Human-machine collaborative video coding through cuboidal partitioning

Ashek Ahmmed, Manoranjan Paul, Manzur Murshed, David Taubman

Research output: Book chapter/Published conference paperConference paperpeer-review

1 Citation (Scopus)

Abstract

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.

Original languageEnglish
Title of host publication2021 IEEE International onference on image processing (ICIP)
PublisherIEEE Computer Society
Pages2074-2078
Number of pages5
ISBN (Electronic)9781665441155
ISBN (Print)9781665431026
DOIs
Publication statusPublished - 23 Aug 2021
Event2021 IEEE International Conference on Image Processing: ICIP 2021 - Anchorage Convention Center, Anchorage, United States
Duration: 19 Sep 202122 Sep 2021
https://www.2021.ieeeicip.org/

Publication series

NameProceedings - International Conference on Image Processing, ICIP
Volume2021-September
ISSN (Print)1522-4880

Conference

Conference2021 IEEE International Conference on Image Processing
Abbreviated titleImaging Without Borders
Country/TerritoryUnited States
CityAnchorage
Period19/09/2122/09/21
OtherThe 28th IEEE International Conference on Image Processing (IEEE - ICIP) will be held in Anchorage-Alaska, Denaʼina Civic and Convention Center in the period September 19-22, 2021.

The IEEE ICIP is the world’s largest and most comprehensive technical conference focused on image and video processing and computer vision. This conference will showcase world-class plenary speakers, tutorials, exhibits, special sessions, industry sessions, and women in engineering that creates an excellent forum to foster innovation and entrepreneurship. There will be opportunities to network with the brightest minds in academia and industry from this field. In addition, several events targeting students and professionals will also be featured at IEEE ICIP 2021.
Internet address

Fingerprint

Dive into the research topics of 'Human-machine collaborative video coding through cuboidal partitioning'. Together they form a unique fingerprint.

Cite this