An object based graph representation for video comparison

Xin Feng, Yuanyi Xue, Yao Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper develops a novel object based graph model for semantic video comparison. The model describes a video with detected objects as nodes, and relationship between the objects as edges in a graph. We investigated several spatial and temporal features as the graph node attributes, and different ways to describe the spatial-temporal relationship between objects as the edge attributes. To tackle the problem of erratic camera motion on the detected object, a global motion estimation and correction approach is proposed to reveal the true object trajectory. We further propose to evaluate the similarity between two videos by establishing the object correspondence between two object graphs through graph matching. The model is verified on a challenging user generated video dataset. Experiments show that our method outperforms other video representation frameworks in matching videos with the same semantic content. The proposed object graph provides a compact and robust semantic descriptor for a video, which can be used for applications such as video retrieval, clustering and summarization. The graph representation is also flexible to incorporate other features as node and edge attributes.

Original languageEnglish (US)
Title of host publication2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings
PublisherIEEE Computer Society
Pages2548-2552
Number of pages5
Volume2017-September
ISBN (Electronic)9781509021758
DOIs
StatePublished - Feb 20 2018
Event24th IEEE International Conference on Image Processing, ICIP 2017 - Beijing, China
Duration: Sep 17 2017Sep 20 2017

Other

Other24th IEEE International Conference on Image Processing, ICIP 2017
CountryChina
CityBeijing
Period9/17/179/20/17

Fingerprint

Semantics
Motion estimation
Cameras
Trajectories
Experiments

Keywords

  • Graph matching
  • Object graph
  • Video comparison
  • Video representation

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Feng, X., Xue, Y., & Wang, Y. (2018). An object based graph representation for video comparison. In 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings (Vol. 2017-September, pp. 2548-2552). IEEE Computer Society. https://doi.org/10.1109/ICIP.2017.8296742

An object based graph representation for video comparison. / Feng, Xin; Xue, Yuanyi; Wang, Yao.

2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. Vol. 2017-September IEEE Computer Society, 2018. p. 2548-2552.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Feng, X, Xue, Y & Wang, Y 2018, An object based graph representation for video comparison. in 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. vol. 2017-September, IEEE Computer Society, pp. 2548-2552, 24th IEEE International Conference on Image Processing, ICIP 2017, Beijing, China, 9/17/17. https://doi.org/10.1109/ICIP.2017.8296742
Feng X, Xue Y, Wang Y. An object based graph representation for video comparison. In 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. Vol. 2017-September. IEEE Computer Society. 2018. p. 2548-2552 https://doi.org/10.1109/ICIP.2017.8296742
Feng, Xin ; Xue, Yuanyi ; Wang, Yao. / An object based graph representation for video comparison. 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. Vol. 2017-September IEEE Computer Society, 2018. pp. 2548-2552
@inproceedings{a7809b10aed042f58b4f132e1a0668d6,
title = "An object based graph representation for video comparison",
abstract = "This paper develops a novel object based graph model for semantic video comparison. The model describes a video with detected objects as nodes, and relationship between the objects as edges in a graph. We investigated several spatial and temporal features as the graph node attributes, and different ways to describe the spatial-temporal relationship between objects as the edge attributes. To tackle the problem of erratic camera motion on the detected object, a global motion estimation and correction approach is proposed to reveal the true object trajectory. We further propose to evaluate the similarity between two videos by establishing the object correspondence between two object graphs through graph matching. The model is verified on a challenging user generated video dataset. Experiments show that our method outperforms other video representation frameworks in matching videos with the same semantic content. The proposed object graph provides a compact and robust semantic descriptor for a video, which can be used for applications such as video retrieval, clustering and summarization. The graph representation is also flexible to incorporate other features as node and edge attributes.",
keywords = "Graph matching, Object graph, Video comparison, Video representation",
author = "Xin Feng and Yuanyi Xue and Yao Wang",
year = "2018",
month = "2",
day = "20",
doi = "10.1109/ICIP.2017.8296742",
language = "English (US)",
volume = "2017-September",
pages = "2548--2552",
booktitle = "2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - An object based graph representation for video comparison

AU - Feng, Xin

AU - Xue, Yuanyi

AU - Wang, Yao

PY - 2018/2/20

Y1 - 2018/2/20

N2 - This paper develops a novel object based graph model for semantic video comparison. The model describes a video with detected objects as nodes, and relationship between the objects as edges in a graph. We investigated several spatial and temporal features as the graph node attributes, and different ways to describe the spatial-temporal relationship between objects as the edge attributes. To tackle the problem of erratic camera motion on the detected object, a global motion estimation and correction approach is proposed to reveal the true object trajectory. We further propose to evaluate the similarity between two videos by establishing the object correspondence between two object graphs through graph matching. The model is verified on a challenging user generated video dataset. Experiments show that our method outperforms other video representation frameworks in matching videos with the same semantic content. The proposed object graph provides a compact and robust semantic descriptor for a video, which can be used for applications such as video retrieval, clustering and summarization. The graph representation is also flexible to incorporate other features as node and edge attributes.

AB - This paper develops a novel object based graph model for semantic video comparison. The model describes a video with detected objects as nodes, and relationship between the objects as edges in a graph. We investigated several spatial and temporal features as the graph node attributes, and different ways to describe the spatial-temporal relationship between objects as the edge attributes. To tackle the problem of erratic camera motion on the detected object, a global motion estimation and correction approach is proposed to reveal the true object trajectory. We further propose to evaluate the similarity between two videos by establishing the object correspondence between two object graphs through graph matching. The model is verified on a challenging user generated video dataset. Experiments show that our method outperforms other video representation frameworks in matching videos with the same semantic content. The proposed object graph provides a compact and robust semantic descriptor for a video, which can be used for applications such as video retrieval, clustering and summarization. The graph representation is also flexible to incorporate other features as node and edge attributes.

KW - Graph matching

KW - Object graph

KW - Video comparison

KW - Video representation

UR - http://www.scopus.com/inward/record.url?scp=85045320657&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045320657&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2017.8296742

DO - 10.1109/ICIP.2017.8296742

M3 - Conference contribution

AN - SCOPUS:85045320657

VL - 2017-September

SP - 2548

EP - 2552

BT - 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings

PB - IEEE Computer Society

ER -