Detecting semantic concepts from video using temporal gradients and audio classification

Mika Rautiainen, Tapio Seppänen, Jani Penttilä, Johannes Peltola

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

7 Citations (Scopus)

Abstract

In this paper we describe new methods to detect semantic concepts from digital video based on audible and visual content. Temporal Gradient Correlogram captures temporal correlations of gradient edge directions from sampled shot frames. Power-related physical features are extracted from short audio samples in video shots. Video shots containing people, cityscape, landscape, speech or instrumental sound are detected with trained self-organized maps and kNN classification results of audio samples. Test runs and evaluations in TREC 2002 Video Track show consistent performance for Temporal Gradient Correlogram and state-of-the-art precision in audio-based instrumental sound detection.
Original languageEnglish
Title of host publicationImage and Video Retrieval
Subtitle of host publicationCIVR 2003
PublisherSpringer
Pages260-270
ISBN (Electronic)978-3-540-45113-6
ISBN (Print)978-3-540-40634-1
DOIs
Publication statusPublished - 2003
MoE publication typeA4 Article in a conference publication
EventImage and Video Retrieval, CIVR 2003 - Urbana-Champaign, United States
Duration: 24 Jul 200325 Jul 2003

Publication series

NameLecture Notes in computer Science LNCS
Volume2728

Conference

ConferenceImage and Video Retrieval, CIVR 2003
Abbreviated titleCIVR 2003
CountryUnited States
CityUrbana-Champaign
Period24/07/0325/07/03

Fingerprint

Semantics
Acoustic waves

Cite this

Rautiainen, M., Seppänen, T., Penttilä, J., & Peltola, J. (2003). Detecting semantic concepts from video using temporal gradients and audio classification. In Image and Video Retrieval: CIVR 2003 (pp. 260-270). Springer. Lecture Notes in Computer Science, Vol.. 2728 https://doi.org/10.1007/3-540-45113-7_26
Rautiainen, Mika ; Seppänen, Tapio ; Penttilä, Jani ; Peltola, Johannes. / Detecting semantic concepts from video using temporal gradients and audio classification. Image and Video Retrieval: CIVR 2003. Springer, 2003. pp. 260-270 (Lecture Notes in Computer Science, Vol. 2728).
@inproceedings{9535aa681def4b4984ff4e20c9b0ab2a,
title = "Detecting semantic concepts from video using temporal gradients and audio classification",
abstract = "In this paper we describe new methods to detect semantic concepts from digital video based on audible and visual content. Temporal Gradient Correlogram captures temporal correlations of gradient edge directions from sampled shot frames. Power-related physical features are extracted from short audio samples in video shots. Video shots containing people, cityscape, landscape, speech or instrumental sound are detected with trained self-organized maps and kNN classification results of audio samples. Test runs and evaluations in TREC 2002 Video Track show consistent performance for Temporal Gradient Correlogram and state-of-the-art precision in audio-based instrumental sound detection.",
author = "Mika Rautiainen and Tapio Sepp{\"a}nen and Jani Penttil{\"a} and Johannes Peltola",
year = "2003",
doi = "10.1007/3-540-45113-7_26",
language = "English",
isbn = "978-3-540-40634-1",
series = "Lecture Notes in computer Science LNCS",
publisher = "Springer",
pages = "260--270",
booktitle = "Image and Video Retrieval",
address = "Germany",

}

Rautiainen, M, Seppänen, T, Penttilä, J & Peltola, J 2003, Detecting semantic concepts from video using temporal gradients and audio classification. in Image and Video Retrieval: CIVR 2003. Springer, Lecture Notes in Computer Science, vol. 2728, pp. 260-270, Image and Video Retrieval, CIVR 2003 , Urbana-Champaign, United States, 24/07/03. https://doi.org/10.1007/3-540-45113-7_26

Detecting semantic concepts from video using temporal gradients and audio classification. / Rautiainen, Mika; Seppänen, Tapio; Penttilä, Jani; Peltola, Johannes.

Image and Video Retrieval: CIVR 2003. Springer, 2003. p. 260-270 (Lecture Notes in Computer Science, Vol. 2728).

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - Detecting semantic concepts from video using temporal gradients and audio classification

AU - Rautiainen, Mika

AU - Seppänen, Tapio

AU - Penttilä, Jani

AU - Peltola, Johannes

PY - 2003

Y1 - 2003

N2 - In this paper we describe new methods to detect semantic concepts from digital video based on audible and visual content. Temporal Gradient Correlogram captures temporal correlations of gradient edge directions from sampled shot frames. Power-related physical features are extracted from short audio samples in video shots. Video shots containing people, cityscape, landscape, speech or instrumental sound are detected with trained self-organized maps and kNN classification results of audio samples. Test runs and evaluations in TREC 2002 Video Track show consistent performance for Temporal Gradient Correlogram and state-of-the-art precision in audio-based instrumental sound detection.

AB - In this paper we describe new methods to detect semantic concepts from digital video based on audible and visual content. Temporal Gradient Correlogram captures temporal correlations of gradient edge directions from sampled shot frames. Power-related physical features are extracted from short audio samples in video shots. Video shots containing people, cityscape, landscape, speech or instrumental sound are detected with trained self-organized maps and kNN classification results of audio samples. Test runs and evaluations in TREC 2002 Video Track show consistent performance for Temporal Gradient Correlogram and state-of-the-art precision in audio-based instrumental sound detection.

U2 - 10.1007/3-540-45113-7_26

DO - 10.1007/3-540-45113-7_26

M3 - Conference article in proceedings

SN - 978-3-540-40634-1

T3 - Lecture Notes in computer Science LNCS

SP - 260

EP - 270

BT - Image and Video Retrieval

PB - Springer

ER -

Rautiainen M, Seppänen T, Penttilä J, Peltola J. Detecting semantic concepts from video using temporal gradients and audio classification. In Image and Video Retrieval: CIVR 2003. Springer. 2003. p. 260-270. (Lecture Notes in Computer Science, Vol. 2728). https://doi.org/10.1007/3-540-45113-7_26