Automatic vision sensor placement apparatus and method
AssigneeAjou University Industry Cooperation Foundation
InventorsYun Young Nam, We Duke CHO, Uin BURN
Life of this patent
Estimating the term…
Abstract
There are provided an automatic vision sensor placement apparatus and method which analyze static spatial information in various aspects, calculate priorities of spaces using an agent that models the movement pattern of a user, suggest a method of effectively covering a given space, provide a camera placement method to appropriately install cameras with various levels of performance in a specified space, and calculate the optimal number of cameras to be installed based on installation cost.
Claims10
An automatic vision sensor placement apparatus comprising:
- a space modeling unit modeling a specified space as a two-dimensional (2D) grid map;
- a priority space extraction unit expressing the space priority of each cell of the grid map in a numerical value based on an amount of movement of an agent in a first area of the grid map and a probability that the agent will move from the first area to a second area;
- a suitability extraction unit extracting the suitability of a vision sensor at each location on the grid map based on the sum of space priority values of cells within a field of view (FOV) of the vision sensor and the performance and cost of the vision sensor;
- and
- a placement location selection unit calculating the number of vision sensors to be placed based on a maximum vision sensor placement cost and minimum space coverage and selecting locations, at which the vision sensor is to be placed, in order of highest to lowest suitability of the vision sensor,
- wherein the FOV of the vision sensor is defined by a viewing distance d, available angle a, and position angle φ of the vision sensor at a specified coordinate point on the grid map, and the minimum space coverage is the proportion of a minimum area that can be monitored by the vision sensor in the specified space.
An automatic vision sensor placement method comprising:
- modeling a specified space as a 2D grid map;
- expressing the space priority of each cell of the grid map in a numerical value based on an amount of movement of an agent in a first area of the grid map and a probability that the agent will move from the first area to a second area;
- extracting the suitability of a vision sensor at each location on the grid map based on the sum of space priority values of cells within an FOV of the vision sensor and the performance and cost of the vision sensor;
- and
- calculating the number of vision sensors to be placed based on a maximum vision sensor placement cost and minimum space coverage and selecting locations, at which the vision sensor is to be placed, in order of highest to lowest suitability of the vision sensor,
- wherein the FOV of the vision sensor is defined by a viewing distance d, available angle a, and position angle φ of the vision sensor at a specified coordinate point, and the minimum space coverage is the proportion of a minimum area that can be monitored by the vision sensor in the specified space.
Dependencies are inferred from the claim text.