IP Library Granted Patent US 10,356,311
Granted Patent B2
US 10,356,311 · App. 15/894,944 · Granted Jul 16, 2019

Method and apparatus for performing image processing operation based on frame/algorithm selection

Inventors: Cheng-Tsai Ho (Taichung, TW); Ding-Yun Chen (Taipei, TW); Chi-Cheng Ju (Hsinchu, TW)
Assignee: MEDIATEK INC.
H04N5/23219G06K9/00261H04N5/23216H04N5/23241
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,356,311
App. No.
15/894,944
Granted
Jul 16, 2019
Kind
B2
Abstract

An exemplary image processing method includes the following steps: receiving an image input composed of at least one source image; receiving algorithm selection information corresponding to each source image; checking corresponding algorithm selection information of each source image to determine a selected image processing algorithm from a plurality of different image processing algorithms; and performing an object oriented image processing operation upon the source image based on the selected image processing algorithm. The algorithm selection information indicates an image quality of each source image and is generated from one of an auxiliary sensor, an image processing module of an image capture apparatus, a processing circuit being one of a video decoder, a frame rate converter, and an audio/video synchronization (AV-Sync) module, or is a user-defined mode setting.

Claims (13)

1. An image processing method, comprising:

receiving an image input in a device, wherein the image input is composed of at least one source image;

receiving algorithm selection information corresponding to each individual source image in the image input;

regarding each source image included in the image input, checking the corresponding algorithm selection information to determine a selected image processing algorithm for the corresponding individual source image from a plurality of different image processing algorithms; and

performing an object oriented image processing operation including at least one of object detection, object tracking, and object recognition upon the source image based on the selected image processing algorithm;

wherein the algorithm selection information indicates an image quality of each individual source image and is generated from one of an auxiliary sensor while the image input is generated by an image capture apparatus with an image sensor, an image processing module of an image capture apparatus while the image input is generated by the image capture apparatus, a processing circuit being one of a video decoder, a frame rate converter, and an audio/video synchronization (AV-Sync) module while the image input is also generated from the processing circuit, or is a user-defined mode setting.

2. The image processing operation of claim 1 , wherein the different image processing algorithms includes a first image processing algorithm and a second image processing algorithm; and compared to the image processing operation performed upon the source image based on the first image processing algorithm, the image processing operation performed upon the source image based on the second image processing algorithm has a reduced computation/calculation amount or lower power consumption.

3. The image processing method of claim 1 , wherein the image input includes a first source image and a second source image processed by the image processing operation based on different selected processing algorithms respectively; and the image processing method further comprises:

referring to at least a display position of an object marker of an object processed by the image processing operation in the first source image to refine a display position of an object marker of the object processed by the image processing operation in the second source image.

4. An image processing apparatus, comprising:

an image processing unit, arranged for receiving an image input in a device, wherein the image input is composed of at least one source image; and performing an object oriented image processing operation upon a source image based on a selected image processing algorithm; and

an algorithm selection unit, arranged for receiving algorithm selection information corresponding to each individual source image in the image input; and regarding each source image included in the image input, checking the corresponding algorithm selection information to determine the selected image processing algorithm from a plurality of different image processing algorithms;

wherein the algorithm selection information indicates an image quality of each individual source image and is generated from one of an auxiliary sensor while the image input is generated by an image capture apparatus with an image sensor, an image processing module of an image capture apparatus while the image input is generated by the image capture apparatus, a processing circuit being one of a video decoder, a frame rate converter, and an audio/video synchronization (AV-Sync) module while the image input is also generated from the processing circuit, or is a user-defined mode setting.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 18, 2021
From: MEDIATEK INC.
To: XUESHAN TECHNOLOGIES INC.
Reel/Frame 056593/0167 →
Continuity (2)
Division 14027238 · Sep 15, 2013
Related Publication 20180176462A1 · Jun 21, 2018