A vision-based postproduction tool for footage logging, analysis, and annotation

J W Mateer; J A Robinson

doi:10.1016/j.gmod.2005.01.007

A vision-based postproduction tool for footage logging, analysis, and annotation

Research output: Contribution to journal › Article › peer-review

Abstract

We report a new method for logging and annotating video footage directed towards the needs of professional postproduction and archivist end users. SALSA-Semi-Automated Logging with Semantic Annotation-is a hybrid system that uses automated footage analysis for Cut detection and camera movement classification, and a stenographic-like keyboard input system for the logging of higher-level semantic information. Output is presented both in standard printed log form, with the addition of mosaic visual representations of shots, and in a fully searchable database. Experimental comparisons of SALSA with conventional hand analysis show a significant increase in the logger's speed with no reduction in accuracy or semantic detail. (c) 2005 Elsevier Inc. All rights reserved.

Original language	English
Pages (from-to)	565-583
Number of pages	19
Journal	Graphical Models
Volume	67
Issue number	6
DOIs	https://doi.org/10.1016/j.gmod.2005.01.007
Publication status	Published - Nov 2005

Keywords

automated media analysis
content indexing and retrieval
shot boundary detection
semantic annotation
video analysis
editing systems
SHOT-CHANGE DETECTION
CAMERA MOTION
VIDEO
MINIMIZATION

Access to Document

10.1016/j.gmod.2005.01.007

http://dx.doi.org/10.1016/j.gmod.2005.01.007

Cite this

@article{87873748522f4384bf2e423d3d72c6cb,

title = "A vision-based postproduction tool for footage logging, analysis, and annotation",

abstract = "We report a new method for logging and annotating video footage directed towards the needs of professional postproduction and archivist end users. SALSA-Semi-Automated Logging with Semantic Annotation-is a hybrid system that uses automated footage analysis for Cut detection and camera movement classification, and a stenographic-like keyboard input system for the logging of higher-level semantic information. Output is presented both in standard printed log form, with the addition of mosaic visual representations of shots, and in a fully searchable database. Experimental comparisons of SALSA with conventional hand analysis show a significant increase in the logger's speed with no reduction in accuracy or semantic detail. (c) 2005 Elsevier Inc. All rights reserved.",

keywords = "automated media analysis, content indexing and retrieval, shot boundary detection, semantic annotation, video analysis, editing systems, SHOT-CHANGE DETECTION, CAMERA MOTION, VIDEO, MINIMIZATION",

author = "Mateer, {J W} and Robinson, {J A}",

year = "2005",

month = nov,

doi = "10.1016/j.gmod.2005.01.007",

language = "English",

volume = "67",

pages = "565--583",

journal = "Graphical Models",

issn = "1524-0703",

publisher = "Elsevier",

number = "6",

}

TY - JOUR

T1 - A vision-based postproduction tool for footage logging, analysis, and annotation

AU - Mateer, J W

AU - Robinson, J A

PY - 2005/11

Y1 - 2005/11

N2 - We report a new method for logging and annotating video footage directed towards the needs of professional postproduction and archivist end users. SALSA-Semi-Automated Logging with Semantic Annotation-is a hybrid system that uses automated footage analysis for Cut detection and camera movement classification, and a stenographic-like keyboard input system for the logging of higher-level semantic information. Output is presented both in standard printed log form, with the addition of mosaic visual representations of shots, and in a fully searchable database. Experimental comparisons of SALSA with conventional hand analysis show a significant increase in the logger's speed with no reduction in accuracy or semantic detail. (c) 2005 Elsevier Inc. All rights reserved.

AB - We report a new method for logging and annotating video footage directed towards the needs of professional postproduction and archivist end users. SALSA-Semi-Automated Logging with Semantic Annotation-is a hybrid system that uses automated footage analysis for Cut detection and camera movement classification, and a stenographic-like keyboard input system for the logging of higher-level semantic information. Output is presented both in standard printed log form, with the addition of mosaic visual representations of shots, and in a fully searchable database. Experimental comparisons of SALSA with conventional hand analysis show a significant increase in the logger's speed with no reduction in accuracy or semantic detail. (c) 2005 Elsevier Inc. All rights reserved.

KW - automated media analysis

KW - content indexing and retrieval

KW - shot boundary detection

KW - semantic annotation

KW - video analysis

KW - editing systems

KW - SHOT-CHANGE DETECTION

KW - CAMERA MOTION

KW - VIDEO

KW - MINIMIZATION

U2 - 10.1016/j.gmod.2005.01.007

DO - 10.1016/j.gmod.2005.01.007

M3 - Article

SN - 1524-0703

VL - 67

SP - 565

EP - 583

JO - Graphical Models

JF - Graphical Models

IS - 6

ER -