Multi-object extraction in complex scenes using independent component analysis and principal component analysis

a novel hybrid approach

Zhengzheng Tu, Aihua Zheng, Erfu Yang, Bin Luo, Amir Hussain

Research output: Contribution to conferencePoster

Abstract

It is always a big challenge to extract moving objects in complex video scenes because bad weather or dynamic backgrounds can seriously influence the results of motion detection. In this research, a new hybrid approach combining independent component analysis (ICA) with principal component analysis (PCA) is proposed for multiple moving objects extraction in complex scenes. First, a fast ICA algorithm is used to analyze the optical flows of video frames, so that the optical flows of background and foreground can be approximately separated. Next, the PCA is applied to the optical flows of foreground components as such the major optical flows corresponding to target multi-objects can be extracted accurately and the motions resulting from changing backgrounds are cleared away simultaneously. Preliminary experimental results demonstrate that the proposed novel hybrid ICA and PCA-based approach can extract multiple objects effectively in a complex scene.

Acknowledgements: This research is supported by The Royal Society of Edinburgh (RSE) and The National Natural Science Foundation of China (NNSFC) under the RSE-NNSFC joint project (2012-2015) [grant number 61211130309] with Anhui University, China, and the “Sino-UK Higher Education Research Partnership for PhD Studies” joint-project (2013-2015) funded by the British Council China and The China Scholarship Council (CSC). Amir Hussain and Erfu Yang are also funded, by the RSE-NNSFC joint project (2012-2015) [grant number 61211130210] with Beihang University, China.
Original languageEnglish
Pages22-22
Number of pages1
Publication statusPublished - 31 May 2015
EventSixth China-Scotland SIPRA Workshop on Recent Advances in Signal and Image Processing - University of Stirling, Stirling, United Kingdom
Duration: 31 May 20151 Jun 2015

Workshop

WorkshopSixth China-Scotland SIPRA Workshop on Recent Advances in Signal and Image Processing
CountryUnited Kingdom
CityStirling
Period31/05/151/06/15

Fingerprint

Optical flows
Independent component analysis
Natural sciences
Principal component analysis
Education

Keywords

  • motion cognition
  • optical flow
  • independent component analysis
  • principal component analysis
  • moving objects detection

Cite this

Tu, Z., Zheng, A., Yang, E., Luo, B., & Hussain, A. (2015). Multi-object extraction in complex scenes using independent component analysis and principal component analysis: a novel hybrid approach. 22-22. Poster session presented at Sixth China-Scotland SIPRA Workshop on Recent Advances in Signal and Image Processing, Stirling, United Kingdom.
Tu, Zhengzheng ; Zheng, Aihua ; Yang, Erfu ; Luo, Bin ; Hussain, Amir. / Multi-object extraction in complex scenes using independent component analysis and principal component analysis : a novel hybrid approach. Poster session presented at Sixth China-Scotland SIPRA Workshop on Recent Advances in Signal and Image Processing, Stirling, United Kingdom.1 p.
@conference{4dc78000a83b4548a37f713946be8f0d,
title = "Multi-object extraction in complex scenes using independent component analysis and principal component analysis: a novel hybrid approach",
abstract = "It is always a big challenge to extract moving objects in complex video scenes because bad weather or dynamic backgrounds can seriously influence the results of motion detection. In this research, a new hybrid approach combining independent component analysis (ICA) with principal component analysis (PCA) is proposed for multiple moving objects extraction in complex scenes. First, a fast ICA algorithm is used to analyze the optical flows of video frames, so that the optical flows of background and foreground can be approximately separated. Next, the PCA is applied to the optical flows of foreground components as such the major optical flows corresponding to target multi-objects can be extracted accurately and the motions resulting from changing backgrounds are cleared away simultaneously. Preliminary experimental results demonstrate that the proposed novel hybrid ICA and PCA-based approach can extract multiple objects effectively in a complex scene.Acknowledgements: This research is supported by The Royal Society of Edinburgh (RSE) and The National Natural Science Foundation of China (NNSFC) under the RSE-NNSFC joint project (2012-2015) [grant number 61211130309] with Anhui University, China, and the “Sino-UK Higher Education Research Partnership for PhD Studies” joint-project (2013-2015) funded by the British Council China and The China Scholarship Council (CSC). Amir Hussain and Erfu Yang are also funded, by the RSE-NNSFC joint project (2012-2015) [grant number 61211130210] with Beihang University, China.",
keywords = "motion cognition, optical flow, independent component analysis, principal component analysis, moving objects detection",
author = "Zhengzheng Tu and Aihua Zheng and Erfu Yang and Bin Luo and Amir Hussain",
note = "Poster; Sixth China-Scotland SIPRA Workshop on Recent Advances in Signal and Image Processing ; Conference date: 31-05-2015 Through 01-06-2015",
year = "2015",
month = "5",
day = "31",
language = "English",
pages = "22--22",

}

Tu, Z, Zheng, A, Yang, E, Luo, B & Hussain, A 2015, 'Multi-object extraction in complex scenes using independent component analysis and principal component analysis: a novel hybrid approach' Sixth China-Scotland SIPRA Workshop on Recent Advances in Signal and Image Processing, Stirling, United Kingdom, 31/05/15 - 1/06/15, pp. 22-22.

