.png){kind=icon}
.png){kind=icon}
Return
Visual Sensor Placement Based on Risk Maps
.png){kind=icon}
PRE
AI
DOI：10.1109/TIM.2019.2927650.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The research work on camera placement has focused on maximizing the coverage or minimizing the installation cost of video surveillance systems. Typical placement schemes mount surveillance cameras with no emphasis on the coverage demand divergences, which impacts the system's cost and efficiency. This paper addresses the camera placement problem based on an inverse modeling taxonomy. Thus, rather than performing the optimization on uniformly distributed grids, this paper introduces an underlying mechanism to elaborate the security sensitive zones prior to the coverage optimization. The outcome of the prioritization process is termed as Risk Maps. Obtained empirical results show the reliability of the placement using inverse modeling. Finally, the validation of the proposed placement scheme is carried out in a constraint environment.
Keywords:
Cameras
modeling
optimization
simulation
video cameras
video surveillance
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
5.9
Papers:
1.9W
Citations:
5.8W
Organization
View more organizations