Multi-object extraction in complex scenes using independent component analysis and principal component analysis : a novel hybrid approach

Tu, Zhengzheng and Zheng, Aihua and Yang, Erfu and Luo, Bin and Hussain, Amir (2015) Multi-object extraction in complex scenes using independent component analysis and principal component analysis : a novel hybrid approach. In: Sixth China-Scotland SIPRA Workshop on Recent Advances in Signal and Image Processing, 2015-05-31 - 2015-06-01, University of Stirling.

Full text not available in this repository.Request a copy from the Strathclyde author

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.