DART: dense articulated real-time tracking with consumer depth cameras

被引：0
作者：
Tanner Schmidt
Richard Newcombe
Dieter Fox
机构：
[1] University of Washington,
来源：
Autonomous Robots | 2015年 / 39卷
关键词：
Articulated model tracking; Signed distance function ; Real-time vision; RGB-D;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
This paper introduces DART, a general framework for tracking articulated objects composed of rigid bodies connected through a kinematic tree. DART covers a broad set of objects encountered in indoor environments, including furniture and tools, and human and robot bodies, hands and manipulators. To achieve efficient and robust tracking, DART extends the signed distance function representation to articulated objects and takes full advantage of highly parallel GPU algorithms for data association and pose optimization. We demonstrate the capabilities of DART on different types of objects that have each required dedicated tracking techniques in the past.
引用
收藏
页码：239 / 258
页数：19
相关论文
共 29 条
[1]  
Chang W(2008)Automatic registration for articulated shapes Computer Graphics Forum 27 1459-1468
[2]  
Zwicker M(2007)Kinematic sets for real-time robust articulated object tracking Image and Vision Computing 25 374-391
[3]  
Comport A(2014)Hierarchically constrained 3D hand pose estimation using regression forests from single frame depth data Pattern Recognition Letters 50 91-100
[4]  
Marchand E(2011)Learning GP-BayesFilters via Gaussian process latent variable models Autonomous Robots 30 3-23
[5]  
Chaumette F(2011)Manipulator and object tracking for in-hand 3d object modeling The International Journal of Robotics Research 30 1311-1327
[6]  
Kiraç F(2008)Global correspondence optimization for non-rigid registration of depth scans Computer Graphics Forum 27 1421-1430
[7]  
Kara YE(2013)Realtime facial animation with on-the-fly correctives ACM Transactions on Graphics 32 42-564
[8]  
Akarun L(2013)Non-parametric hand pose estimation with object context Image and Vision Computing 31 555-undefined
[9]  
Ko J(2014)Real-time continuous pose recovery of human hands using convolutional networks ACM Transactions on Graphics (TOG) 33 169-undefined
[10]  
Fox D(undefined)undefined undefined undefined undefined-undefined
123