Detection devices and methods for detecting regions of interest

Patent metadata

Field	Value
Publication number	US-9892336-B2
Application number	US-201514907032-A
Country	US
Kind code	B2
Filing date	May 15, 2015
Priority date	May 16, 2014
Publication date	Feb 13, 2018
Grant date	Feb 13, 2018

Abstract

A detection method and a detection device for detection of at least one region of interest (ROI) using the same are provided. A plurality of successive frames is captured by an image sensor. A first frame among the plurality of successive frames is divided into a plurality of sub regions. A first vital-sign feature of a first sub region among the plurality of sub regions is obtained. A first feature signal is generated according to the first vital-sign feature. Whether the first feature signal is a first valid image signal is determined. When it is determined that the first feature signal is a first valid image signal, the first sub region is identified as a first ROI. In the frames occurring after the first frame, the first ROI is tracked.

First claim

What is claimed is:

1. A detection device for detecting at least one region of interest (ROI) in a first frame captured by an image sensor:
an image processing module to divide the first frame into a plurality of sub regions;
a calculation module to obtain a first vital-sign feature of a first sub region among the plurality of sub regions to generate a first feature signal; and
an identification module to receive the first feature signal and determine whether the first feature signal is a first valid image signal,
wherein when the identification module determines the first feature signal is the first valid image signal, the identification module identifies the first sub region as a first ROI.

2. The detection device as claimed in claim 1 , wherein the image processing module divides the first frame into the plurality of sub regions by pixel configuration of the image sensor, a plurality of quadrangles, a plurality of polygons, or a plurality of circles.

3. The detection device as claimed in claim 1 , wherein the image processing module divides the first frame into the plurality of sub regions according to color difference or edge appearance shown in the first frame.

4. The detection device circuit as claimed in claim 1 , wherein each of the sub regions corresponds to an object, and, in a predetermined time-interval occurring after the first frame is captured, a shape or position of one sub region is changed by tracking the corresponding object.

5. The detection device as claimed in claim 1 , wherein the calculation module performs a specific operation on a sensing signal of the first sub region within a predetermined time-interval occurring after the first frame is captured to obtain the first vital-sign feature, and the first feature signal is estimated according to the first vital-sign feature.

6. The detection device as claimed in claim 5 , wherein the calculation module performs the specific operation on the sensing signal to extract an average value of at least one color component of the first frame to serve as the first vital-sign feature.

7. The detection device as claimed in claim 1 , wherein the first vital-sign feature is related to heart rates, respiration rates, or blood-oxygen content of human beings.

8. The detection device as claimed in claim 1 , wherein the identification module assesses quality of the first feature signal and determines whether the first feature signal is the first valid image signal according to an assessment result.

9. The detection device as claimed in claim 1 , wherein the identification module compares the first feature signal with a predetermined reference signal and determines whether the first feature signal is the first valid image signal according to a comparison result.

10. The detection device as claimed in claim 9 , wherein when a difference between the first feature signal and the predetermined reference signal is within a reference range, the identification module determines that the first feature signal is a first valid image signal, and when the difference between the first feature signal and the predetermined reference signal is outside the reference range, the identification module determines that the first feature signal is not the valid image signal.

11. The detection device circuit as claimed in claim 1 ,
wherein the calculation module obtains a second vital-sign feature of a second sub region among the plurality of sub regions to generate a second feature signal, and the identification module receives the second feature signal and determines whether the second feature signal is a second valid image signal, and
wherein when the identification module determines the second feature signal is the second valid image signal and the second sub region is adjacent to the first sub region, the identification module merges the first sub region and the second sub region to form a merged region and identifies the merged region as the first ROI.

12. The detection device circuit as claimed in claim 1 ,
wherein the calculation module obtains a second vital-sign feature of a second sub region among the plurality of sub regions to generate a second feature signal, and the identification module receives the second feature signal and determines whether the second feature signal is a second valid image signal,
wherein when the identification module determines the second feature signal is the second valid image signal and the second sub region is separated from the first sub region, the identification module identifies the second sub region as a second ROI.

13. A detection method for detecting at least one region of interest (ROI):
capturing a plurality of successive frames;
dividing a first frame among the plurality of successive frames into a plurality of sub regions;
obtaining a first vital-sign feature of a first sub region among the plurality of sub regions generating a first feature signal according to the first vital-sign feature;
determining whether the first feature signal is a first valid image signal;
when it is determined that the first feature signal is the first valid image signal, identifying the first sub region as a first ROI; and
tracking the first ROI in the frames occurring after the first frame.

14. The detection method as claimed in claim 13 , wherein in the step of dividing the first frame into the plurality of sub regions, the first frame is divided by pixel configuration of the image sensor, a plurality of quadrangles, a plurality of polygons, or a plurality of circles.

15. The detection method as claimed in claim 13 , wherein in the step of dividing the first frame into the plurality of sub regions, the first frame is divided according to color difference or edge appearance shown in the first frame.

16. The detection method circuit as claimed in claim 13 , wherein each of the sub regions corresponds to an object, and, in a predetermined time-interval occurring after the first frame is captured, a shape or position of one sub region is changed by tracking the corresponding object.

17. The detection method as claimed in claim 13 , wherein in the step of obtaining the first vital-sign feature of the first sub region, a specific operation is performed to a sensing signal of the first sub region within a predetermined time-interval occurring after the first frame is captured to obtain the first vital-sign feature.

18. The detection method as claimed in claim 17 , wherein the specific operation is performed to the sensing signal to extract an average value of at least one color component of the first frame to serve as the first vital-sign feature.

19. The detection method as claimed in claim 13 , wherein the first vital-sign feature is related to heart rates, respiration rates, or blood-oxygen content of human beings.

20. An image tracking apparatus comprising:
an image sensor to capture a plurality of successive frames;
a detection device to perform a detection operation on the successive frames by dividing one frame into a plurality of sub regions, obtain at least one vital-sign feature of at least one sub region among the plurality of sub regions to generate at least one feature signal, and determine whether the at least one feature signal is valid, wherein when the detection device determines that the at least one feature signal is valid, the detection device identifies the at least one sub region as a region of interest (ROI); and
a tracking module to track the ROI in the frames occurring after the one frame.

Assignees

• Mediatek Inc

Inventors

• Chen Yu Ting
• Chen Tung Chien

Classifications

• G06T7/0016 Primary

  involving temporal comparison · CPC title

• G06V10/25

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

• G06K9/3233 Primary

  Physics · mapped topic

• G06T7/11

  Region-based segmentation · CPC title

• G06T2207/30196

  Human being; Person · CPC title