PROJECT TITLE :
Continuous camera placement using multiple objective optimisation process
Most existing camera placement algorithms concentrate on coverage and/or visibility analysis, which ensures that the object of interest is visible in the camera's field of view (FOV). However, visibility is insufficient for continuous and automatic tracking. In such applications, a sufficient overlap between FOVs ought to be secured so that camera handoff will be executed successfully and automatically before the thing of interest becomes untraceable or unidentifiable. Moreover, most of the present algorithms use discrete answer area, that suffers from limited answer accuracy and high computational complexity thanks to the high dimension of sampled solution area. During this paper, we tend to propose to perform the optimisation of the camera parameters in a very continuous answer house. Furthermore, to include the optimisation of coverage and sufficient overlapped FOVs, a weighted total approach is utilised to translate a multiple objective optimisation problem into a single objective optimisation method in our previous work. Considerably improved handoff success rates are illustrated via experiments using typical workplace floor plans in comparison with Erdem and Sclaroff's method. Improved accuracy, enhanced robustness, completeness of the answer set, and reduced computational complexity are accomplished compared with our previous algorithms.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here