Image processing method

Patent metadata

Field	Value
Publication number	US-11557185-B2
Application number	US-201715807477-A
Country	US
Kind code	B2
Filing date	Nov 8, 2017
Priority date	May 12, 2015
Publication date	Jan 17, 2023
Grant date	Jan 17, 2023

Abstract

An image processing method is provided. The method includes acquiring a video. The method includes using an object detection engine to detect a person in the video. The object detection engine is integrated with an image signal processing pipeline. The method includes transmitting the video over a network. The method includes determining that the detected person has moved less than a pre-set distance. The method includes, responsive to the determining, pausing transmission of the video. An embedded image processor including an object detection engine is also provided.

First claim

What is claimed is:

1. An image processing method, comprising:
acquiring a video;
using an object detection engine to detect a person in the video, the object detection engine being integrated with an image signal processing pipeline;
using an encoder to compress the acquired video;
modifying the behaviour of the encoder based on an output of the object detection engine;
transmitting the compressed video over a network;
determining, by analysing the acquired video prior to or during transmission of the compressed video over the network, that the detected person has moved less than a pre-set distance; and
responsive to the determining, pausing the transmission of the compressed video over the network.

2. The method of claim 1 , wherein the object detection engine is integrated with the image signal processing pipeline in an embedded image processor.

3. The method of claim 1 , wherein the object detection engine receives raw digital video from an image sensor and analyses the raw digital video on a frame by frame basis.

4. The method of claim 1 , wherein the object detection engine outputs data for each video frame describing:
a pose of one or more detected persons;
a location or coordinates of the one or more detected persons; and
a location or coordinates of at least one body part of the one or more detected persons.

5. The method of claim 1 , comprising:
extracting a thumbnail image from the video, the thumbnail image comprising a face of the detected person; and
sending a text alert to an end user, the text alert comprising the thumbnail, wherein the end user can choose to access a live video feed.

6. The method of claim 5 , comprising sending the alert responsive to determining, based on pre-defined rules, that the detected person is not an allowed person.

7. The method of claim 1 , wherein modifying the behaviour of the encoder comprises modifying one or more of:
compression ratio;
quantization;
output resolution; and
frame rate.

8. An embedded image processor comprising an object detection engine, the embedded image processor configured to:
acquire a video;
use the object detection engine to detect a person in the video, the object detection engine being integrated with an image signal processing pipeline;
use an encoder to compress the acquired video;
modify the behaviour of the encoder based on an output of the object detection engine;
transmit the compressed video over a network;
determine, by analysing the acquired video prior to or during transmission of the compressed video over the network, that the detected person has moved less than a pre-set distance; and
responsive to the determining, pause the transmission of the compressed video over the network.

9. The embedded image processor of claim 8 , wherein the object detection engine is integrated with the image signal processing pipeline in the embedded image processor.

10. The embedded image processor of claim 8 , wherein the object detection engine receives raw digital video from an image sensor and analyses the raw digital video on a frame by frame basis.

11. The embedded image processor of claim 8 , wherein the object detection engine outputs data for each video frame describing:
a pose of one or more detected persons;
a location or coordinates of the one or more detected persons; and
a location or coordinates of at least one body part of the one or more detected persons.

12. The embedded image processor of claim 8 , further configured to:
extract a thumbnail image from the video, the thumbnail image comprising a face of the detected person; and
send a text alert to an end user, the text alert comprising the thumbnail, wherein the end user can choose to access a live video feed.

13. The embedded image processor of claim 12 , further configured to send the alert responsive to determining, based on pre-defined rules, that the detected person is not an allowed person.

14. The embedded image processor of claim 8 , wherein the object detection engine and the image signal processing pipeline:
are integrated with a graphics processing unit or a system on a chip; or
form part of the graphics processing unit or the system on the chip.

15. The embedded image processor of claim 8 , wherein modifying the behaviour of the encoder comprises modifying one or more of:
compression ratio;
quantization;
output resolution; and
frame rate.

Assignees

• Apical Ltd
• Advanced Risc Mach Ltd

Inventors

• Romanenko Ilya
• Tusch Michael

Classifications

• H04N5/14

  Picture signal circuitry for video frequency region (cameras or camera modules comprising electronic image sensors, or control thereof H04N23/00) · CPC title

• H04N19/167

  Position within a video image, e.g. region of interest [ROI] · CPC title

• G06V10/25

  Determination of region of interest [ROI] or a volume of interest [VOI] · CPC title

• H04N19/503

  involving temporal prediction (adaptive coding with adaptive selection between spatial and temporal predictive coding H04N19/107; adaptive coding with adaptive selection among a plurality of temporal predictive coding modes H04N19/109) · CPC title

• H04N19/115

  Selection of the code volume for a coding unit prior to coding · CPC title