The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Kaedah untuk pembahagian pemandangan yang tepat menggunakan dua jenis graf terarah yang diperolehi oleh pemadanan objek dan ciri audio dicadangkan. Secara amnya, dalam bahan audiovisual, seperti program siaran dan filem, terdapat penampilan berulang tangkapan serupa yang merangkumi bingkai latar belakang, objek atau tempat yang sama, dan tangkapan sedemikian disertakan dalam satu adegan. Banyak kaedah pembahagian adegan berdasarkan idea ini telah dicadangkan; walau bagaimanapun, memandangkan mereka menggunakan maklumat warna sebagai ciri visual, mereka tidak dapat memberikan hasil pembahagian pemandangan yang tepat jika ciri warna berubah dalam tangkapan berbeza yang bingkainya termasuk objek yang sama disebabkan oleh operasi kamera seperti zum dan panning. Bagi menyelesaikan masalah ini, pembahagian adegan dengan kaedah yang dicadangkan direalisasikan dengan menggunakan dua pendekatan baru. Dalam pendekatan pertama, pemadanan objek dilakukan antara dua bingkai yang setiap satu disertakan dalam tangkapan yang berbeza. Dengan menggunakan hasil padanan ini, penampilan berulang tangkapan yang bingkainya mengandungi objek yang sama boleh berjaya ditemui dan diwakili sebagai graf terarah. Kaedah yang dicadangkan juga menjana satu lagi graf terarah yang mewakili penampilan berulang tangkapan dengan ciri audio yang serupa dalam pendekatan kedua. Dengan penggunaan gabungan kedua-dua graf terarah ini, kemerosotan ketepatan pembahagian pemandangan, yang terhasil daripada penggunaan hanya satu jenis graf, boleh dielakkan dalam kaedah yang dicadangkan dan dengan itu pembahagian pemandangan yang tepat dapat direalisasikan. Keputusan eksperimen yang dilakukan dengan menggunakan kaedah yang dicadangkan kepada program penyiaran sebenar ditunjukkan untuk mengesahkan keberkesanan kaedah yang dicadangkan.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Salinan
Makoto YAMAMOTO, Miki HASEYAMA, "An Accurate Scene Segmentation Method Based on Graph Analysis Using Object Matching and Audio Feature" in IEICE TRANSACTIONS on Fundamentals,
vol. E92-A, no. 8, pp. 1883-1891, August 2009, doi: 10.1587/transfun.E92.A.1883.
Abstract: A method for accurate scene segmentation using two kinds of directed graph obtained by object matching and audio features is proposed. Generally, in audiovisual materials, such as broadcast programs and movies, there are repeated appearances of similar shots that include frames of the same background, object or place, and such shots are included in a single scene. Many scene segmentation methods based on this idea have been proposed; however, since they use color information as visual features, they cannot provide accurate scene segmentation results if the color features change in different shots for which frames include the same object due to camera operations such as zooming and panning. In order to solve this problem, scene segmentation by the proposed method is realized by using two novel approaches. In the first approach, object matching is performed between two frames that are each included in different shots. By using these matching results, repeated appearances of shots for which frames include the same object can be successfully found and represented as a directed graph. The proposed method also generates another directed graph that represents the repeated appearances of shots with similar audio features in the second approach. By combined use of these two directed graphs, degradation of scene segmentation accuracy, which results from using only one kind of graph, can be avoided in the proposed method and thereby accurate scene segmentation can be realized. Experimental results performed by applying the proposed method to actual broadcast programs are shown to verify the effectiveness of the proposed method.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E92.A.1883/_p
Salinan
@ARTICLE{e92-a_8_1883,
author={Makoto YAMAMOTO, Miki HASEYAMA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={An Accurate Scene Segmentation Method Based on Graph Analysis Using Object Matching and Audio Feature},
year={2009},
volume={E92-A},
number={8},
pages={1883-1891},
abstract={A method for accurate scene segmentation using two kinds of directed graph obtained by object matching and audio features is proposed. Generally, in audiovisual materials, such as broadcast programs and movies, there are repeated appearances of similar shots that include frames of the same background, object or place, and such shots are included in a single scene. Many scene segmentation methods based on this idea have been proposed; however, since they use color information as visual features, they cannot provide accurate scene segmentation results if the color features change in different shots for which frames include the same object due to camera operations such as zooming and panning. In order to solve this problem, scene segmentation by the proposed method is realized by using two novel approaches. In the first approach, object matching is performed between two frames that are each included in different shots. By using these matching results, repeated appearances of shots for which frames include the same object can be successfully found and represented as a directed graph. The proposed method also generates another directed graph that represents the repeated appearances of shots with similar audio features in the second approach. By combined use of these two directed graphs, degradation of scene segmentation accuracy, which results from using only one kind of graph, can be avoided in the proposed method and thereby accurate scene segmentation can be realized. Experimental results performed by applying the proposed method to actual broadcast programs are shown to verify the effectiveness of the proposed method.},
keywords={},
doi={10.1587/transfun.E92.A.1883},
ISSN={1745-1337},
month={August},}
Salinan
TY - JOUR
TI - An Accurate Scene Segmentation Method Based on Graph Analysis Using Object Matching and Audio Feature
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1883
EP - 1891
AU - Makoto YAMAMOTO
AU - Miki HASEYAMA
PY - 2009
DO - 10.1587/transfun.E92.A.1883
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E92-A
IS - 8
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - August 2009
AB - A method for accurate scene segmentation using two kinds of directed graph obtained by object matching and audio features is proposed. Generally, in audiovisual materials, such as broadcast programs and movies, there are repeated appearances of similar shots that include frames of the same background, object or place, and such shots are included in a single scene. Many scene segmentation methods based on this idea have been proposed; however, since they use color information as visual features, they cannot provide accurate scene segmentation results if the color features change in different shots for which frames include the same object due to camera operations such as zooming and panning. In order to solve this problem, scene segmentation by the proposed method is realized by using two novel approaches. In the first approach, object matching is performed between two frames that are each included in different shots. By using these matching results, repeated appearances of shots for which frames include the same object can be successfully found and represented as a directed graph. The proposed method also generates another directed graph that represents the repeated appearances of shots with similar audio features in the second approach. By combined use of these two directed graphs, degradation of scene segmentation accuracy, which results from using only one kind of graph, can be avoided in the proposed method and thereby accurate scene segmentation can be realized. Experimental results performed by applying the proposed method to actual broadcast programs are shown to verify the effectiveness of the proposed method.
ER -