Image processing method and electronic device implementing the same

Patent metadata

Field	Value
Publication number	US-9767360-B2
Application number	US-201514717266-A
Country	US
Kind code	B2
Filing date	May 20, 2015
Priority date	May 29, 2014
Publication date	Sep 19, 2017
Grant date	Sep 19, 2017

Abstract

An image processing method and an electronic device implementing the method are provided. The method includes the electronic device sequentially receiving an image captured by a camera and determining whether a frame of the received image satisfies a predetermined condition. If the predetermined condition is satisfied, the electronic device recognizes an object in the frame. Then the electronic device tracks the object in the frame through tracking data created based on a feature extracted from the recognized object.

First claim

What is claimed is:

1. An image processing method comprising:
determining, by a processor, whether a motion value corresponding to a current frame captured by a camera is less than a first motion value and a motion value corresponding to a previous frame captured by the camera is greater than the first motion value;
determining, by the processor, if the motion value corresponding to the current frame is not less than the first motion value and the motion value corresponding to the previous frame is not greater than the first motion value, whether an image variation value related to the current frame is less than a first image variation value and an image variation value related to the previous frame is greater than the first image variation value;
determining, by the processor, if the image variation value related to the current frame is less than the first image variation value and the image variation value related to the previous frame is greater than the first image variation value, whether at least one object exists in the current frame and in the previous frame;
recognizing, by the processor, if the at least one object exists in the current frame and in the previous frame, a feature of the at least one object in the current frame; and
tracking, by the processor, based on the feature, at least one object in subsequent frames sequentially captured by the camera.

2. The method of claim 1 ,
wherein the determining of whether the image variation value related to the current frame is less than the first image variation value and the image variation value related to the previous frame is greater than the first image variation value comprises:
measuring an image variation value between the current frame and the previous frame as the image variation value related to the current frame:
measuring an image variation value between the current frame and other frames before the previous frame as the image variation value related to the previous frame;
determining whether the image variation value related to the current frame is less than the first image variation value; and
determining whether the image variation value related to the previous frame is the greater than the first image variation value.

3. The method of claim 1 , wherein the tracking of the at least one object in the frames comprises:
extracting at least one feature point of the at least one object;
transmitting the at least one extracted feature point to a server;
receiving tracking data corresponding to the at least one extracted feature point from the server; and
tracking the at least one object in the frames based on the tracking data.

4. The method of claim 3 ,
wherein the tracking of the at least one object in the frames comprises determining, after extracting the at least one feature point of the at least one object, whether a density value of the at least one extracted feature point is greater than a first density value, and
wherein the at least one extracted feature point is transmitted to the server when the density value is greater than the first density value.

5. The method of claim 1 , wherein the tracking of the at least one object in the frames is performed after calculating at least one of an initial location of the at least one object and a posture of the at least one object.

6. The method of claim 1 ,
wherein the at least one object comprises a plurality of objects,
wherein the tracking of the at least one object in the frame comprises:
setting a synchronous trackable number for tracking the plurality of objects, and
comparing a number of the plurality of objects with the synchronous trackable number, and

wherein, if the number of the plurality of objects is less than the synchronous trackable number, a recognition mode is performed to further recognize other objects together with a tracking mode for tracking the plurality of objects up to the synchronous trackable number.

7. The method of claim 6 ,
wherein the tracking mode comprises tracking the at least one object by using the tracking data received from a server, and
wherein the recognition mode comprises:
determining whether the motion value corresponding to the current frame captured by the camera is less than the first motion value and the motion value corresponding to the previous frame captured by the camera is greater than the first motion value,
recognizing the other objects, if the motion value corresponding to the current frame is less than the first motion value and the motion value corresponding to the previous frame is greater than the first motion value, and
tracking the at least one object and the other objects in the subsequent frames through the tracking data.

8. An electronic device comprising:
a sensor configured to measure a motion of the electronic device;
an input device comprising a camera configured to receive frames of at least one object;
a memory configured to store data about the motion of the electronic device;
a display configured to display the frames;
a wireless communication device configured to communicate with a server; and
at least one processor configured to control the sensor, the input device, the memory, the display, and the wireless communication device,
wherein the at least one processor is further configured to:
determine whether a motion value corresponding to a current frame captured by a camera is less than a first motion value and a motion value corresponding to a previous frame captured by the camera is greater than the first motion value;
determine, if the motion value corresponding to the current frame is not less than a first motion value and the motion value corresponding to the previous frame is not greater than the first motion value, whether an image variation value related to the current frame is less than a first image variation value and an image variation value related to the previous frame is greater than the first image variation value;
determine, if the image variation value related to the current frame is less than a first image variation value and the image variation value related to the previous frame is greater than the first image variation value, whether at least one object exists in the current frame and in the previous frame;
recognize, if the at least one object exists in the current frame and in the previous frame, a feature of the at least one object in the current frame; and
track, based on the feature, the at least one object in subsequent frames sequentially captured by the camera.

9. The electronic device of claim 8 ,
wherein, to determine whether an image variation value related to the current frame is less than a first image variation value and an image variation value related to the previous frame is greater than the first image variation value, the at least one processor is further configured to:
measure an image variation value between the current frame and the previous frame as the image variation value related to the current frame:
measure an image variation value between the current frame and other frames before the previous frame as the image variation value related to the previous frame; and
determine whether the image variation value related to the current frame is less than the first image variation value; and
determine whether the image variation value related to the previous frame is the greater than the first image variation value.

10. The electronic device of claim 8 , wherein the at least one processor is further configured to:
extract at least one feature point of the at least one object,
transmit the at least one extracted feature point to the server through the wireless communication device,
receive the tracking data correspondi

Assignees

• Samsung Electronics Co Ltd

Inventors

• Cho Ikhwan
• Jung Jinhe
• Hwang Minkyung
• Shin Daekyu
• Cho Kyusung
• Cho Seongho
• Jeon Yongjoon

Classifications

• G06T7/246 Primary

  using feature-based methods, e.g. the tracking of corners or segments · CPC title

• G06K9/00624 Primary

  Physics · mapped topic

• G06K9/4604

  Physics · mapped topic

• G06T2207/10016

  Video; Image sequence · CPC title