Object Height Measurement Using Colored Shadows and Inverted Camera

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Object recognition systems face challenges in distinguishing individual objects in close proximity or overlapping, especially when using machine vision systems that view objects from above or through optically-transmissive surfaces, due to issues with shadow detection and computational power requirements.

Innovation Solution

A system utilizing a combination of colored light sources, a color imaging system, and a diffuse or switchable reference surface to minimize shadows, detect object boundaries, and calculate object heights using trigonometric relationships, allowing for efficient detection and recognition of objects based on their shadows and identifying characteristics.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Difficulty of detecting and measuring

If machine vision systems view objects from above or through optically-transmissive surfaces, then object recognition can be performed, but shadow detection becomes difficult and computational power requirements increase

Engineering Contradiction:

Improveshadow detection difficultyVSAvoidcomputational power requirements

Core Design Contradiction:

Difficulty of detecting and measuringVSPower

Solution Approach 1:

The patent inverts the traditional overhead viewing approach by placing the camera below the optically-transmissive surface, viewing objects from underneath. This inversion allows direct detection of shadows cast on the surface from below, eliminating the shadow detection difficulties and reducing computational requirements for boundary determination.

Inventive Principle:

Principle #13The other way round (Inversion)

Solution Approach 2:

The optically-transmissive surface acts as an intermediary element that enables the camera to view objects from below while still capturing their visual characteristics. This mediator allows shadow detection without requiring direct overhead access to the objects, solving the contradiction between viewing angle and shadow detection capability.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If traditional overhead machine vision is used, then objects can be viewed, but determining individual boundaries of multiple items in close proximity requires significant computational power

Engineering Contradiction:

Improveobject boundary determination accuracyVSAvoidcomputational power

Core Design Contradiction:

Measurement precisionVSPower

Solution Approach 1:

By inverting the viewing direction to below the surface, the system captures shadows that naturally delineate object boundaries. This approach simplifies boundary determination for closely-spaced objects, achieving high measurement precision with reduced computational power compared to overhead viewing methods.

Inventive Principle:

Principle #13The other way round (Inversion)

3Device complexity

If a single light source is used, then illumination is simple, but shadow confusion occurs when objects are in close proximity or overlapping

Engineering Contradiction:

Improveillumination system complexityVSAvoidobject distinction accuracy

Core Design Contradiction:

Device complexityVSReliability

Solution Approach 1:

The illumination system is segmented into multiple light sources positioned at different locations below the surface. Each light source creates distinct shadow patterns that, when combined, provide sufficient information to distinguish individual objects even when they are in close proximity or overlapping, thereby improving object distinction accuracy.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Multiple shadow images captured from different light source positions are merged into a single composite view. This combining of multiple perspectives allows the system to reliably distinguish individual objects and their boundaries, overcoming the limitations of single-light-source illumination while maintaining manageable system complexity.

Inventive Principle:

Principle #5Merging (Combining)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This approach improves object boundary detection, reduces computational requirements, and enables effective recognition of objects by minimizing shadow confusion and reducing the need for 3D cameras, while allowing for the identification of characteristics like barcodes and colors.

Implementation Method 1

The system first uses a broad, extended source comprised of many individual light sources to minimize shadows of the items on the reference surface

Methodology Applied

Scientific EffectLight scattering: Scattering

Implementation Method 2

the system uses a red, green, and blue triplet of light sources to form three different colored shadows of each item on the reference surface

Methodology Applied

Scientific EffectShadow formation: Shadow

Data Source

PatentUS10909713B2System and method for item location, delineation, and measurement

Publication Date: 2021.02.02 DATALOGIC USA INC

AI summary

A location, dimension, and height of an object can be determined and measured using shadows. The object is located on a surface and an array of lights is mounted over the surface and shines on the object. The surface can be switchable between a translucent state and a transparent state. A colored shadow occurs based on the color of the light that shines on the object, where red, green, and blue are the typical colors used to provide shadows. A camera that is located below the surface captures an image of the shadows. The camera can be a color camera or a monochrome camera. The image is processed using thresholding to segment the different types of shadows that can occur. With the shadows, calculations can be made to determine the location, dimension, and height of the object.