Method and system for queue length analysis
View Patent ↗A system and method for analyzing queues in frames of video enables operators to preferably draw three regions of interest overlaid upon the video as short, medium, and long queue regions that form a notional queue area within the video. The regions are drawn with knowledge of, or in anticipation of, foreground objects such as individuals and vehicles waiting for service in a queue. Examples include retail point of sale locations or for automated teller machine (ATM) transactions. In conjunction with a video analytics system that analyses the movement of the foreground objects relative to the queue regions, the system determines the number of objects occupying each queue region, length of the queue, and other queue-related statistics. The system can then create reports and send messages that include the queue analysis results for directing operators to change their staffing resources as part of a real-time queue servicing and optimization response.
1. A method for determining object occupancy, the method comprising:
at least one video camera generating video data of a monitored queue area;
a video analytics system receiving the video data and defining queue regions within the area with respect to the video data;
the video analytics system determining that each object occupies the area by determining that each object intersects with the area by a minimum intersection amount for a predetermined period of time based on the video data;
the video analytics system determining intersection of the objects upon the queue regions based on the video data;
the video analytics system marking each object as occupying one or more of the queue regions, if the area of intersection between each object and a queue region is at least equal to a minimum region intersection threshold based on the video data; and
determining a length of a queue by calculating a union, for each of the queue regions, of the marked areas of intersection and comparing the union of the marked areas of intersection of the objects belonging to each of the queue regions, to a minimum occupancy area for each of the queue regions and successively determining if each of the queue regions is occupied.
2. The method of claim 1 , wherein the queue regions are queue regions forming the queue area.
3. The method of claim 1 , further comprising enabling drawing of the queue regions over video data.
4. The method of claim 1 , wherein the queue regions are rectangular.
5. The method of claim 1 , wherein the queue regions are trapezoidal.
6. The method of claim 1 , wherein queue length is determined by:
calculating a union, for each of the queue regions, of the marked areas of intersection; and
comparing the union of the marked areas of intersection of the objects belonging to each of the queue regions, to a minimum occupancy area for each of the queue regions.
7. The method of claim 1 , further comprising determining a number of objects that are within an area by counting the objects that belong to the queue regions forming the queue area.
8. A video analysis system for monitoring queues, comprising:
at least one video camera generating video data of a monitored area; and
a video analytics system that determines whether each object occupies queue regions within the area by determining that each object intersects with the queue regions by a minimum intersection amount for a predetermined period of time, determining intersection of the objects upon the queue regions and marking each object as occupying one or more of the queue regions, if the area of intersection between each object and a queue region is at least equal to a minimum region intersection threshold, calculating a union, for each of the queue regions, of the marked areas of intersection, comparing the union of the marked areas of intersection of the objects belonging to each of the queue regions, to a minimum occupancy area for each of the queue regions, and determining a length of a queue by successively determining if each of the queue regions is occupied.
9. The system of claim 8 , wherein the one or more queue regions are one or more queue regions forming the queue area.
10. The system of claim 8 , wherein the video analytics system enables drawing of the queue regions over video data.
11. The system of claim 8 , wherein the queue regions are rectangular.
12. The system of claim 8 , wherein the queue regions are trapezoidal.
13. The system of claim 8 , wherein the video analytics system determines a number of objects that are within an area by counting the objects that belong to the one or more queue regions forming the queue area.