Deakin University
Browse

File(s) under permanent embargo

Human-Machine Collaborative Video Coding Through Cuboidal Partitioning

Version 2 2024-06-06, 03:38
Version 1 2022-11-29, 01:33
conference contribution
posted on 2024-06-06, 03:38 authored by Ashek Ahmmed, Manoranjan Paul, Manzur MurshedManzur Murshed, David Taubman
Video coding algorithms encode and decode an entire video frame while feature coding techniques only preserve and communicate the most critical information needed for a given application. This is because video coding targets human perception, while feature coding aims for machine vision tasks. Recently, attempts are being made to bridge the gap between these two domains. In this work, we propose a video coding framework by leveraging on to the commonality that exists between human vision and machine vision applications using cuboids. This is because cuboids, estimated rectangular regions over a video frame, are computationally efficient, has a compact representation and object centric. Such properties are already shown to add value to traditional video coding systems. Herein cuboidal feature descriptors are extracted from the current frame and then employed for accomplishing a machine vision task in the form of object detection. Experimental results show that a trained classifier yields superior average precision when equipped with cuboidal features oriented representation of the current test frame. Additionally, this representation costs 7% less in bit rate if the captured frames are need be communicated to a receiver.

History

Volume

2021-September

Pagination

2074-2078

Location

Anchorage, AK, USA

Start date

2021-09-19

End date

2021-09-22

ISSN

1522-4880

ISBN-13

9781665441155

Language

eng

Publication classification

E1.1 Full written paper - refereed

Title of proceedings

ICIP 2021 : Image Processing : Proceedings of theInstitute of Electrical and Electronics Engineers 2021 conference

Event

Institute of Electrical and Electronics Engineers. Conference (2021 : Anchorage, AK, USA)

Publisher

Institute of Electrical and Electronics Engineers

Place of publication

Piscataway, N.J.

Series

IEEE International Conference on Image Processing ICIP