Dual-Pixel Sensor Skin-Color Filtering for Object Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Image sensors face interference from environmental light and background objects, which complicates the accurate detection of object images, as these interferences can obscure the object image and hinder determination.

Innovation Solution

A detection system equipped with both infrared and color pixels, where a processor generates IR and color pictures, identifies skin-color objects, and compares them to filter out non-corresponding parts of the IR image, thereby isolating the object image for improved recognition and positioning.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If the image sensor captures images using only infrared pixels, then the object image can be detected, but background interference from environmental light and non-object sources cannot be removed

Engineering Contradiction:

Improveobject image detection accuracyVSAvoidbackground interference

Core Design Contradiction:

Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

The image sensor is segmented into two distinct types of pixels: infrared pixels and color pixels. Each type processes different wavelength ranges independently, allowing the system to separate object signal detection (infrared) from background interference identification (color), thereby resolving the contradiction between detection accuracy and background interference.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The color picture serves as an intermediary component that identifies and marks background objects and environmental light sources. This intermediary information is then used to filter and remove corresponding interference from the infrared object image, enabling accurate object detection despite background interference.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Object-affected harmful factors

If the image sensor uses both infrared and color pixels, then background interference can be identified and removed, but the device complexity increases

Engineering Contradiction:

Improvebackground interference removalVSAvoidimage sensor structure

Core Design Contradiction:

Object-affected harmful factorsVSDevice complexity

Solution Approach 1:

The infrared pixels and color pixels are merged into a single integrated image sensor array, sharing common structural components such as the substrate, pixel circuits, and signal processing pathways. This merging approach enables background interference removal capability while minimizing the increase in device complexity through shared architecture.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The dual-pixel image sensor is designed with multi-functionality: the infrared pixels detect object images while the color pixels simultaneously identify background interference. Both pixel types share common processing resources and can operate independently or in combination, providing universal detection capabilities that reduce overall system complexity.

Inventive Principle:

Principle #6Universality (Multi-functionality)

3Measurement precision

If the processor compares skin-color objects with IR object images, then accurate object isolation is achieved, but the processing time and computational complexity increase

Engineering Contradiction:

Improveobject image isolation accuracyVSAvoidimage processing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The processor performs preliminary segmentation of the infrared image into candidate object regions based on intensity thresholds and shape characteristics before comparing with color picture information. This preliminary action reduces the computational scope of the subsequent skin-color matching, thereby maintaining high isolation accuracy while reducing processing time.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The comparison between skin-color objects and infrared object images is applied selectively only to regions identified as potential objects, rather than processing the entire image. This partial action approach maintains high object isolation accuracy for relevant regions while minimizing unnecessary computational overhead and processing time.

Inventive Principle:

Principle #16Partial or excessive action

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 effectively removes background interference, enhancing the accuracy of object detection and gesture recognition by isolating the object image from environmental light and background noise.

Implementation Method 1

An image sensor usually has a plurality of sensing elements, which can convert light into voltages

Methodology Applied

Scientific EffectPhotoelectric effect: Photoelectric Effect

Implementation Method 2

The image sensor includes infrared pixels and color pixels and is configured to output a picture

Methodology Applied

Scientific EffectInfrared radiation detection: Infrared Radiation

Data Source

PatentUS10803625B2Detection system and picturing filtering method thereof

Publication Date: 2020.10.13 PIXART IMAGING INC

AI summary

A detection system including a light source, an image sensor and a processor is provided. The light source is configured to illuminate an object. The image sensor is configured to output a picture. The processor is configured to generate an IR picture and a color picture according to the picture captured by the image sensor, identify a skin-color object in the color picture and determine an object image in the IR picture according to the skin-color object.