# US 2018/0324393 A1 · Method for monitoring occupancy in a work area

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2018/0324393 A1
- Document ID: US20180324393A1
- Status: Published application
- Kind: A1
- Application number: 15/973,445
- Filed: 2018-05-07
- Published: 2018-11-08
- Earliest claimed: 2017-05-05
- Assignees: VergeSense, Inc.
- Applicants: VergeSense, Inc.
- Inventors: Dan Ryan; Kelby Green
- Web page: https://patentgrep.com/patent/US20180324393A1

## CPC

- H04N 7/188: {Capturing isolated or intermittent images triggered by the occurrence of a predetermined event, e.g. an object reaching a predetermined position (signal generation from motion picture films H04N5/253)}
- G05D 23/1917: {using digital means}
- G06F 18/23: Clustering techniques
- G06V 10/143: Sensing or illuminating at different wavelengths
- G06V 10/762: using clustering, e.g. of similar faces in social networks
- G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69)
- G06V 20/53: {Recognition of crowd images, e.g. recognition of crowd congestion}
- Y02B 20/40: Control techniques providing energy savings, e.g. smart controller or presence detection
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION
- G05D: SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- Y02B: CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS

## Abstract

One variation of a method for monitoring occupancy in a work area includes, at a sensor block: transitioning from an inactive state into an active state when an output of a motion sensor indicates motion in a work area; during a scan cycle in the active state, recording an image through an optical sensor at a time, detecting a set of humans in the image, detecting a second set of human effects in the image, predicting a second set of humans occupying but absent the work area based on the second set of human effects, and estimating a total occupancy in the work area at the time based on the set of humans and the second set of humans; and transmitting the total occupancy to a remote computer system for update of a scheduler for the work area.

## Claims

### Claim 1

A method for monitoring occupancy in a work area, the method comprising:
at a sensor block, transitioning from an inactive state into an active state in response to an output of a motion sensor, integrated into the sensor block, indicating motion in a field of view of an optical sensor integrated into the sensor block, the field of view encompassing the work area;
during a first scan cycle in the active state:
recording a first image through the optical sensor at a first time;
detecting a first set of humans in the first image;
detecting a second set of human effects in the first image;
predicting a second set of humans occupying but absent the work area based on the second set of human effects; and
estimating a first total occupancy in the work area at the first time based on the first set of humans and the second set of humans; and
transmitting the first total occupancy to a remote computer system for update of a scheduler for the work area.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
in the active state:
recording a last time of an output of the motion sensor indicating motion in the work area;
in response to the last time preceding a current time by more than a threshold duration, recording a second image through the optical sensor; and
scanning the second image for humans and human effects; and
in response to detecting, in the second image, absence of humans and absence of human effects indicative of human occupancy in the work area, transitioning from the active state into the inactive state.

### Claim 3 (depends on 2)

The method of claim 2, further comprising:
at the remote computer system, in response to receipt of the first total occupancy, greater than null, from the sensor block at approximately the first time:
tightening a tolerance on a target temperature in the work area;
serving a command specifying a temperature change in the work area to a ventilation control system coupled to the work area;
at the sensor block, in response to detecting absence of humans and absence of human effects in the second image and prior to transitioning from the active state into the inactive state, transmitting confirmation of vacancy in the work area at the second time to the remote computer system; and
in response to receipt of confirmed vacancy in the work area from the sensor block at approximately the second time, loosening the tolerance on the target temperature in the work area.

### Claim 4 (depends on 1)

The method of claim 1, further comprising, at the sensor block:
operating in the inactive state by default, the inactive state defining a low-power mode;
in the active state, executing a series of scan cycles between periods of low-power operation to calculate a series of total occupancy estimates for the work area following the first time, each period of low-power operation in the active state less than a first duration; and
in the active state, transmitting a preceding subset of total occupancy estimates, in the series of total occupancy estimates, to the remote computer system in time intervals greater than the first duration.

### Claim 5 (depends on 4)

The method of claim 4, wherein executing the series of scan cycles between periods of low-power operation comprises, in the active state, executing the series of scan cycles between periods of low-power operation of duration inversely proportional to a rate of change of total occupancy estimates, in the work area, detected during preceding scan cycles.

### Claim 6 (depends on 1)

The method of claim 1:
wherein transitioning from the inactive state into the active state comprises transitioning from the inactive state into the active state in response to the motion sensor detecting a motion event in the work area comprising a conference room;
wherein recording the first image comprises recording the first image through the optical sensor, defining the field of view intersecting the conference room, responsive to the motion event; and
further comprising, at the remote computer system, updating the scheduler associated with the conference room to indicate the conference room as occupied at the first time based on the first total occupancy exceeding a threshold occupancy.