Multi-object extraction in complex scenes using independent component analysis and principal component analysis : a novel hybrid approach. / Tu, Zhengzheng; Zheng, Aihua; Yang, Erfu; Luo, Bin; Hussain, Amir.

2015. 22-22 Poster session presented at Sixth China-Scotland SIPRA Workshop on Recent Advances in Signal and Image Processing, Stirling, United Kingdom.

Research output: Contribution to conferencePoster

TY - CONF

T1 - Multi-object extraction in complex scenes using independent component analysis and principal component analysis

T2 - a novel hybrid approach

AU - Tu, Zhengzheng

AU - Zheng, Aihua

AU - Yang, Erfu

AU - Luo, Bin

AU - Hussain, Amir

N1 - Poster

PY - 2015/5/31

Y1 - 2015/5/31

N2 - It is always a big challenge to extract moving objects in complex video scenes because bad weather or dynamic backgrounds can seriously influence the results of motion detection. In this research, a new hybrid approach combining independent component analysis (ICA) with principal component analysis (PCA) is proposed for multiple moving objects extraction in complex scenes. First, a fast ICA algorithm is used to analyze the optical flows of video frames, so that the optical flows of background and foreground can be approximately separated. Next, the PCA is applied to the optical flows of foreground components as such the major optical flows corresponding to target multi-objects can be extracted accurately and the motions resulting from changing backgrounds are cleared away simultaneously. Preliminary experimental results demonstrate that the proposed novel hybrid ICA and PCA-based approach can extract multiple objects effectively in a complex scene.Acknowledgements: This research is supported by The Royal Society of Edinburgh (RSE) and The National Natural Science Foundation of China (NNSFC) under the RSE-NNSFC joint project (2012-2015) [grant number 61211130309] with Anhui University, China, and the “Sino-UK Higher Education Research Partnership for PhD Studies” joint-project (2013-2015) funded by the British Council China and The China Scholarship Council (CSC). Amir Hussain and Erfu Yang are also funded, by the RSE-NNSFC joint project (2012-2015) [grant number 61211130210] with Beihang University, China.

AB - It is always a big challenge to extract moving objects in complex video scenes because bad weather or dynamic backgrounds can seriously influence the results of motion detection. In this research, a new hybrid approach combining independent component analysis (ICA) with principal component analysis (PCA) is proposed for multiple moving objects extraction in complex scenes. First, a fast ICA algorithm is used to analyze the optical flows of video frames, so that the optical flows of background and foreground can be approximately separated. Next, the PCA is applied to the optical flows of foreground components as such the major optical flows corresponding to target multi-objects can be extracted accurately and the motions resulting from changing backgrounds are cleared away simultaneously. Preliminary experimental results demonstrate that the proposed novel hybrid ICA and PCA-based approach can extract multiple objects effectively in a complex scene.Acknowledgements: This research is supported by The Royal Society of Edinburgh (RSE) and The National Natural Science Foundation of China (NNSFC) under the RSE-NNSFC joint project (2012-2015) [grant number 61211130309] with Anhui University, China, and the “Sino-UK Higher Education Research Partnership for PhD Studies” joint-project (2013-2015) funded by the British Council China and The China Scholarship Council (CSC). Amir Hussain and Erfu Yang are also funded, by the RSE-NNSFC joint project (2012-2015) [grant number 61211130210] with Beihang University, China.

KW - motion cognition

KW - optical flow

KW - independent component analysis

KW - principal component analysis

KW - moving objects detection

UR - http://www.cs.stir.ac.uk/events/sipra-workshop2015/SIPRA-Workshop-Stirling-2015.pdf

M3 - Poster

SP - 22

EP - 22

ER -

Tu Z, Zheng A, Yang E, Luo B, Hussain A. Multi-object extraction in complex scenes using independent component analysis and principal component analysis: a novel hybrid approach. 2015. Poster session presented at Sixth China-Scotland SIPRA Workshop on Recent Advances in Signal and Image Processing, Stirling, United Kingdom.