Polygonal Point Set Tracking

05/30/2021
by   Gunhee Nam, et al.
0

In this paper, we propose a novel learning-based polygonal point set tracking method. Compared to existing video object segmentation (VOS) methods that propagate pixel-wise object mask information, we propagate a polygonal point set over frames. Specifically, the set is defined as a subset of points in the target contour, and our goal is to track corresponding points on the target contour. Those outputs enable us to apply various visual effects such as motion tracking, part deformation, and texture mapping. To this end, we propose a new method to track the corresponding points between frames by the global-local alignment with delicately designed losses and regularization terms. We also introduce a novel learning strategy using synthetic and VOS datasets that makes it possible to tackle the problem without developing the point correspondence dataset. Since the existing datasets are not suitable to validate our method, we build a new polygonal point set tracking dataset and demonstrate the superior performance of our method over the baselines and existing contour-based VOS methods. In addition, we present visual-effects applications of our method on part distortion and text mapping.

READ FULL TEXT

page 1

page 4

page 8

page 10

page 11

page 12

page 13

research
11/20/2017

Pixel-wise object tracking

In this paper, we propose a novel pixel-wise visual object tracking fram...
research
03/15/2023

Unsupervised Contour Tracking of Live Cells by Mechanical and Cycle Consistency Losses

Analyzing the dynamic changes of cellular morphology is important for un...
research
09/01/2015

Tumor Motion Tracking in Liver Ultrasound Images Using Mean Shift and Active Contour

In this paper we present a new method for motion tracking of tumors in l...
research
06/08/2017

Automatic tracking of vessel-like structures from a single starting point

The identification of vascular networks is an important topic in the med...
research
07/13/2022

Left Ventricle Contouring of Apical Three-Chamber Views on 2D Echocardiography

We propose a new method to automatically contour the left ventricle on 2...
research
06/13/2023

Marking anything: application of point cloud in extracting video target features

Extracting retrievable features from video is of great significance for ...
research
09/09/2016

Track Facial Points in Unconstrained Videos

Tracking Facial Points in unconstrained videos is challenging due to the...

Please sign up or login with your details

Forgot password? Click here to reset