# US 2019/0318211 A1 · Contextually aware system and method

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

- Number: US 2019/0318211 A1
- Document ID: US20190318211A1
- Status: Published application
- Kind: A1
- Application number: 16/462,550
- Filed: 2017-11-21
- Published: 2019-10-17
- Earliest claimed: 2016-11-21
- Assignees: Poly Ai, Inc.
- Applicants: Poly Ai, Inc.
- Inventors: Alberto RIZZOLI; Simon EDWARDSSON
- Web page: https://patentgrep.com/patent/US20190318211A1

## CPC

- G06V 10/82: using neural networks
- G06N 3/02: Neural networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06V 10/70: using pattern recognition or machine learning (optical pattern recognition or electronic computations therefor G06V10/88)
- G06V 10/955: {using specific electronic processors}
- G06V 20/10: Terrestrial scenes (scenes under surveillance with static cameras G06V20/52; scenes perceived from the exterior of a vehicle G06V20/56; scenes perceived from the interior of a vehicle G06V20/59)
- G06N 3/045: Combinations of networks
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A method of analysing an image the image transmitted from a local image acquisition device to a local image processor; the local image processor processing the image locally in order to define at least one context descriptor relevant to a scene contained in the image.

## Claims

### Claim 1

A method of analysing an image the image transmitted from a local image acquisition device to a local image processor; the local image processor processing the image locally in order to define at least one context descriptor relevant to a scene contained in the image.

### Claim 2 (depends on 1)

The method of claim 1 wherein the local image processor utilises a first processing algorithm to define a class or object within said scene.

### Claim 3 (depends on 1)

The method of claim 1 wherein said local image processor utilises at least one associated local input.

### Claim 4 (depends on 3)

The method of claim 3 wherein the local image processor utilises the at least one associated local input to trigger generation of said at least one context descriptor.

### Claim 5 (depends on 3)

The method of claim 3 wherein the associated local input comprises a GPS signal.

### Claim 6 (depends on 3)

The method of claim 3 wherein the associated local input comprises a clock signal

### Claim 7 (depends on 3)

The method of claim 3 wherein the associated local input comprises a accelerometer signal

### Claim 8 (depends on 3)

The method of claim 3 wherein the associated local input comprises a gyroscope signal.

### Claim 9 (depends on 3)

The method of claim 3 wherein the associated local input is a local switch.

### Claim 10 (depends on 3)

The method of claim 3 wherein the associated local input is a touchscreen switch.

### Claim 11 (depends on 2)

The method of claim 2 wherein the local image processor utilises a second processing algorithm to define the at least one context descriptor.

### Claim 12 (depends on 11)

The method of claim 11 wherein the local image processor utilises output from the first processing algorithm to define the at least one context descriptor.

### Claim 13 (depends on 11)

The method of claim 11 wherein the local image processor utilises at least one associated local input to define the at least one context descriptor.

### Claim 14 (depends on 2)

The method of claim 2 wherein the local image processor utilises output from the first processing algorithm and at least one associated local input to define the at least one context descriptor.

### Claim 15 (depends on 2)

The method of claim 2 wherein the first processing algorithm utilises a convolutional neural network algorithm to process the image.

### Claim 16 (depends on 11)

The method of claim 11 wherein the second processing algorithm utilises a convolutional neural network algorithm to process the image thereby to define said at least one context descriptor relevant to said scene contained in the image.

### Claim 17 (depends on 1)

The method of claim 1 wherein the local image acquisition device and local image processor form part of and are mechanically and electronically associated with a portable digital device.

### Claim 18 (depends on 17)

The method of claim 17 wherein the portable digital device is a smart phone.

### Claim 19 (depends on 17)

The method of claim 17 wherein the portable digital device is a wearable device.

### Claim 20 (depends on 17)

The method of claim 17 wherein the portable digital device is an augmented reality headset.

### Claim at position 21

21-37. (canceled)