VeRLab
  • Laboratory
    • Laboratory’s Gallery
    • Infrastructure
    • Our Team
    • About Us
  • News
  • Research
    • Projects
      • Three-dimensional Mapping with Augmented Navigation Cost
      • Cooperative Area Coverage Using Hexagonal Segmentation
      • Fenrir: 3D Printed Robotic Arm
      • Determining the Association of Individuals and the Collective Social Space
      • Semantic Description of Objects in Images Based on Prototype Theory
      • Semantic Mapping for Visual Robot Navigation
      • Detecting Landmarks On Different Domains Faces
      • Underwater Imaging
      • Project system of identification and multiview tracking for equipment and objects in Construction and Manufacturing.
      • Advanced teleoperation of mining equipment: excavator
      • Three-Dimensional Reconstruction from Large Image Datasets
      • Scene Understanding
      • HeRo: An Open Platform for Robotics Research and Education
      • Semantic Hyperlapse for First-Person Videos
    • Publications
    • Events
  • Social Media
    • Linkedin
    • Instagram
    • Twitter
    • YouTube
  • Contact
  • Restrict Area

Things we have done

All Projects

Semantic Hyperlapse Video

  • » Next
  • Previous »

In this project, we deal with a central challenge that is to make egocentric videos watchable. These videos are generally long-running streams with unedited content, which make them boring and visually unpalatable. Just fast-foward it is not enough, because the natural motion of the recorder’s body in a fast-forward mode becomes nauseate. In this work we propose a novel methodology to compose the new fast-forward video by selecting frames based in semantic information extracted from images.

More

Contact
  • UFMG
  • +55 (31) 3409-5856
  • verlab (at) dcc (dot) ufmg (dot) br
Stay Connected
  • Github
  • Youtube
Visitors in last month

  • VeRLab - Computer Vision and Robotics Lab
  • Contact