# US 2021/0342579 A1 · Method for identifying a hand pose in a vehicle

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

- Number: US 2021/0342579 A1
- Document ID: US20210342579A1
- Status: Published application
- Kind: A1
- Application number: 17/273,521
- Filed: 2019-08-27
- Published: 2021-11-04
- Earliest claimed: 2018-09-05
- Assignees: Daimler AG
- Applicants: Daimler AG
- Inventors: Hisham CHOLAKKAL; Sanath NARAYAN; Arjun JAIN; Shuaib AHMED; Amit BHATKAL; Mallikarjun BYRASANDRA RAMALINGA REDDY; Apurbaa MALLIK
- Web page: https://patentgrep.com/patent/US20210342579A1

## CPC

- G06V 40/113: {Recognition of static hand signs}
- G06F 18/2413: based on distances to training or reference patterns
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- G06T 3/40: Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T 7/74: {involving reference images or patches}
- G06V 20/59: inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions
- G06V 40/107: {Static hand or arm}
- G06V 40/28: {Recognition of hand or arm movements, e.g. recognition of deaf sign language (static hand signs G06V40/113)}
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/20132: Image cropping
- G06T 2207/30268: Vehicle interior
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

A method for identifying a hand pose in a vehicle involves identifying a hand image for a hand in the vehicle by extraction from a vehicle image of the vehicle. A plurality of contextual images of the hand image is obtained based on the single point. Each of the plurality of contextual images are processed using one or more layers of a neural network to obtain a plurality of contextual features associated with the hand image. A hand pose associated with the hand is identified based on the plurality of contextual features using a classifier model.

## Claims

### Claim at position 1

1-7. (canceled)

### Claim 8

A method, comprising:
extracting a hand image of a hand in a vehicle image of a vehicle using a single point associated with the hand;
obtaining a plurality of contextual images of the hand image based on the single point;
processing each of the plurality of contextual images using one or more layers of a neural network to obtain a plurality of contextual features associated with the hand image; and
identifying, using a classifier model, a hand pose associated with the hand based on the plurality of contextual features.

### Claim 9 (depends on 8)

The method of claim 8, wherein the identification of the hand pose further comprises:
aggregating each of the plurality of contextual features.

### Claim 10 (depends on 8)

The method of claim 8, wherein the neural network is a convolution neural network having one or more layers comprising at least one of a convolution unit, a batch normalization unit, a rectified linear unit, a fully connected unit, and a pooling unit.

### Claim 11 (depends on 8)

The method of claim 8, wherein the plurality of contextual images are obtained by:
pre-processing the hand image using one or more image channels associated with the hand image and a neural network.

### Claim 12 (depends on 8)

The method of claim 8, wherein each of the plurality of contextual images is obtained by:
cropping the hand image to a corresponding predefined size; and
selecting the single point at a fixed position in the hand image.

### Claim 13

A method, comprising:
extracting a hand image of a hand in a vehicle image of a vehicle using a single point associated with the hand;
obtaining a plurality of contextual images of the hand image based on the single point;
processing each of the plurality of contextual images using one or more layers of a neural network to obtain a plurality of contextual features associated with the hand image;
identifying, using a classifier model, a hand pose associated with the hand based on the plurality of contextual features; and
performing, by an event performing system, an event corresponding to the identified hand pose.

### Claim 14

A system, comprising:
a processor; and
a non-transitory memory communicatively coupled to the processor, wherein the memory stores processor-executable instructions, which, on execution, cause the processor to:
extract a hand image of a hand in a vehicle image of a vehicle using a single point associated with the hand;
obtain a plurality of contextual images of the hand image based on the single point;
process each of the plurality of contextual images using one or more layers of a neural network to obtain a plurality of contextual features associated with the hand image; and
identify, using a classifier model, a hand pose associated with the hand based on the plurality of contextual features.
