Exploiting Geometric Constraints on Dense Trajectories for Motion Saliency

09/29/2019
by   Muhammad Faisal, et al.
22

The existing approaches for salient motion segmentation are unable to explicitly learn geometric cues and often give false detections on prominent static objects. We exploit multiview geometric constraints to avoid such mistakes. To handle nonrigid background like sea, we also propose a robust fusion mechanism between motion and appearance-based features. We find dense trajectories, covering every pixel in the video, and propose trajectory-based epipolar distances to distinguish between background and foreground regions. Trajectory epipolar distances are data-independent and can be readily computed given a few features' correspondences in the images. We show that by combining epipolar distances with optical flow, a powerful motion network can be learned. Enabling the network to leverage both of these information, we propose a simple mechanism, we call input-dropout. We outperform the previous motion network on DAVIS-2016 dataset by 5.2 network with an appearance network using the proposed input-dropout, we also outperform the previous methods on DAVIS-2016, 2017 and Segtrackv2 dataset.

READ FULL TEXT

page 1

page 3

page 5

page 6

page 8

research
09/04/2022

Treating Motion as Option to Reduce Motion Dependency in Unsupervised Video Object Segmentation

Unsupervised video object segmentation (VOS) aims to detect the most sal...
research
04/08/2023

Co-attention Propagation Network for Zero-Shot Video Object Segmentation

Zero-shot video object segmentation (ZS-VOS) aims to segment foreground ...
research
04/06/2022

Implicit Motion-Compensated Network for Unsupervised Video Object Segmentation

Unsupervised video object segmentation (UVOS) aims at automatically sepa...
research
03/08/2023

TSANET: Temporal and Scale Alignment for Unsupervised Video Object Segmentation

Unsupervised Video Object Segmentation (UVOS) refers to the challenging ...
research
03/06/2019

Robust Video Background Identification by Dominant Rigid Motion Estimation

The ability to identify the static background in videos captured by a mo...
research
03/25/2022

Dense Continuous-Time Optical Flow from Events and Frames

We present a method for estimating dense continuous-time optical flow. T...

Please sign up or login with your details

Forgot password? Click here to reset