Method and device for monitoring individuals in a place equipped with distributed detection means

Patent metadata

Field	Value
Publication number	US-10636262-B2
Application number	US-201615068014-A
Country	US
Kind code	B2
Filing date	Mar 11, 2016
Priority date	Mar 13, 2015
Publication date	Apr 28, 2020
Grant date	Apr 28, 2020

Abstract

Method for monitoring individuals in a place equipped with cameras, the method including the steps of: detecting representative characteristics of an individual in a first zone of the place; detecting representative characteristics of an individual in at least a second zone and comparing these representative characteristics with representative characteristics previously stored in order to determine whether the individual detected in the second zone has been detected in other zones; confirming the determination from a topography of the place by checking consistency of a path of the individual from one zone to another and of the time model by comparing temporal detection information on the representative characteristics in the zones. Device for implementing this method.

First claim

The invention claimed is:

1. A method for determining paths of individuals in a place having zones equipped with detection means for detecting individuals, and some of which are inaccessible directly from other zones, the detection means being connected to a computerised processing unit incorporating a topography of the place and a time model comparing a travel time and at least one possible path between the zones, the method comprising the steps of,
storing in the computerised processing unit image data of initial events each associating a detection of representative characteristics of an individual in a first zone and temporal detection information, detection in the first zone is realized in the vicinity of an access control station in which each individual must present an identification document,
listing in the computerised processing unit image data of subsequent events each associating a detection of representative characteristics of an individual in another one of the zones of the place and temporal detection information,
reconstituting in the computerised processing unit a path of each individual in the place from the first zone by aggregating events subsequent to each initial event by comparing representative characteristics of each subsequent event with representative characteristics of each initial event, and checking consistency of the paths of the individuals from one zone to another from the topography of the place, the time model and temporal detection information,
when at least one subsequent event, referred to as a residual subsequent event, has not been able to be aggregated in a path, the method comprises the subsequent steps of: identifying reconstituted paths considered to be incomplete from the topography of the place, determining a probability that the residual subsequent event follows a last subsequent event of each reconstituted path considered to be incomplete and aggregating the residual subsequent event with one of the reconstituted paths according to this probability,
in which, during subsequent steps, from the topography, paths are sought that may lead an individual to the residual subsequent event starting from the last subsequent event of each reconstituted path and a probability density is calculated for all these paths.

2. A method according to claim 1 , wherein the probability that the residual subsequent event follows the last subsequent event of one of the reconstituted paths considered to be incomplete for forming a new reconstituted path is a product of:
a probability that the representative characteristics of the last subsequent event of the one of the reconstituted paths belong to the same individual as the representative characteristics of the residual subsequent event from a model of the representative characteristics,
a probability that an individual passes from a zone of the last subsequent event of the one of the reconstituted paths to a zone of the residual subsequent event without having been detected in an intermediate zone.

3. A method according to claim 2 , in which the product for calculating the probability that the residual subsequent event follows the last subsequent event of the one of the reconstituted paths also comprises a probability that an individual passes from the zone of the last subsequent event of the reconstituted path to the zone of the residual subsequent event in a time separating time information of the last subsequent event of the reconstituted path and the time information of the residual subsequent event.

4. A method according to claim 2 , in which the probability that an individual passes from the zone of the last subsequent event of the reconstituted path to the zone of the residual subsequent event without having been detected is a product of:
an error detection probability,
a probability that an individual passes from the zone of the last subsequent event of the reconstituted path to a zone of the residual subsequent event taking account of a history of the reconstituted paths.

5. A method according to claim 1 , in which, during subsequent steps, from the topography, paths are sought that may lead an individual to the residual subsequent event starting from the last subsequent event of each reconstituted path and a probability density is calculated for all these paths.

6. A method according to claim 5 , in which a path is ignored if the probability that an individual takes this path to pass from the zone of the last subsequent event of the reconstituted path to the zone of the residual subsequent event taking account of a history of the reconstituted paths is below a predetermined threshold.

7. A method according to claim 1 , in which the time model is based on a mean travel time over a path.

8. A method according to claim 1 , in which the detection means comprises at least one biometric sensor.

9. A method according to claim 8 , in which the detection means comprise a plurality of biometric sensors, the biometric sensors being of different types in order to capture biometric characteristics of different types.

10. A method according to claim 1 , in which the detection means of the first zone are disposed in the vicinity of an access control station in which each individual must present an identification document.

11. A method according to claim 1 , in which the representative characteristics detected in each zone are stored.

12. A monitoring device for monitoring individuals in a place having zones equipped with detection means for detecting individuals, and some of which are inaccessible directly from other zones, the monitoring device comprising a computerised processing unit that is connected to the detection means and is arranged to process data transmitted by the detection means, the computerised processing unit having a memory containing a topography of the place and a time model comparing a travel time and at least one path between the zones and executing a program implementing the method according to claim 1 .

13. A method according to claim 1 , wherein the detection means comprise cameras for capturing images of the individual moving in the zones, the representative characteristics of the individual being biometric characteristics extracted from said images.

Assignees

• Morpho
• Idemia Identity & Security

Inventors

• Beiler Olivier
• Escamilla Pierre
• Gentric Stephane

Classifications

• G08B31/00

  Predictive alarm systems characterised by extrapolation or other computation using updated historic data · CPC title

• G06T7/292

  Multi-camera tracking · CPC title

• G08B13/19641 Primary

  Multiple cameras having overlapping views on a single scene · CPC title

• G06T2207/30241

  Trajectory · CPC title

• G08B25/009

  Signalling of the alarm condition to a substation whose identity is signalled to a central station, e.g. relaying alarm signals in order to extend communication range · CPC title