Integrating Tracking with Fine Object Segmentation
We present a novel method for on-line, joint object tracking and segmentation in a monocular video captured by a possibly moving camera. Our goal is to integrate tracking and fine segmentation of a single, previously unseen, potentially non-rigid object of unconstrained appearance, given its segmentation in the first frame of an image sequence as the only prior information. To this end, we tightly couple an existing kernel-based object tracking method with Random Walker-based image segmentation. Bayesian inference mediates between tracking and segmentation, enabling effective data fusion of pixel-wise spatial and color visual cues. The fine segmentation of an object at a certain frame provides tracking with reliable initialization for the next frame, closing the loop between the two building blocks of the proposed framework. The effectiveness of the proposed methodology is evaluated experimentally by comparing it to a large collection of state of the art tracking and video-based object segmentation methods on the basis of a data set consisting of several challenging image sequences for which ground truth data is available.
Publication:
K. Papoutsakis, A.A. Argyros, Integrating tracking with fine object segmentation, Image and Vision Computing, Volume 31, Issue 10, pp. 771-785, Oct. 2013.
Links:
http://www.sciencedirect.com/science/article/pii/S0262885613001121
http://www.ics.forth.gr/~argyros/research/trackingsegmentation.html
Видео Integrating Tracking with Fine Object Segmentation канала Antonis Argyros
Publication:
K. Papoutsakis, A.A. Argyros, Integrating tracking with fine object segmentation, Image and Vision Computing, Volume 31, Issue 10, pp. 771-785, Oct. 2013.
Links:
http://www.sciencedirect.com/science/article/pii/S0262885613001121
http://www.ics.forth.gr/~argyros/research/trackingsegmentation.html
Видео Integrating Tracking with Fine Object Segmentation канала Antonis Argyros
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
![Online segmentation and classification of actions (BMVC 2014)](https://i.ytimg.com/vi/LxIiTFDavpg/default.jpg)
![Tracking the articulated motion of the human body with two RGBD cameras](https://i.ytimg.com/vi/n5irgHVuFwc/default.jpg)
![Scalable 3D Tracking of Multiple Interacting Objects - CVPR 2014](https://i.ytimg.com/vi/SCOtBdhDMKg/default.jpg)
![Localizing Periodicity in Time Series and Videos (BMVC 2016)](https://i.ytimg.com/vi/2oa0Y9znH6g/default.jpg)
![Tracking deformable surfaces that undergo topological changes using an RGB-D camera (3DV 2016)](https://i.ytimg.com/vi/Hxa7nKUvsso/default.jpg)
![Shape from Interaction](https://i.ytimg.com/vi/uZQQkGTk6-k/default.jpg)
![Joint 3D Tracking of a Deformable Object in Interaction with a Hand (ECCV 2018)](https://i.ytimg.com/vi/JSOIy3D_5I0/default.jpg)
![Efficient 3D Hand Tracking in Articulation Subspaces for the Manipulation of Virtual Objects](https://i.ytimg.com/vi/9sU2HAvnCKQ/default.jpg)
![Vision-based SLAM and moving objects tracking for a smart walker platform (ACVR 2014)](https://i.ytimg.com/vi/RnKFCypUk9U/default.jpg)
![Monitoring and Interpreting Human Motion to Support Clinical Applications of a Smart Walker](https://i.ytimg.com/vi/YkyJsIW7FVM/default.jpg)
![Controlling a computer mouse through visual recognition and interpretation of hand gestures](https://i.ytimg.com/vi/bbIqPR6iLvI/default.jpg)
![3D Tracking of Human Hands in Interaction with Unknown Objects (BMVC 2015)](https://i.ytimg.com/vi/9r43PtJ0Fwg/default.jpg)
![Hierarchical Particle Filtering for 3D Hand Tracking](https://i.ytimg.com/vi/DR8YUOAM3QM/default.jpg)
![A Hybrid Method for 3D Pose Estimation of Personalized Human Body Models (WACV 2018)](https://i.ytimg.com/vi/SCgpIIaRIuI/default.jpg)
![Binding vision to physics based simulation: The case study of a bouncing ball](https://i.ytimg.com/vi/Lr5wq5It4io/default.jpg)
![From multiple views to textured 3D meshes: a GPU-powered approach](https://i.ytimg.com/vi/n0KC7wL_D_Q/default.jpg)
![Boosting the Performance of Model-based 3D Tracking by Employing Low Level Motion Cues (BMVC 2015)](https://i.ytimg.com/vi/nPru6PpWrK4/default.jpg)
![3D Hand Tracking by Employing Probabilistic Principal Component Analysis to Model Action Priors](https://i.ytimg.com/vi/L09qeohuJ9k/default.jpg)
![Model-based 3D Hand Tracking with on-line Hand Shape Adaptation (BMVC 2015)](https://i.ytimg.com/vi/4dgwoKkDSn8/default.jpg)
![ReActNet: Temporal Localization of Repetitive Activities in Real-World Videos](https://i.ytimg.com/vi/pPqg1lMkuaQ/default.jpg)
![Using a Single RGB Frame for Real Time 3D Hand Pose Estimation in the Wild (IEEE WACV 2018)](https://i.ytimg.com/vi/VoWAmtga9fg/default.jpg)