An Efficient Approach to Automatic Generation of Time-lapse Video Sequences

Javier Calero de Torres, Bryan Gardiner, Ilias Dahi, Sandra Moffett, Marco Herbst, Joan Condell

Research output: Contribution to conferencePaperpeer-review

121 Downloads (Pure)


Time-lapse video sequences have recently become a highly utilised asset for marketing and advertising, particularly within the field of construction and landscape development. However, the manual generation of these videos, at a quality that can be used for marketing purposes, can be quite time-consuming. In this paper, a novel application for generating time-lapse videos is proposed, which will automatically select the optimal frames for time-lapse video generation, enhance these frames by applying a number of image pre-processing and machine learning techniques such as FAST super-resolution to improve the frames quality, and finally, provide an intuitive user interface to allow users to customise the time-lapse video with company branding. The auto-generated time-lapse videos will use techniques such as Laplacian filtering and temporal smoothing filtering to determine inactivity within the video sequence, classify day or night and, by use of optical character recognition, have the ability to remove unwanted artefacts such as the captured video date and time stamp. The obtained results from the proposed approach produce comparable video sequences to those produced manually, but with the advantage of being generated much faster and not requiring specialised video editing skills to complete.
Original languageEnglish
Number of pages205
Publication statusPublished (in print/issue) - 28 Aug 2019
EventIrish Machine Vision Image Processing Conference - Technological University Dublin
Duration: 28 Aug 201930 Aug 2019


ConferenceIrish Machine Vision Image Processing Conference
Abbreviated titleIMVIP


  • Time-lapse video generation
  • timestamp removal
  • FAST super-resolution processing


Dive into the research topics of 'An Efficient Approach to Automatic Generation of Time-lapse Video Sequences'. Together they form a unique fingerprint.

Cite this