AR Scan Distance Guidance for Machine Learning Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing augmented reality systems struggle to accurately superimpose virtual objects on a real-world environment by determining the correct scanning distance for object recognition, leading to inefficiencies in identifying objects using machine learning models.
Innovation Solution
A smart device application uses a machine learning model to determine the optimal scan distance by displaying a reticle on the user interface, guiding the user to adjust their position relative to the object, and automatically capturing images when within the optimal range, while considering factors like object size, camera field of view, and sensor data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the scanning distance is not accurately determined, then the augmented reality object placement is incorrect, but the system complexity increases due to multiple sensors and processing requirements
Solution Approach 1:
The patent replaces complex mechanical measurement systems with computational methods. Instead of using multiple physical sensors to directly measure distance, the system uses the camera's field of view and image processing algorithms to calculate scanning distance, thereby reducing hardware complexity while maintaining measurement precision
Solution Approach 2:
The patent introduces an intermediary computational layer that processes visual information from the camera. This intermediary system uses image analysis and geometric calculations to derive distance information, acting as a mediator between the simple camera input and the complex augmented reality placement requirements
2Reliability
If the image detail is insufficient for machine learning model recognition, then object identification accuracy decreases, but the scanning distance range becomes more restricted
Solution Approach 1:
The patent implements dynamic adjustment of scanning distance ranges based on real-time image quality assessment. The system continuously monitors image detail sufficiency and adapts the acceptable distance range accordingly, allowing flexible operation across varying conditions while maintaining identification accuracy
Solution Approach 2:
The patent changes the parameter of scanning distance range dynamically based on image detail quality. When image details are sufficient, the system expands the acceptable distance range; when details are insufficient, it restricts the range, thereby maintaining reliability while maximizing adaptability
3Measurement precision
If manual positioning is required to achieve optimal scan distance, then measurement precision improves, but ease of operation decreases
Solution Approach 1:
The patent implements a feedback mechanism that provides real-time guidance to users about their scanning distance. The system analyzes image quality and communicates whether the user is at the optimal distance, giving continuous feedback that enables precise measurement while keeping operation simple through intuitive cues
Solution Approach 2:
The patent enables the system to self-adjust and self-guide the positioning process. Through automated image analysis and real-time feedback provision, the system serves itself by determining optimal scan parameters and guiding the user without requiring manual intervention for precise positioning
Data Source
AI summary
A smart device is provided with an application program for displaying a video feed received from the smart device's camera. The application can determine the coordinates for an intersection point, which is a point on the ground where the smart device is pointing at. The application can display a target on the visual representation of the intersection point. Based on whether the smart device is at an appropriate distance from the intersection point, the user interface can superimpose an indicator on the video feed received from the camera. This can inform the user whether the smart device is at an optimal scan distance from the intersection point (or an object) so that the object can be identified by a machine learning model.