Dual Camera Pupil Center Coordinate Acquisition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing pupil detection systems face challenges in achieving accurate and fast calculation of pupil center point coordinates, with high-resolution cameras improving accuracy but reducing speed, and low-resolution cameras improving speed but reducing accuracy.
Innovation Solution
A system utilizing a low-resolution color camera for face detection and a high-resolution infrared camera for pupil detection, where the first camera captures a face image and the second camera captures a pupil image, with a processor converting the eye region from the first image to the second image to perform pupil detection and calculate coordinates, employing image gradient matrices, adaptive thresholds, and weight matrices for accurate and efficient coordinate determination.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a high-resolution camera is used to capture face images for pupil detection, then the calculation accuracy of pupil center point coordinates is improved, but the calculation speed is reduced
Solution Approach 1:
The system divides the detection task into two segments: face detection using a low-resolution first camera and pupil detection using a high-resolution second camera. This segmentation allows each camera to be optimized for its specific task, with the first camera providing rapid face localization and the second camera delivering high-precision pupil detection, thereby resolving the contradiction between speed and accuracy
Solution Approach 2:
The system introduces an intermediary coordinate conversion process that maps the eye region from the first image to the second image. This intermediary step enables the low-resolution face detection results to be transferred to the high-resolution pupil detection domain, allowing the system to leverage both cameras' strengths without being constrained by resolution-speed trade-offs
2Productivity
If a low-resolution camera is used to capture face images for pupil detection, then the calculation speed is improved, but the calculation accuracy is reduced
Solution Approach 1:
The detection system is segmented into two functional components: a low-resolution first camera optimized for fast face detection and a high-resolution second camera optimized for accurate pupil detection. This segmentation allows the system to achieve both high speed (from the first camera) and high accuracy (from the second camera) by assigning different resolution requirements to different detection stages
Solution Approach 2:
The coordinate conversion mechanism acts as an intermediary that bridges the low-resolution face detection results with the high-resolution pupil detection capability. By converting the eye region coordinates from the first image to the second image, the system enables the low-resolution fast detection to guide the high-resolution accurate detection, thus achieving both speed and accuracy
Data Source
AI summary
A system and a method of calculating coordinates of a pupil center point are provided. The system for acquiring the coordinates of the pupil center point includes a first camera, a second camera, a storage and a processor. The first camera is configured to capture a first image including a face and output the first image to the processor, the second camera is configured to capture a second image including a pupil and output the second image to the processor, a resolution of the first camera is smaller than a resolution of the second camera, and the storage is configured to store processing data, and the processor is configured to: acquire the first image and the second image; extract a first eye region corresponding to an eye from the first image; convert the first eye region into the second image, to acquire a second eye region corresponding to the eye in the second image; and detect a pupil in the second eye region and acquire the coordinates of the pupil center point.