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

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.