Traffic list generation for passenger conveyance

1. A method of passenger tracking for an elevator system for tracking a passenger transition from a first lobby to an elevator and from the elevator to a second lobby, the method comprising:

tracking an individual passenger in a first lobby, wherein the tracking is performed using 3D depth sensor data from a sensor in the elevator that comprises identifying an approaching, leaving, passing by or combination thereof of the individual passenger with regard to a position of the elevator doors, wherein the identifying of the approaching, leaving, passing by, or combination thereof of the individual passenger with regard to the position of the elevator doors comprises monitoring a convergence of a matrix mathematical relationship estimation of a calibration information to determine when sufficient accuracy has been achieved;

tracking the individual passenger while within an elevator from the first lobby using 3D depth sensor data from the sensor in the elevator;

tracking the individual passenger from the elevator into a second lobby using 3D depth sensor data from the sensor in the elevator to generate a traffic list, wherein a unique passenger identity is maintained during the passenger transition from the first lobby to the elevator, within the elevator, and from within the elevator to the second lobby, the identity and associated passenger tracking data is maintained in a way that preserves privacy using Bayesian Inference for a probabilistic prediction of the individual passenger's intended destination, wherein tracking the individual passenger includes edge weighting a graph-based optimization by order and time difference, the passenger tracked by two trackers that comprise a head-shoulder tracker and a body tracker such that the unique passenger identity is maintained by detecting a head of each individual passenger via a circle-Hough transform and tracking the head via particle filtering;

combining a multiple of traffic lists for each of a multiple of individual passenger over time, with time as a parameter using Bayesian Inference, to facilitate statistical distribution determination of elevator usage for an entire building; and

pre-assigning elevators to particular runs, purposefully skipping floors, with time as a parameter, in response to the statistical distribution determination of usage.

2. The method as recited in claim 1 , further comprising adjusting the head detection result to enclose each individual passenger based on optical flow.

3. The method as recited in claim 1 , wherein at least one of tracking the individual passenger while within the elevator from the first lobby and tracking the individual passenger from the elevator into a second lobby comprises a tracking hand over approach.

4. The method as recited in claim 1 , wherein at least one of tracking the individual passenger while within the elevator from the first lobby and tracking the individual passenger from the elevator into a second lobby to generate a traffic list comprises elevator door open/close identification.

5. The method as recited in claim 1 , further comprising combining the multiple of traffic lists for each of a multiple of individual passengers over time with time as a parameter to facilitate statistical distribution determination of usage for daily load estimation.

6. The method as recited in claim 1 , further comprising combining a multiple of traffic lists for each of a multiple of individual passenger over time with time as a parameter to facilitate statistical distribution determination of usage for system diagnostics.

7. The method as recited in claim 1 , further comprising determining an elevator system diagnostics based on abnormal traffic list information in response to the statistical distribution determination of usage.

8. The method as recited in claim 1 , wherein the head-shoulder tracker is based on online boosting and the body tracker is based on particle filtering.

9. A passenger tracking system for tracking a passenger

transition from at least one of a first lobby to an elevator from the elevator to a second lobby, comprising:

one or more depth-sensing sensors for capturing sensor data wherein the sensor data is 3D depth data, wherein the depth-sensing sensor comprises a structured light measurement, phase shift measurement, time of flight measurement, stereo triangulation device, sheet of light triangulation device, light field cameras, coded aperture cameras, computational imaging techniques, simultaneous localization and mapping (SLAM), imaging radar, imaging sonar, scanning LIDAR, flash LIDAR, Passive Infrared (PIR) sensor, and small Focal Plane Array (FPA), or a combination comprising at least one of the foregoing that comprises identifying an approaching, leaving, passing by, or combination thereof of the individual passenger with regard to a position of the elevator doors, wherein the identifying of the approaching, leaving, passing by, or combination thereof of the individual passenger with regard to the position of the elevator doors comprises monitoring a convergence of a matrix mathematical relationship estimation of a calibration information to determine when sufficient accuracy has been achieved, the identifying of the approaching, leaving, passing by, or combination thereof of the individual passenger with regard to the position of the elevator doors comprises a deduction of scene geometry that locates the elevator doors and the field of view;

and

a processing module in communication with the one or more sensors to receive the sensor data, where the processing module uses the sensor data to track an object and calculate passenger data associated with the tracked object to generate a passenger tracking list that tracks a passenger in the sensor data from a first lobby to a second lobby, wherein a unique passenger identity is maintained during a passenger transition from a first lobby to an elevator and from the elevator to a second lobby, the identity and associated passenger tracking data is maintained in a way that preserves privacy, wherein the processing module calculates an object parameter of the tracked object, wherein the object parameter comprises an object count, a location, a size, a direction, an acceleration, a velocity, an object classification, or a combination comprising at least one of the foregoing, the processing module calculates the passenger data if the tracked object is classified as a passenger, the passenger tracked by two trackers that comprise a head-shoulder tracker and a body tracker when in at least one of the first lobby, the elevator, and the second lobby, a signal from a data processing module is utilized as an input to a load sensor for re-calibration to maintain the accuracy thereof,

combines a multiple of traffic lists for each of a multiple of individual passenger over time, with time as a parameter using Bayesian Inference, to facilitate statistical distribution determination of elevator usage for an entire building; and

pre-assigns elevators to particular runs, purposefully skipping floors, with time as a parameter, in response to the statistical distribution determination of usage.