Logo Detection and Identification in System for Audio-Visual Broadcast Transcription

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F46747885%3A24220%2F21%3A00009295" target="_blank" >RIV/46747885:24220/21:00009295 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/9522636" target="_blank" >https://ieeexplore.ieee.org/document/9522636</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/TSP52935.2021.9522636" target="_blank" >10.1109/TSP52935.2021.9522636</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Logo Detection and Identification in System for Audio-Visual Broadcast Transcription

Popis výsledku v původním jazyce

We present logo detection and identification based on a single-stage deep convolutional detector, the Scaled YOLOv4. This method is used in our system for audio-visual broadcast transcription and indexing which can be employed mainly for transcription of TV programs, mostly sports and advertising blocks. All transcribed information from audio and video streams together with time boundaries is indexed in the ElasticSearch database which can then be used to search for interesting keywords, entities etc. In this paper we present mainly the development and evaluation of the method for detection and identification of logos from images. We evaluate the logo detector on several of the most popular logo detection benchmarks, namely FlickrLogos-32, Logos-32plus, TopLogo-10 and QMUL-OpenLogo. The detector significantly outperforms the most common approach based on two stage models such as Faster R-CNN in terms of both speed and accuracy, achieving relative improvement up to 46% while running up to 2x faster.

Název v anglickém jazyce

Logo Detection and Identification in System for Audio-Visual Broadcast Transcription

Popis výsledku anglicky

We present logo detection and identification based on a single-stage deep convolutional detector, the Scaled YOLOv4. This method is used in our system for audio-visual broadcast transcription and indexing which can be employed mainly for transcription of TV programs, mostly sports and advertising blocks. All transcribed information from audio and video streams together with time boundaries is indexed in the ElasticSearch database which can then be used to search for interesting keywords, entities etc. In this paper we present mainly the development and evaluation of the method for detection and identification of logos from images. We evaluate the logo detector on several of the most popular logo detection benchmarks, namely FlickrLogos-32, Logos-32plus, TopLogo-10 and QMUL-OpenLogo. The detector significantly outperforms the most common approach based on two stage models such as Faster R-CNN in terms of both speed and accuracy, achieving relative improvement up to 46% while running up to 2x faster.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/TH03010018" target="_blank" >TH03010018: DeepSpot - Multilingvální technologie pro detekci a včasné upozornění</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2021

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

44th International Conference on Telecommunications and Signal Processing

ISBN

978-166542933-7

ISSN

—

e-ISSN

—

Počet stran výsledku

4

Strana od-do

357-360

Název nakladatele

IEEE

Místo vydání

—

Místo konání akce

on-line, Brno

Datum konání akce

1. 1. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000701604600076