

Surface-Based GICP 基于地表GICP

2018 15th Conference on Computer and Robot Vision (CRV) Pub Date : 2018-05-01 DOI: 10.1109/CRV.2018.00044

M. Vlaminck, H. Luong, W. Philips

引用次数: 6

An Evaluation of Deep CNN Baselines for Scene-Independent Person Re-identification 场景无关人物再识别的深度CNN基线评价

2018 15th Conference on Computer and Robot Vision (CRV) Pub Date : 2018-05-01 DOI: 10.1109/CRV.2018.00049

P. Marchwica, Michael Jamieson, P. Siva

引用次数: 6

Walking on Thin Air: Environment-Free Physics-Based Markerless Motion Capture 在稀薄的空气中行走:基于无环境物理的无标记动作捕捉

2018 15th Conference on Computer and Robot Vision (CRV) Pub Date : 2018-05-01 DOI: 10.1109/CRV.2018.00031

M. Livne, L. Sigal, Marcus A. Brubaker, David J. Fleet

{"title":"Walking on Thin Air: Environment-Free Physics-Based Markerless Motion Capture","authors":"M. Livne, L. Sigal, Marcus A. Brubaker, David J. Fleet","doi":"10.1109/CRV.2018.00031","DOIUrl":"https://doi.org/10.1109/CRV.2018.00031","url":null,"abstract":"We propose a generative approach to physics-based motion capture. Unlike prior attempts to incorporate physics into tracking that assume the subject and scene geometry are calibrated and known a priori, our approach is automatic and online. This distinction is important since calibration of the environment is often difficult, especially for motions with props, uneven surfaces, or outdoor scenes. The use of physics in this context provides a natural framework to reason about contact and the plausibility of recovered motions. We propose a fast data-driven parametric body model, based on linear-blend skinning, which decouples deformations due to pose, anthropometrics and body shape. Pose (and shape) parameters are estimated using robust ICP optimization with physics-based dynamic priors that incorporate contact. Contact is estimated from torque trajectories and predictions of which contact points were active. To our knowledge, this is the first approach to take physics into account without explicit a priori knowledge of the environment or body dimensions. We demonstrate effective tracking from a noisy single depth camera, improving on state-of-the-art results quantitatively and producing better qualitative results, reducing visual artifacts like foot-skate and jitter.","PeriodicalId":281779,"journal":{"name":"2018 15th Conference on Computer and Robot Vision (CRV)","volume":"353 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122763811","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

A Pyramid CNN for Dense-Leaves Segmentation 密集叶分割的金字塔CNN

2018 15th Conference on Computer and Robot Vision (CRV) Pub Date : 2018-04-05 DOI: 10.1109/CRV.2018.00041

Daniel Morris

引用次数: 27