Causal Video Object Segmentation From Persistence of Occlusions

Abstract

Occlusion relations inform the partition of the image domain into"objects"but are difficult to determine from a single image or short-baseline video. We show how long-term occlusion relations can be robustly inferred from video, and used within a convex optimization framework to segment the image domain into regions. We highlight the challenges in determining these occluder/occluded relations and ensuring regions remain temporally consistent, propose strategies to overcome them, and introduce an efficient numerical scheme to perform the partition directly on the pixel grid, without the need for superpixelization or other preprocessing steps.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
May 01, 2015
Accession Number
ADA622259

Entities

People

  • Brian A Taylor
  • Stefano Soatto
  • Vasiliy Karasev

Organizations

  • University of California, Los Angeles

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Algorithms
  • Birds
  • Boundaries
  • Computer Vision
  • Consistency
  • Detection
  • Extrapolation
  • Failure Mode And Effect Analysis
  • Flow
  • Flow Fields
  • Indicators
  • Machine Learning
  • Optimization
  • Precision
  • Test And Evaluation
  • Test Sets
  • Vascular System Injuries

Fields of Study

  • Computer science

Readers

  • Computer Vision.
  • Mathematical Modeling and Probability Theory.

Technology Areas

  • AI & ML
  • AI & ML - Information Retrieval
  • AI & ML - Machine Learning Algorithms