Optical Camera Communication Frame Correction via Machine Learning

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Optical camera communication (OCC) systems face issues with missing frames due to asynchronous sampling frame rates between cameras and IoT devices, leading to incomplete data transmission.

Innovation Solution

An electronic device equipped with a processor, storage medium, and capturing device uses machine learning models to predict missing timestamps and generate complement frames, ensuring complete data transmission by inputting optical signals into machine learning models to correct frame asynchrony.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If the transmitter transmits optical signals with a higher frequency to improve data transmission efficiency, then the data transmission efficiency is improved, but the sampling frame rate of the camera becomes floating or skewed over time, causing asynchrony and missing frames

Engineering Contradiction:

Improvedata transmission efficiencyVSAvoidframe synchronization

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The system performs preliminary actions by detecting timestamp information in advance and predicting missing timestamps before data transmission completes. The machine learning model predicts missing timestamps proactively, allowing the system to prepare compensation measures ahead of time, thus resolving the asynchrony issue without compromising high-frequency transmission

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements feedback mechanisms by using detected timestamp information to train machine learning models that predict missing timestamps. The model continuously learns from timestamp patterns and provides feedback to the frame synchronization process, enabling dynamic adjustment and maintaining reliability during high-frequency transmission

Inventive Principle:

Principle #23Feedback

2Adaptability or versatility

If the camera sampling frame rate changes over time, then the camera can adapt to different conditions, but asynchrony between the camera and transmitter occurs, resulting in missing frames in the received optical signal

Engineering Contradiction:

Improvecamera frame rate adaptabilityVSAvoidmissing frames

Core Design Contradiction:

Adaptability or versatilityVSLoss of information

Solution Approach 1:

The system handles parameter changes by detecting timestamp information that reflects camera frame rate variations. Machine learning models analyze these timestamp parameters to predict missing frames, allowing the system to adapt to changing camera conditions while preventing information loss through intelligent compensation

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

Timestamp information serves as an intermediary between the camera's variable frame rate and the data transmission process. The machine learning model uses timestamps as intermediate data to predict missing frames, bridging the asynchrony gap and preventing information loss without restricting camera adaptability

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS11758286B1Method and electronic device of correcting frame for optical camera communication

Publication Date: 2023.09.12 WISTRON CORP

AI summary

A method and an electronic device of correcting frame for an optical camera communication (OCC) are provided. The method includes the following steps. The optical signal is captured. The optical signal is input to a first machine learning (ML) model to obtain a missing timestamp. The optical signal and the missing timestamp are input to a second ML model to obtain a first complement frame corresponding to the missing timestamp. The first complement frame is outputted.