3D Glasses Detection for Augmented Reality Rendering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing 3D television systems require users to wear dedicated glasses to observe stereoscopic images, limiting the glasses' application to only image observation and not exploring new uses.
Innovation Solution
An image processing apparatus that includes an image pickup unit, glasses identifying unit, face detector, and augmented-reality special rendering unit to detect facial regions and add virtual features, allowing the glasses to serve as a landmark for augmented reality rendering and communication systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If dedicated glasses are used to observe stereoscopic images, then stereoscopic vision is achieved, but the application scope of the glasses is limited
Solution Approach 1:
The patent extends the functionality of dedicated 3D glasses from solely observing stereoscopic images to also serving as landmarks for augmented reality rendering. The glasses identifying unit detects the glasses worn by the user, and the augmented-reality special rendering unit uses this detection to add virtual features, thereby making the glasses a multi-functional device that combines stereoscopic observation with AR interaction capabilities
2Adaptability or versatility
If the glasses are used only for observing stereoscopic images, then the observation function is reliable, but new fields of application cannot be explored
Solution Approach 1:
The patent introduces an intermediary approach by using the glasses themselves as a detectable landmark object. The glasses identifying unit detects the glasses as an intermediary element, and this detection serves as the basis for the augmented-reality special rendering unit to add virtual features. This intermediary mechanism enables new applications without requiring fundamentally new hardware, only additional processing capabilities
3Measurement precision
If facial region detection is performed without using glasses as reference, then detection can be done on any face, but detection accuracy and stability decrease
Solution Approach 1:
The patent applies local quality by using the glasses as a specific reference point on the face. Instead of attempting to detect facial regions on any face without reference, the system uses the uniquely identifiable glasses as a localized anchor point. The glasses identifying unit detects the glasses first, and the face detector then uses this detected glasses position as a reference to accurately locate the facial region, improving detection precision through this localized reference approach
Data Source
AI summary
Methods and apparatus provide for: capturing an image of an object, which includes a face of a person wearing an optical display apparatus by which to observe a stereoscopic image that contains a first parallax image and a second parallax image obtained when the object in a three-dimensional (3D) space is viewed from different viewpoints; identifying the optical display apparatus included in the image of the object; and generating an image of the face of the person that does not include the optical display apparatus by excluding the identified optical display apparatus, and instead by adding features of the face of the person to a region in which the identified optical display apparatus is excluded.