Depth sensor based passenger detection

Patent metadata

Field	Value
Publication number	US-10055657-B2
Application number	US-201615089622-A
Country	US
Kind code	B2
Filing date	Apr 4, 2016
Priority date	Apr 3, 2015
Publication date	Aug 21, 2018
Grant date	Aug 21, 2018

Abstract

A passenger conveyance system includes a depth-sensing sensor within a passenger conveyance enclosure for capturing depth map data of objects within a field of view that includes a passenger conveyance door. A processing module in communication with the depth-sensing sensor to receive the depth map data, the processing module uses the depth map data to determine that the passenger conveyance enclosure is empty. a passenger conveyance controller receives the passenger data from the processing module to control operation of a passenger conveyance door in response to an empty car determination.

First claim

What is claimed is:

1. A passenger conveyance system, comprising:
a depth-sensing sensor within a passenger conveyance enclosure for capturing depth map data from within the passenger conveyance enclosure;
a processing module in electronic communication with the depth-sensing sensor to receive the depth map data, the processing module uses the depth map data to detect an object therein;
a data capture module in electronic communication with the depth-sensing sensor and the processing module, the data capture module operable to receive the depth map data from the depth-sensing sensor for communication to the processing module to classify the object, wherein the classification comprises identification of a human via application of a human shape model; and
a load sensor in electronic communication with the data capture module, the load sensor operable to trigger the data capture module to obtain the depth map data if the sensed load weight is less than a preset threshold.

2. The system as recited in claim 1 , wherein the depth map data is 3D depth map data.

3. The system as recited in claim 2 , wherein the depth-sensing sensor utilizes at least one of structured light, phase shift, time of flight, stereo triangulation, sheet of light triangulation, 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).

4. The system as recited in claim 3 , wherein the processing module calculates at least one of the following object parameters with respect to the object, including: location, size, direction, acceleration, velocity, and object classification.

5. A method of detecting an object, the method comprising:
detecting an object with a depth-sensing sensor within a passenger conveyance enclosure via depth based depth map data;
using the depth-based depth map data to classify the object, wherein the classification comprises identification of the object separate from an associated passenger; and
providing an alert in response to classification of an object remaining in the passenger conveyance enclosure and the associated passenger leaving the passenger conveyance enclosure.

6. The method as recited in claim 5 , wherein the classification includes a location of the object.

7. The method as recited in claim 6 , wherein the classification includes a size of the object.

8. The method as recited in claim 7 , wherein the classification includes identification of a human as the associated passenger.

9. The method as recited in claim 8 , wherein identification of the human includes application of a human shape model.

10. The method as recited in claim 9 , wherein the classification includes background subtraction.

11. The method as recited in claim 10 , wherein the classification includes frame differencing.

12. The method as recited in claim 11 , wherein the classification includes spurious data rejection.

13. The method as recited in claim 12 , wherein spurious data rejection includes:
computing a depth background to segment foreground objects;
removing isolated foreground regions and segment moving objects for further analysis via 3D morphological operations;
transform moving objects to 3D world coordinates to estimate at least one of actual dimensions, areas, and volumes; and
remove spurious moving objects from the scene via geometric filtering.

14. The method as recited in claim 13 , wherein the 3D morphological operations includes:
computing a 2D foreground object mask by depth background subtraction;
size filtering on the mask as a function of range;
connecting mask regions; and
segmenting objects in 3D based on depth discontinuity.

15. The method as recited in claim 14 , wherein the 2D foreground objects within the mask can be at any depth.

16. The method as recited in claim 5 , wherein detecting the object associated with the passenger includes providing an audible alert when the associated passenger leaves the passenger conveyance enclosure.

17. The method as recited in claim 6 , wherein the classification includes distinction of the object from a human.

18. The method as recited in claim 6 , wherein the classification includes associating of the object with a particular passenger.

Assignees

• Otis Elevator Co

Inventors

• Fang Hui
• Hsu Arthur
• Finn Alan Matthew
• Jia Zhen

Classifications

• H04N13/204

  using stereoscopic image cameras (stereoscopic photography G03B35/00) · CPC title

• G06T7/50

  Depth or shape recovery · CPC title

• G01C3/08

  Use of electric radiation detectors · CPC title

• B66B3/02

  Position or depth indicators · CPC title

• B66B5/0012

  Devices monitoring the users of the elevator system · CPC title