Multimodal Fusion in Surveillance Applications

摘要: The recent outbreak of vandalism, accidents and criminal activities has increased general public’s awareness about safety security, demanding improved security measures. Smart surveillance video systems have become an ubiquitous platform which monitors private public environments, ensuring citizens well-being. Their universal deployment integrates diverse media acquisition systems, generating daily enormous amount multimodal data. Nowadays, numerous applications exploit multiple types data features benefitting from their uncorrelated contributions. Hence, the analysis, standardisation fusion complex content, specially visual, a fundamental problem to enhance by increasing accuracy, robustness reliability. During this chapter, exhaustive survey existing techniques in is provided. Addressing some revealed challenges state art, chapter focuses on development technique for automatic object classification. proposed exploits benefits Bayesian inference scheme systems’ performance. ends with evaluation Bayesian-based classifier against two state-of-the-art classifiers demonstrate applications.