# US 2025/0375108 A1 · Implicit gaze and focus distance calibration

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

- Number: US 2025/0375108 A1
- Document ID: US20250375108A1
- Status: Published application
- Kind: A1
- Application number: 18/735,608
- Filed: 2024-06-06
- Published: 2025-12-11
- Earliest claimed: 2024-06-06
- Assignees: Distance Technologies Oy
- Applicants: Distance Technologies Oy
- Inventors: Thomas Carlsson; Mikko Strandborg
- Web page: https://patentgrep.com/patent/US20250375108A1

## CPC

- A61B 3/111: {for measuring interpupillary distance}
- G06V 20/597: {Recognising the driver's state or behaviour, e.g. attention or drowsiness}
- B60K 35/233: controlling the size or position in display areas of virtual images depending on the condition of the vehicle or the driver
- G02B 27/0093: {with means for monitoring data relating to the user, e.g. head-tracking, eye-tracking}
- G06F 3/013: {Eye tracking input arrangements (G06F3/015 takes precedence)}
- G06F 3/0304: {Detection arrangements using opto-electronic means (constructional details of pointing devices not related to the detection arrangement using opto-electronic means G06F3/033; optical digitisers G06F3/042)}
- G06T 7/55: from multiple images
- G06V 40/18: Eye characteristics, e.g. of the iris
- G02B 2027/0138: {comprising image capture systems, e.g. camera}
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- B60K: ARRANGEMENT OR MOUNTING OF PROPULSION UNITS OR OF TRANSMISSIONS IN VEHICLES; ARRANGEMENT OR MOUNTING OF PLURAL DIVERSE PRIME-MOVERS IN VEHICLES; AUXILIARY DRIVES FOR VEHICLES; INSTRUMENTATION OR DASHBOARDS FOR VEHICLES; ARRANGEMENTS IN CONNECTION WITH COOLING, AIR INTAKE, GAS EXHAUST OR FUEL SUPPLY OF PROPULSION UNITS IN VEHICLES
- G02B: OPTICAL ELEMENTS, SYSTEMS OR APPARATUS
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

Images of a user's face are captured at a plurality of time instants. Tracking parameters are determined, tracking parameters include: a pose of the user's head, positions of eyeballs, and at least one of: relative positions of irises with respect to boundaries of the eyeballs, relative positions of irises with respect to corners, shapes of the user's eyes. Uncalibrated gaze vectors of the user's eyes are estimated. A set of uncalibrated gaze vectors is generated. The uncalibrated gaze vectors of thset are stored along with corresponding time instants and tracking parameters. A first subset of uncalibrated gaze vectors whose direction matches with a predefined forward axis of vision, is selected. For the uncalibrated gaze vectors, corresponding tracking parameters are fetched. A maximum distance between the irises is determined. The maximum distance is considered as an interpupillary distance.

## Claims

### Claim 1

A system comprising:
at least one tracking camera; and
at least one processor configured to:
capture a plurality of images of a user's face at a plurality of time instants, using the at least one tracking camera;
process a given image captured at a given time instant, to determine a plurality of tracking parameters comprising: a pose of the user's head, positions of eyeballs of the user's eyes, and at least one of: relative positions of irises of the user's eyes with respect to boundaries of the eyeballs, relative positions of irises of the user's eyes with respect to corners of the user's eyes, shapes of the user's eyes;
estimate uncalibrated gaze vectors of the user's eyes corresponding to the given time instant, based on the plurality of tracking parameters determined from the given image;
generate a set of uncalibrated gaze vectors of the user's eyes corresponding to the plurality of time instants, by performing said processing and said estimation for each of the plurality of images;
store at least temporarily the uncalibrated gaze vectors of the set along with corresponding time instants and corresponding pluralities of tracking parameters;
select, from amongst the set of uncalibrated gaze vectors, a first subset of uncalibrated gaze vectors whose direction matches with a predefined forward axis of vision;
for the uncalibrated gaze vectors of the first subset, fetch corresponding pluralities of tracking parameters;
determine a maximum distance between the irises of the user's eyes, based on the corresponding pluralities of tracking parameters fetched for the uncalibrated gaze vectors of the first subset; and
consider the maximum distance as an interpupillary distance of the user for focusing distances greater than a predefined threshold distance.

### Claim 2 (depends on 1)

The system of claim 1, wherein the at least one processor is configured to:
generate a mapping between a forward axis of vision specific to the user and the corresponding pluralities of tracking parameters fetched for the uncalibrated gaze vectors of the first subset; and
estimate calibrated gaze vectors of the user's eyes corresponding to a next time instant, based on a plurality of tracking parameters determined from a next image captured at the next time instant, by utilising the generated mapping.

