Mobile Terminal Depth Estimation Using Eye Gaze Geometry
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing devices that generate depth maps for augmented reality applications rely on dedicated depth sensors like LIDAR, increasing costs and reducing their prevalence, making them less accessible for creating depth maps in various scenes.
Innovation Solution
A method and apparatus using the front and rear cameras of a mobile terminal to estimate depth by determining angles and distances based on user gaze direction and object location, eliminating the need for dedicated depth sensors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a dedicated depth sensor like LIDAR is used to generate depth maps, then measurement precision is improved, but device cost increases
Solution Approach 1:
The patent makes the mobile terminal's existing cameras perform multiple functions: they not only capture images but also enable depth estimation through computational methods. By utilizing the front and rear cameras for both imaging and depth measurement, the system eliminates the need for a separate dedicated depth sensor, thereby reducing device cost while maintaining depth measurement capability
Solution Approach 2:
The patent replaces the mechanical/optical depth sensing system (LIDAR) with a computational approach using existing camera images. Instead of using a dedicated depth sensor hardware system, the invention uses image processing algorithms that analyze geometric relationships, angles, and distances from camera captures to calculate depth, substituting mechanical measurement with computational estimation
2Measurement precision
If a dedicated depth sensor is included, then depth estimation accuracy is improved, but ease of manufacture deteriorates
Solution Approach 1:
The patent extracts the depth estimation functionality from a separate dedicated sensor and integrates it into the existing camera system through software processing. By removing the requirement for a separate depth sensor component, the manufacturing process is simplified, and the device can be manufactured more easily using only standard camera hardware that is already present in mobile terminals
3Adaptability or versatility
If dedicated depth sensors are used, then depth map generation capability is improved, but device complexity increases
Solution Approach 1:
The patent merges the imaging function and depth estimation function into a single integrated system using the mobile terminal's existing cameras. Instead of having separate dedicated components for imaging and depth sensing, the system combines both capabilities through computational methods that process images from the available cameras, thereby reducing overall device complexity while maintaining depth map generation capability
Data Source
AI summary
The method, apparatus and computer program product estimate the depth to objects within a scene that is captured by first and second cameras of a mobile terminal. A method includes determining, based upon an image including an eye of a user captured by a first camera of a mobile terminal and an image of a scene captured by a second camera of the mobile terminal, two or more angles of a geometric shape defined by the eye, the mobile terminal and an object of the scene. Based upon the image captured by the first camera, the method also determines a first distance from the first camera to the eye. The method further estimates the depth to the object in the scene relative to the mobile terminal based upon the first distance and one or more angles of the geometric shape defined by the eye, the mobile terminal and the object.