Intra-frame Object Tracking by Deblatting

05/09/2019
by   Jan Kotera, et al.
0

Objects moving at high speed along complex trajectories often appear in videos, especially videos of sports. Such objects elapse non-negligible distance during exposure time of a single frame and therefore their position in the frame is not well defined. They appear as semi-transparent streaks due to the motion blur and cannot be reliably tracked by standard trackers. We propose a novel approach called Tracking by Deblatting based on the observation that motion blur is directly related to the intra-frame trajectory of an object. Blur is estimated by solving two intertwined inverse problems, blind deblurring and image matting, which we call deblatting. The trajectory is then estimated by fitting a piecewise quadratic curve, which models physically justifiable trajectories. As a result, tracked objects are precisely localized with higher temporal resolution than by conventional trackers. The proposed TbD tracker was evaluated on a newly created dataset of videos with ground truth obtained by a high-speed camera using a novel Trajectory-IoU metric that generalizes the traditional Intersection over Union and measures the accuracy of the intra-frame trajectory. The proposed method outperforms baseline both in recall and trajectory accuracy.

READ FULL TEXT
research
08/21/2019

Effects of Blur and Deblurring to Visual Object Tracking

Intuitively, motion blur may hurt the performance of visual object track...
research
09/15/2019

Non-Causal Tracking by Deblatting

Tracking by Deblatting stands for solving an inverse problem of deblurri...
research
11/25/2019

Sub-frame Appearance and 6D Pose Estimation of Fast Moving Objects

We propose a novel method that tracks fast moving objects, mainly non-un...
research
11/23/2016

The World of Fast Moving Objects

The notion of a Fast Moving Object (FMO), i.e. an object that moves over...
research
07/08/2019

TrackNet: A Deep Learning Network for Tracking High-speed and Tiny Objects in Sports Applications

Ball trajectory data are one of the most fundamental and useful informat...
research
11/29/2021

Motion-from-Blur: 3D Shape and Motion Estimation of Motion-blurred Objects in Videos

We propose a method for jointly estimating the 3D motion, 3D shape, and ...
research
08/11/2021

Two is a crowd: tracking relations in videos

Tracking multiple objects individually differs from tracking groups of r...

Please sign up or login with your details

Forgot password? Click here to reset