Super Resolution on Compressed Image Sequences for Embedded Devices

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Embedded devices, such as mobile phones and cameras, face processor and memory limitations that prevent the real-time application of super resolution techniques to produce higher resolution images due to the large size of raw, uncompressed images, leading to offline processing and inability to display high-resolution images on lower resolution screens.

Innovation Solution

Implementing a method to perform super resolution on compressed image sequences using video compression techniques, specifically employing lossless or near-lossless video compression and motion vector estimation to generate higher resolution images directly on embedded devices without fully decoding lower resolution images.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If super resolution technique is applied to raw uncompressed images, then higher resolution images can be generated, but memory and processor resources are excessively consumed

Engineering Contradiction:

Improveimage resolutionVSAvoidmemory consumption

Core Design Contradiction:

Measurement precisionVSQuantity of substance

Solution Approach 1:

The patent applies video compression to the image sequence before performing super resolution processing. By pre-compressing the images using motion estimation and compensation, the patent reduces the amount of data that needs to be processed, thereby decreasing memory and processor resource consumption while still enabling super resolution to generate higher resolution images

Inventive Principle:

Principle #10Preliminary action

2Measurement precision

If super resolution technique is applied to raw uncompressed images, then higher resolution images can be generated, but processor resources are excessively consumed

Engineering Contradiction:

Improveimage resolutionVSAvoidprocessor resources

Core Design Contradiction:

Measurement precisionVSPower

Solution Approach 1:

The patent applies video compression to the image sequence before performing super resolution processing. By pre-compressing the images using motion estimation and compensation, the patent reduces the amount of data that needs to be processed, thereby decreasing processor resource consumption while still enabling super resolution to generate higher resolution images

Inventive Principle:

Principle #10Preliminary action

3Measurement precision

If images are saved offline for super resolution processing, then super resolution can be performed, but real-time high resolution display is not possible

Engineering Contradiction:

Improveimage resolutionVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent applies video compression to the image sequence before performing super resolution processing. By pre-compressing the images using motion estimation and compensation, the patent reduces the amount of data that needs to be processed, thereby decreasing processing time and enabling real-time super resolution processing and display

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS8374444B2Method and apparatus for providing higher resolution images in an embedded device

Publication Date: 2013.02.12 SONY GROUP CORP

AI summary

A method and apparatus to providing higher resolution images on an embedded device by performing a super resolution technique on a compressed image sequence and one or more motion vectors are described. In one example, the method includes compressing an image sequence using a video compression technique, wherein the image sequence comprises a plurality of lower resolution images and applying a super resolution technique to the compressed image sequence to generate a higher resolution image.