### Claim 3 (depends on 1)

The system of claim 1, wherein the at least one processor is configured to:
detect an input event pertaining to a selection of an input option by the user;
when the input event is detected, determine a position of the input option selected by the user and a time instant at which the input option was selected by the user;
select, from amongst the set of uncalibrated gaze vectors, a second subset of uncalibrated gaze vectors whose corresponding time instants lie within a predefined time period from the time instant at which the input option was selected by the user, and whose direction matches with viewing directions pointing from the positions of the eyeballs towards the position of the input option;
for the uncalibrated gaze vectors of the second subset, fetch corresponding pluralities of tracking parameters; and
determine a focusing distance of the user's eyes corresponding to when the user is looking at the input option, based on a distance between the position of the input option and the positions of eyeballs of the user's eyes in the corresponding pluralities of tracking parameters fetched for the uncalibrated gaze vectors of the second subset.

### Claim 4 (depends on 3)

The system of claim 3, wherein the at least one processor is configured to:
determine a distance between the irises of the user's eyes, based on the corresponding pluralities of tracking parameters fetched for the uncalibrated gaze vectors of the second subset; and
consider the distance as an interpupillary distance of the user for the focusing distance of the user's eyes corresponding to when the user is looking at the input option.

### Claim 5 (depends on 3)

The system of claim 3, wherein the at least one processor is configured to:
generate a mapping between the viewing directions pointing from the positions of the eyeballs towards the position of the input option, and the corresponding pluralities of tracking parameters fetched for the uncalibrated gaze vectors of the second subset; and
estimate calibrated gaze vectors of the user's eyes corresponding to another next time instant, based on a plurality of tracking parameters determined from another next image captured at the another next time instant, by utilising the generated mapping.

### Claim 6 (depends on 1)

The system of claim 1, wherein the system is implemented in an enclosed space in which at least one instrument is being used, and wherein the at least one processor is configured to:
select, from amongst the set of uncalibrated gaze vectors, a third subset of uncalibrated gaze vectors whose direction matches with viewing directions pointing from the positions of the eyeballs towards a position of the at least one instrument;
for the uncalibrated gaze vectors of the third subset, fetch corresponding pluralities of tracking parameters; and
determine a focusing distance of the user's eyes corresponding to when the user is looking at the at least one instrument, based on a distance between the position of the at least one instrument and the positions of eyeballs of the user's eyes in the corresponding pluralities of tracking parameters fetched for the uncalibrated gaze vectors of the third subset.

### Claim 7 (depends on 6)

The system of claim 6, wherein the at least one processor is configured to:
determine a distance between the irises of the user's eyes, based on the corresponding pluralities of tracking parameters fetched for the uncalibrated gaze vectors of the third subset; and
consider the distance as an interpupillary distance of the user for the focusing distance of the user's eyes corresponding to when the user is looking at the at least one instrument.

### Claim 8 (depends on 6)

The system of claim 6, wherein the at least one processor is configured to:
generate a mapping between the viewing directions pointing from the positions of the eyeballs towards the position of the at least one instrument, and the corresponding pluralities of tracking parameters fetched for the uncalibrated gaze vectors of the third subset; and
estimate calibrated gaze vectors of the user's eyes corresponding to yet another next time instant, based on a plurality of tracking parameters determined from yet another next image captured at the yet another next time instant, by utilising the generated mapping.

### Claim 9 (depends on 1)

The system of claim 1, wherein the system is implemented in a vehicle, the system further comprising at least one real-world-facing camera, wherein the at least one processor is configured to:
process images captured by the at least one real-world-facing camera, to generate a depth image of the real-world environment;
reproject the depth image of the real-world environment from a perspective of the at least one real-world facing camera to a perspective of a position of a given eye of the user; and
for the uncalibrated gaze vectors of the first subset, determine a focusing distance of the user's eyes corresponding to a forward axis of vision specific to the user, by utilising the reprojected depth image.

### Claim 10

A method comprising:
capturing a plurality of images of a user's face at a plurality of time instants, using at least one tracking camera;
processing a given image captured at a given time instant, to determine a plurality of tracking parameters comprising: a pose of the user's head, positions of eyeballs of the user's eyes, and at least one of: relative positions of irises of the user's eyes with respect to boundaries of the eyeballs, relative positions of irises of the user's eyes with respect to corners of the user's eyes, shapes of the user's eyes;
estimating uncalibrated gaze vectors of the user's eyes corresponding to the given time instant, based on the plurality of tracking parameters determined from the given image;
generating a set of uncalibrated gaze vectors of the user's eyes corresponding to the plurality of time instants, by performing said processing and said estimation for each of the plurality of images;
storing at least temporarily the uncalibrated gaze vectors of the set along with corresponding time instants and corresponding pluralities of tracking parameters;
selecting, a first subset of uncalibrated gaze vectors from amongst the set of uncalibrated gaze vectors whose direction matches with a predefined forward axis of vision;
fetching corresponding pluralities of tracking parameters for the uncalibrated gaze vectors of the first subset;
determining a maximum distance between the irises of the user's eyes, based on the corresponding pluralities of tracking parameters fetched for the uncalibrated gaze vectors of the first subset; and
considering the maximum distance as an interpupillary distance of the user for focusing distances greater than a predefined threshold distance.

