Multi-Camera Line-of-Sight Data Collection With 3D Coordinate Alignment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing line-of-sight direction data collection methods suffer from low efficiency and accuracy, with restrictions on data collection location and poor accuracy due to the use of single collection methods and depth camera field angles.
Innovation Solution
Collect object and facial images using multiple depth cameras, determine three-dimensional coordinates for objects and eyes, and align these coordinates across camera systems to calculate line-of-sight direction data, utilizing external parameter matrices for calibration when necessary.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a single collection method is used, then the device complexity is reduced, but the data collection efficiency deteriorates
Solution Approach 1:
The patent combines multiple depth cameras (first depth camera and second depth camera) into a unified data collection system. The first depth camera collects object images and determines object three-dimensional coordinates, while the second depth camera collects facial images and determines eye three-dimensional coordinates. By merging these multiple collection channels, the system achieves simultaneous collection of multiple line-of-sight direction data points, thereby improving data collection efficiency without requiring complex coordinate transformation calculations.
2Measurement precision
If a single depth camera is used, then the device complexity is reduced, but the measurement precision deteriorates
Solution Approach 1:
The patent segments the data collection function into two specialized depth cameras: the first depth camera is dedicated to collecting object images and determining object three-dimensional coordinates, while the second depth camera is dedicated to collecting facial images and determining eye three-dimensional coordinates. This segmentation allows each camera to be optimized for its specific function, improving the overall measurement precision of line-of-sight direction data while maintaining manageable device complexity through clear functional division.
3Adaptability or versatility
If the field angle of the depth camera is limited, then the device complexity is reduced, but the adaptability deteriorates
Solution Approach 1:
The patent transitions from a single-camera perspective to a multi-camera spatial arrangement, utilizing different spatial dimensions and angles. The first depth camera and second depth camera are positioned at different locations and orientations, allowing the system to collect data from multiple viewpoints simultaneously. This dimensional expansion overcomes the field angle limitations of individual cameras and provides greater flexibility in data collection locations without requiring overly complex camera arrangements.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Disclosed are a method for collecting line-of-sight direction data, an apparatus, a device and a storage medium. The method includes: collecting an object image of a target object through a first depth camera, and determining an object three-dimensional coordinate of the target object under a first depth camera coordinate system based on the object image, the target object is an object a user stares at; collecting a facial image of the user through a second depth camera, and determining an eye three-dimensional coordinate of the user under a second depth camera coordinate system based on the facial image; determining an object coordinate of the object three-dimensional coordinate and an eye coordinate of the eye three-dimensional coordinate under each collection camera coordinate system; and determining line-of-sight direction data of the user based on the object coordinate and the eye coordinate under each collection camera coordinate system.