Real-time object detection from decompressed images

Patent metadata

Field	Value
Publication number	US-12347208-B2
Application number	US-202318860026-A
Country	US
Kind code	B2
Filing date	Aug 21, 2023
Priority date	Aug 29, 2022
Publication date	Jul 1, 2025
Grant date	Jul 1, 2025

Abstract

A system or method trains and implements a machine learning model for object detection. A first computing device remote to a vehicle trains a machine learning model by receiving a decoded set of previously encoded training image data and training the machine learning model to detect objects within images based on the decoded set of training image data. A processor of a second computing device encodes at least one image captured by a camera, decodes the encoded image, and executes the machine learning model to extract a set of objects from the decoded image.

First claim

What is claimed is:

1. A method for training and implementing a machine learning model for object detection, wherein a first computing device remote to a vehicle trained the machine learning model by receiving a decoded set of previously encoded training image data; changing a size of each of the decoded set of training image data from a first number of pixels to a second number of pixels; and training the machine learning model to detect objects within images based on the decoded set of training image data in the second number of pixels, the method comprising:
encoding, by at least one processor of a second computing device in communication with a camera mounted on or in the vehicle, at least one image captured by the camera;
decoding, by the at least one processor, the encoded at least one image;
changing, by the at least one processor, a size of the decoded at least one image from the first number of pixels to the second number of pixels; and
executing, by the at least one processor, the machine learning model to extract a set of objects from the decoded at least one image in the second number of pixels.

2. The method of claim 1 , wherein the first computing device trained the machine learning model by decoding the encoded set of training image data from a compressed format into a decompressed format, and wherein:
encoding the at least one image comprises encoding, by the at least one processor, the at least one image into the compressed format; and
decoding the encoded at least one image comprises decoding, by the at least one processor, the encoded at least one image into the decompressed format.

3. The method of claim 1 , wherein the first computing device trained the machine learning model by decoding the encoded set of training image data using a software decoder, and
wherein decoding the encoded at least one image comprises decoding, by the at least one processor, the encoded at least one image using a hardware decoder.

4. The method of claim 1 , wherein the first computing device trained the machine learning model by changing the size of each of the decoded set of training image data using a first software resizer, and
wherein changing the size of the encoded at least one image comprises changing, by the at least one processor, the size of the encoded at least one image using the first software resizer, a second software resizer, or a hardware resizer.

5. The method of claim 1 , wherein executing the machine learning model comprises executing, by the at least one processor, the machine learning model to extract a set of objects from the decoded at least one image in real time as the vehicle is driving.

6. The method of claim 1 , wherein receiving the at least one image from the camera comprises receiving, by the at least one processor, a video comprising a plurality of images including the at least one image, and wherein decoding the at least one image comprises decoding, by the at least one processor, the at least one image in response to selecting the at least one image from the plurality of images according to one or more selection rules.

7. The method of claim 6 , wherein selecting the at least one image according to the one or more selection rules comprises selecting, by the at least one processor, the at least one image by identifying the at least one image at a set interval of images in the plurality of images.

8. The method of claim 1 , further comprising:
determining, by the at least one processor, a change in vehicle operation of the vehicle based on the extracted set of objects; and
transmitting, by the at least one processor, the change in vehicle operation of the vehicle to a second processor controlling the vehicle, the second processor controlling the vehicle according to the change in vehicle operation.

9. The method of claim 1 , wherein the second computing device is mounted on or in the vehicle.

10. A system for training and implementing a machine learning model for object detection, the system comprising
a remote processor of a first computing device remote from a vehicle, the remote processor coupled to a remote non-transitory memory of the first computing device, wherein the remote processor is configured to:
receive an encoded set of training image data;
decode the encoded set of training image data;
change a size of each of the decoded set of training image data from a first number of pixels to a second number of pixels; and
train a machine learning model to detect objects within images based on the decoded set of training image data; and

an on-board processor of a second computing device in communication with an on-board non-transitory memory of the second computing device and a camera mounted on or in the vehicle, wherein the on-board processor of the second computing device is configured to:
encode at least one image captured by the camera;
decode the encoded at least one image;
change a size of the decoded at least one image from the first number of pixels to the second number of pixels; and
execute the machine learning model to extract a set of objects from the decoded at least one image in the second number of pixels.

11. The system of claim 10 , wherein the remote processor is further configured to transmit the machine learning model to the on-board processor across a network.

12. The system of claim 10 , wherein the remote processor is further configured to transmit the machine learning model to the on-board processor responsive to determining the machine learning model has an accuracy above an accuracy threshold on decoded input data.

13. The system of claim 10 , wherein the remote processor is configured to:
decode the encoded set of training image data by decoding the encoded set of training image data from a compressed format into a decompressed format, and

wherein the on-board processor is configured to:
encode the at least one image by encoding the at least one image into the compressed format; and
decode the encoded at least one image by decoding the encoded at least one image into the decompressed format.

14. The system of claim 10 , wherein the remote processor is configured to decode the encoded set of training image data using a software decoder, and
wherein the on-board processor is configured to decode the encoded at least one image by decoding the encoded at least one image using a hardware decoder.

15. The system of claim 10 , wherein the on-board processor is further configured to:
receive the at least one image from the camera mounted on or in the vehicle as the vehicle is driving down a road,
wherein the on-board processor is configured to encode the at least one image by encoding an image including a depiction of the road.

16. A method for training and implementing a model for object detection, comprising:
encoding, by at least one processor of a computing device in communication with a camera mounted on or in a vehicle, at least one first image captured by the camera;
transmitting, by the at least one processor, the encoded at least one first image to a remote computing device remote from the at least one processor, the remote computing device or a second computing device decoding the encoded at least one first image, changing, a size of the decoded at least one first image from a first number of pixels to a second number of pixels; and
training, with the decoded at least one first image, a machine learning model to extract objects within images in the second number of pixels;
receiving, by the at least one processor, the machine learning model from the remote computing device or the second

Assignees

• Netradyne Inc

Inventors

• Yerakaraju Suresh Kumar
• Motuti Shravan Kumar
• Gupta Hitesh
• Mathad Praveen
• Yedla Arvind
• Annapureddy Venkata Sreekanta Reddy

Classifications

• G06V10/70

  using pattern recognition or machine learning (optical pattern recognition or electronic computations therefor G06V10/88) · CPC title

• G06V10/82

  using neural networks · CPC title

• G06V10/776

  Validation; Performance evaluation · CPC title

• G06N20/00

  Machine learning · CPC title

• G06V20/58 Primary

  Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads · CPC title