### Claim 11 (depends on 10)

The method of claim 10, further comprising:
generating a mapping between a forward axis of vision specific to the user and the corresponding pluralities of tracking parameters fetched for the uncalibrated gaze vectors of the first subset; and
estimating calibrated gaze vectors of the user's eyes corresponding to a next time instant, based on a plurality of tracking parameters determined from a next image captured at the next time instant, by utilising the generated mapping.

### Claim 12 (depends on 10)

The method of claim 10, further comprising:
detecting an input event pertaining to a selection of an input option by the user;
when the input event is detected, determining a position of the input option selected by the user and a time instant at which the input option was selected by the user;
selecting, from amongst the set of uncalibrated gaze vectors, a second subset of uncalibrated gaze vectors whose corresponding time instants lie within a predefined time period from the time instant at which the input option was selected by the user, and whose direction matches with viewing directions pointing from the positions of the eyeballs towards the position of the input option;
fetching corresponding pluralities of tracking parameters for the uncalibrated gaze vectors of the second subset; and
determining a focusing distance of the user's eyes corresponding to when the user is looking at the input option, based on a distance between the position of the input option and the positions of eyeballs of the user's eyes in the corresponding pluralities of tracking parameters fetched for the uncalibrated gaze vectors of the second subset.

### Claim 13 (depends on 12)

The method of claim 12, further comprising:
determining a distance between the irises of the user's eyes, based on the corresponding pluralities of tracking parameters fetched for the uncalibrated gaze vectors of the second subset; and
considering the distance as an interpupillary distance of the user for the focusing distance of the user's eyes corresponding to when the user is looking at the input option.

### Claim 14 (depends on 12)

The method of claim 12, further comprising:
generating a mapping between the viewing directions pointing from the positions of the eyeballs towards the position of the input option, and the corresponding pluralities of tracking parameters fetched for the uncalibrated gaze vectors of the second subset; and
estimating calibrated gaze vectors of the user's eyes corresponding to another next time instant, based on a plurality of tracking parameters determined from another next image captured at the another next time instant, by utilising the generated mapping.

### Claim 15 (depends on 10)

The method of claim 10, further comprising:
selecting, from amongst the set of uncalibrated gaze vectors, a third subset of uncalibrated gaze vectors whose direction matches with viewing directions pointing from the positions of the eyeballs towards a position of at least one instrument, wherein the at least one instrument is being used in an enclosed space;
fetching corresponding pluralities of tracking parameters for the uncalibrated gaze vectors of the third subset; and
determining a focusing distance of the user's eyes corresponding to when the user is looking at the at least one instrument, based on a distance between the position of the at least one instrument and the positions of eyeballs of the user's eyes in the corresponding pluralities of tracking parameters fetched for the uncalibrated gaze vectors of the third subset.

### Claim 16 (depends on 15)

The method of claim 15, further comprising:
determining a distance between the irises of the user's eyes, based on the corresponding pluralities of tracking parameters fetched for the uncalibrated gaze vectors of the third subset; and
considering the distance as an interpupillary distance of the user for the focusing distance of the user's eyes corresponding to when the user is looking at the at least one instrument.

### Claim 17 (depends on 15)

The method of claim 15, further comprising:
generating a mapping between the viewing directions pointing from the positions of the eyeballs towards the position of the at least one instrument, and the corresponding pluralities of tracking parameters fetched for the uncalibrated gaze vectors of the third subset; and
estimating calibrated gaze vectors of the user's eyes corresponding to yet another next time instant, based on a plurality of tracking parameters determined from yet another next image captured at the yet another next time instant, by utilising the generated mapping.

### Claim 18 (depends on 10)

The method of claim 10, further comprising:
processing images captured by at least one real-world-facing camera to generate a depth image of the real-world environment, wherein the at least one real-world-facing camera is implemented in a vehicle;
reprojecting the depth image of the real-world environment from a perspective of the at least one real-world facing camera to a perspective of a position of a given eye of the user; and
determining a focusing distance of the user's eyes for the uncalibrated gaze vectors of the first subset, by utilising the reprojected depth image, wherein the focusing distance of the user's eyes correspond to a forward axis of vision specific to the user.