### Claim 7 (depends on 6)

The method of claim 6, further comprising:
in the active state at the sensor block:
entering a low-power mode for a first dwell period following the first scan cycle; and
during a second scan cycle following the first dwell period:
recording a second image through the optical sensor at a second time;
detecting humans in the conference room based on features detected in the second image;
characterizing engagement between humans in the conference room at the second time based on features detected in the second image;
estimating a second meeting quality in the conference room based on engagement between humans in the conference room at the second time; and
transmitting the second meeting quality to the remote computer system; and
at the remote computer system:
in response to the second meeting quality exceeding a threshold quality, updating the scheduler to indicate the conference room as occupied and unavailable; and
in response to the second meeting quality falling below the threshold quality, updating the scheduler to indicate the conference room as occupied but available.

### Claim 8 (depends on 6)

The method of claim 6:
wherein transmitting the first total occupancy to the remote computer system comprises transmitting the first total occupancy to the remote computer system at approximately the first time;
further comprising:
in the active state, executing a series of scan cycles between periods of low-power operation following the first scan cycle;
during each scan cycle in the series of scan cycles:
recording an image through the optical sensor; and
detecting a quantity of humans in the conference room based on features detected in the image;
recording a last time of an output of the motion sensor indicating motion in the conference room;
in response to the last time preceding a current time by more than a threshold duration, recording a second image through the optical sensor;
scanning the second image for humans and human effects; and
in response to detecting absence of humans and absence of human effects indicative of human occupancy in the second image:
transmitting a time series of quantities of humans in the conference room from approximately the first time to approximately the current time to the remote computer system; and
transitioning from the active state into the inactive state.

### Claim 9 (depends on 6)

The method of claim 6:
further comprising, in response to transitioning from the inactive state into the active state, setting a delay timer for a duration associated with aggregation of humans in the conference room; and
wherein recording the first image comprises recording the first image during the first scan cycle at the first time in response to expiration of the delay timer.

### Claim 10 (depends on 6)

The method of claim 6:
wherein transmitting the first total occupancy to the remote computer system comprises transmitting the first total occupancy to the remote computer system at approximately the first time;
further comprising:
in the active state, executing a series of scan cycles between periods of low-power operation following the first scan cycle; and
during each scan cycle in the series of scan cycles:
recording an image through the optical sensor;
detecting a current quantity of humans in the conference room based on features detected in the image; and
in response to the current quantity of humans in the conference room differing from a quantity of humans detected in the conference room during a preceding scan cycle, transmitting the current quantity of humans to the remote computer system.

### Claim 10 (depends on 10)

method of claim 10, further comprising, at the remote computer system, in response to receiving a quantity of humans in the conference room from the sensor block:
calculating a target rate of air exchange in the conference room proportional to the quantity of humans in the conference room; and
serving a command specifying the target rate of air exchange to a ventilation control system connected to the conference room.

### Claim 12 (depends on 1)

The method of claim 1:
wherein transitioning from the inactive state into the active state comprises transitioning from the inactive state into the active state in response to the motion sensor detecting a motion event in the work area comprising an agile work environment comprising a set of agile desks;
wherein recording the first image comprises recording the first image through the optical sensor, defining the field of view containing the set of agile desks, responsive to the motion event;
wherein detecting the first set of humans in the first image comprises interpreting proximity of the first set of humans, detected in the first image, to locations of a first subset of agile desks in the set of agile desks as occupancy of the first subset of agile desks at the first time;
wherein predicting the second set of humans occupying but absent the work area comprises interpreting proximity of the second set of human effects, detected in the first image, to locations of a second subset of agile desks in the set of agile desks and absence of humans proximal the second subset of agile desks as absent occupancy of the second subset of agile desks at the first time; and
further comprising, at the remote computer system, updating the scheduler associated with the set of agile desks to indicate the first subset of agile desks and the second subset of agile desks as occupied at the first time based on the first total occupancy.

### Claim 13 (depends on 12)

The method of claim 12:
wherein transmitting the first total occupancy to the remote computer system comprises transmitting, to the remote computer system:
confirmation of occupancy of the first subset of agile desks;
confirmation of occupancy of the second subset of agile desks; and
locations of the first subset of agile desks and the second subset of agile desks in the field of view of the optical sensor; and
wherein updating the scheduler comprises, at the remote computer system:
referencing locations of the first subset of agile desks and the second subset of agile desks received from the sensor block to a map of agile desks in the agile work environment to determine an identifier of each agile desk in the first subset of agile desks and the second subset of agile desks; and
updating the scheduler to reflect occupancy of the first subset of agile desks and the second subset of agile desks at approximately the first time based on identifiers of the first subset of agile desks and the second subset of agile desks and the first total occupancy.

