eprintid: 3481
rev_number: 5
eprint_status: archive
userid: 69
dir: disk0/00/00/34/81
datestamp: 2016-05-05 13:57:04
lastmod: 2016-05-05 13:57:04
status_changed: 2016-05-05 13:57:04
type: conference_item
metadata_visibility: show
creators_name: Minervini, Massimo
creators_name: Tsaftaris, Sotirios A.
creators_id: massimo.minervini@imtlucca.it
creators_id: sotirios.tsaftaris@imtlucca.it
title: Classification-aware distortion metric for HEVC intra coding
ispublished: pub
subjects: QA75
divisions: CSA
full_text_status: none
pres_type: paper
keywords: Bit rate;Distortion;Encoding;Image coding;Optimization;Standards
abstract: Increasingly many vision applications necessitate the transmission of acquired images and video to a remote location for automated processing. When the image data are consumed by analysis algorithms and possibly never seen by a human, tailoring compression to the application is beneficial from a bit rate perspective. We inject prior knowledge of the application in the encoder to make rate-distortion decisions based on an estimate of the accuracy that will be achieved when analyzing reconstructed image data. Focusing on classification (e.g., used for image segmentation), we propose a new application-aware distortion metric based on a geometric interpretation of classification error. We devise an implementation for the High Efficiency Video Coding standard, and derive optimal model parameters for the A-domain rate control algorithm by curve fitting procedures. We evaluate our approach on time-lapse sequences from plant phenotyping experiments and cell fluorescence microscopy encoded in intra-only mode, observing a reduction in segmentation error across bit rates.
date: 2015-12
date_type: published
publisher: IEEE
event_title: 2015 Visual Communications and Image Processing (VCIP)
event_location: Singapore, Singapore
event_dates: December 13-16, 2015
event_type: conference
id_number: 10.1109/VCIP.2015.7457877
refereed: TRUE
book_title: 2015 Visual Communications and Image Processing (VCIP)
official_url: http://dx.doi.org/10.1109/VCIP.2015.7457877
citation:   Minervini, Massimo and Tsaftaris, Sotirios A.  Classification-aware distortion metric for HEVC intra coding.  In: 2015 Visual Communications and Image Processing (VCIP), December 13-16, 2015, Singapore, Singapore         (2015)