Surveillance of a 2D plane area with 3D deployed cameras.
Bottom Line:
The discrete camera deployment problem is NP-hard and many heuristic methods have been proposed to solve it, most of which make very simple assumptions.We can simultaneously optimize the number and the configuration of the cameras through the introduction of a regulation item in the cost function.The simulation results showed the effectiveness of the proposed PI-BPSO algorithm.
View Article:
PubMed Central - PubMed
Affiliation: Department of Automation, Tsinghua University, Beijing 100084, China. iamdafu@gmail.com.
ABSTRACT
As the use of camera networks has expanded, camera placement to satisfy some quality assurance parameters (such as a good coverage ratio, an acceptable resolution constraints, an acceptable cost as low as possible, etc.) has become an important problem. The discrete camera deployment problem is NP-hard and many heuristic methods have been proposed to solve it, most of which make very simple assumptions. In this paper, we propose a probability inspired binary Particle Swarm Optimization (PI-BPSO) algorithm to solve a homogeneous camera network placement problem. We model the problem under some more realistic assumptions: (1) deploy the cameras in the 3D space while the surveillance area is restricted to a 2D ground plane; (2) deploy the minimal number of cameras to get a maximum visual coverage under more constraints, such as field of view (FOV) of the cameras and the minimum resolution constraints. We can simultaneously optimize the number and the configuration of the cameras through the introduction of a regulation item in the cost function. The simulation results showed the effectiveness of the proposed PI-BPSO algorithm. No MeSH data available. Related in: MedlinePlus |
Related In:
Results -
Collection
License getmorefigures.php?uid=PMC3958228&req=5
Mentions: We present some results obtained by the algorithms (Figures 10, 11 and 12). In the figures, blue bold line represents the area that needs to be surveilled and the red dash lines represent the FOV of the cameras. In Figures 11 and 12, we choose the same surveillance area and choose different sample frequencies for the pose parameters. In Figure 11, the parameters is (fx = fy = fφ = fψ =4, fz = fθ = 2), the fitness of the surveillance is 0.9785, the number of the surveillance cameras is 24; while in Figure 12, the parameters is (fx = fy = fz = fφ = fψ = fθ = 4), the fitness of the surveillance grows to 0.9908 while the number of the surveillance cameras is decreased to 16. From the experiments, we know that we can get more accurate results when we use a bigger sample space. In Figure 11, the sample space is 4,096 which is too big for classical Binary Integer Linear programming optimizations. |
View Article: PubMed Central - PubMed
Affiliation: Department of Automation, Tsinghua University, Beijing 100084, China. iamdafu@gmail.com.
No MeSH data available.