Camera-Based Volume Detection for Home Appliance Load Estimation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Home appliances struggle to accurately determine the amount and attributes of objects being treated, such as laundry or food, due to limitations in weight and volume measurement, leading to ineffective treatment processes.

Innovation Solution

A home appliance equipped with a camera and neural network model that recognizes characteristic shapes within the container to estimate the amount of the object, using pre-trained images to differentiate between visible and hidden features, and combines this with weight data to determine density and select appropriate treatment modes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If weight sensors are used to detect the amount of laundry, then the weight measurement is improved, but the volume measurement capability deteriorates

Engineering Contradiction:

Improveweight measurementVSAvoidvolume measurement capability

Core Design Contradiction:

Measurement precisionVSVolume of moving object

Solution Approach 1:

The invention separates weight measurement (performed by weight sensors) and volume measurement (performed by camera-based image processing) as independent functions. The camera captures images of the container interior and processes them to estimate volume, while weight sensors simultaneously measure mass. This segmentation allows each measurement type to be optimized independently without interfering with the other.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The invention introduces image processing algorithms as an intermediary method to estimate volume from camera images. Instead of relying solely on weight sensors, the system uses computer vision technology to analyze the spatial occupation of objects in the container, providing volume information that complements the weight measurement data.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Volume of moving object

If object recognition is attempted to determine volume, then volume measurement is improved, but recognition accuracy deteriorates when object cannot be separated from background

Engineering Contradiction:

Improvevolume measurementVSAvoidrecognition accuracy

Core Design Contradiction:

Volume of moving objectVSMeasurement precision

Solution Approach 1:

The invention replaces traditional object recognition methods that rely on separating objects from backgrounds with a spatial occupation analysis approach. Instead of attempting to segment and identify individual objects, the system analyzes the overall spatial occupation within the container by processing camera images to determine volume, eliminating the need for object-background separation.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

Instead of trying to identify objects by separating them from the background, the invention inverts the approach by analyzing what the objects occupy in terms of space. The system determines volume by measuring the spatial occupation directly from images, rather than by identifying and segmenting individual objects against the background.

Inventive Principle:

Principle #13The other way round (Inversion)

3Ease of operation

If only weight-based treatment determination is used, then control simplicity is improved, but treatment appropriateness deteriorates due to inability to grasp object properties

Engineering Contradiction:

Improvecontrol simplicityVSAvoidtreatment appropriateness

Core Design Contradiction:

Ease of operationVSReliability

Solution Approach 1:

The invention merges weight measurement and volume measurement into a unified control system. Both parameters are simultaneously acquired and integrated to determine object properties such as density, enabling more appropriate treatment decisions while maintaining automated control simplicity. The system combines multiple measurement modalities to achieve comprehensive object characterization.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The control system is designed to handle multiple measurement types (weight and volume) and multiple object properties (mass, volume, density) through a single integrated processing unit. This multi-functional approach allows the system to adapt to different object types and treatment requirements while maintaining a unified control interface and decision-making process.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS11634849B2Home appliance and method for controlling home appliance

Publication Date: 2023.04.25 LG ELECTRONICS INC

AI summary

A home appliance and a control method for the home appliance, which is operable in an IoT environment through a 5G communication network and uses a neural network model generated according to machine learning is provided. The home appliance may include a home appliance main body; a container mounted within the home appliance main body to accommodate a treatment target; a camera arranged to photograph the inside of the container; and one or more processors configured to control an operation of the home appliance, wherein the processor is configured to determine an amount of a treatment target based on feature shapes of the container identified in an image of the inside of the container photographed by the camera.