### Claim 14 (depends on 12)

The method of claim 12:
further comprising, during the first scan cycle at the sensor block, interpreting absence of humans and absence of human effects, detected in the first image, proximal locations of a third subset of agile desks in the set of agile desks as vacancy of the third subset of agile desks at the first time; and
wherein transmitting the first total occupancy to the remote computer system comprises transmitting confirmed occupancy at the first subset of agile desks, predicted occupancy at the second subset of agile desks, and vacancy of the third subset of agile desks at the second time.

### Claim 15 (depends on 12)

The method of claim 12:
wherein transmitting the first total occupancy to the remote computer system comprises transmitting the first total occupancy to the remote computer system at approximately the first time;
further comprising:
in the active state, executing a series of scan cycles between periods of low-power operation following the first scan cycle; and
during each scan cycle in the series of scan cycles:
recording an image through the optical sensor;
detecting, in the image, presence of humans and human effects in the agile work environment;
interpreting presence of humans and human effects proximal agile desks in the agile work environment as a current distribution of occupancy and vacancy of agile desks in the agile work environment; and
in response to the current distribution of occupancy and vacancy of agile desks in the agile work environment differing from a distribution of occupancy and vacancy of agile desks detected in the agile work environment during a preceding scan cycle, transmitting the current distribution of occupancy and vacancy of agile desks in the agile work environment to the remote computer system.

### Claim 16 (depends on 12)

The method of claim 12:
wherein detecting a second set of human effects in the first image comprises:
detecting computing devices, clothing, notebooks, and drink containers in the first image; and
grouping human effects in the first image into a set of clusters of human effects; and
wherein predicting the second set of humans occupying but absent the work area comprises:
detecting each agile desk in the set of agile desks in the first image;
associating a particular cluster of human effects, in the set of clusters, with a particular agile desk in the second set of agile desks based on intersection of the particular cluster of human effects and the particular agile desk in the first image; and
predicting absent occupancy of the particular agile desk based on the particular cluster of human effects and absence of a human, detected in the first image, within a threshold distance of the particular agile desk.

### Claim 17 (depends on 1)

The method of claim 1, wherein detecting the first set of humans in the first image, detecting the second set of human effects in the first image, predicting the second set of humans occupying but absent the work area, and estimating the first total occupancy in the work area at the first time comprises executing an artificial intelligence model locally on the sensor block to extract the first total occupancy from the first image.

### Claim 18 (depends on 1)

The method of claim 1, further comprising:
in the active state at the sensor block:
during the first scan cycle, detecting a first distribution of objects in the first image; and
entering a low-power mode for a first dwell period following the first scan cycle;
during a second scan cycle following the first dwell period:
recording a second image through the optical sensor at a second time;
detecting a second distribution of objects in the second image;
calculating an object entropy in the work area based on a difference between the first distribution of objects and the second distribution of objects; and
transmitting the object entropy to the remote computer system; and
at the remote computer system, in response to receipt of the object entropy exceeding a threshold entropy, serving a prompt to straighten the work area to maintenance staff at approximately the second time.

### Claim 19

A method for monitoring occupancy in a conference room, the method comprising:
at a sensor block, transitioning from an inactive state into an active state in response to a motion sensor, integrated into the sensor block, detecting a motion event within the conference room;
during a first scan cycle in the active state:
recording a first image through an optical sensor, integrated into the sensor block and defining a field of view intersecting the conference room, at a first time; and
detecting a first set of humans in the first image;
transmitting the first total occupancy to a remote computer system for update of a scheduler for the conference room;
during a second scan cycle succeeding the first scan cycle in the active state:
recording a second image through the optical sensor at a second time; and
detecting absence of humans in the second image; and
in response to lack of outputs from the motion sensor indicating motion in the conference room for more than a threshold duration and detecting absence of humans in the second image:
transmitting confirmation of vacancy in the conference room to the remote computer system for update of the scheduler for the conference room; and
transitioning from the active state into the inactive state.

### Claim 20

A method for monitoring occupancy in an agile work environment, the method comprising:
at a sensor block, transitioning from an inactive state into an active state in response to a motion sensor, integrated into the sensor block, detecting a motion event within the agile work environment;
during a first scan cycle in the active state:
recording a first image through an optical sensor, integrated into the sensor block and defining a field of view containing a set of agile desks within the agile work environment, at a first time;
detecting a first set of humans in the first image;
interpreting proximity of the first set of humans, detected in the first image, to locations of a first subset of agile desks, in the set of agile desks, as occupancy of the first subset of agile desks at the first time;
detecting a second set of human effects in the first image; and
interpreting proximity of the second set of human effects, detected in the first image, to locations of a second subset of agile desks, in the set of agile desks, and absence of humans proximal the second subset of agile desks as absent occupancy of the second subset of agile desks at the first time; and
transmitting confirmation of occupancy of the first subset of agile desks and the second subset of agile desks to a remote computer system for update of a scheduler for the agile work environment.
