Towards video based collective motion analysis through shape tracking and matching. Issue 17 (1st August 2020)

• Record Type: Journal Article
• Authors: Pandey, B.; Thakur, S.; Joshi, H.; Pradhanga, A.; Akiyama, Y.; Peethambaran, J.
• Is Part Of: Electronics letters. Volume 56:Issue 17(2020)
• Page Start: 881
• Page End: 884
• Publication Date: 2020-08-01
• Subjects: object detection -- image motion analysis -- image sequences -- learning (artificial intelligence) -- feature extraction -- video signal processing; shape tracking -- aggregate motions -- visually pleasing shapes -- moving collectives -- polygonal boundaries -- geometric shapes -- extracting video frames -- user defined shape -- deep‐learning based object detection -- alpha shapes -- modified shape context -- video based collective motion analysis -- shape matching; Electronics -- Periodicals; 621.381
• DOI: 10.1049/el.2020.1362
• Languages: English
• ISSNs: 0013-5194

Abstract

Abstract : The term 'collective' is used to refer to a group of animals such as a flock of birds or a herd of elephants. Aggregate motions of such collectives often give rise to visually pleasing shapes and patterns (e.g. V‐shape formation of geese while they migrate from one place to another). While shapes of moving collectives are of great interest in many scientific studies, scant attention has been given to algorithmically extract and render these shapes via polygonal boundaries or graphs. In this Letter, the authors present a multi‐stage, proof of concept framework for tracking geometric shapes and extracting video frames containing a user defined shape of moving collectives, by employing a deep‐learning based object detection, well‐known alpha shapes and a modified shape context. They demonstrate the usefulness of the proposed framework on a couple of test videos and discuss its potential applications in a wider area.