Multi-Directional Depth Bounding Box for AR Object Measurement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional electronic devices struggle to accurately measure the size of real-world objects using augmented reality technology, as they rely on user input for point selection, which can be inaccurate and laborious.
Innovation Solution
An electronic device equipped with a processor, memory, and sensors (ToF and RGB image sensors) generates depth information from multiple directions, creates point clouds, and combines bounding boxes to display the object's size accurately, guiding the user for improved measurement precision.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional point selection method is used for object size measurement, then user can obtain size information, but measurement accuracy deteriorates due to user input errors and laborious operation
Solution Approach 1:
The system performs automatic object size measurement without requiring user input for point selection. The electronic device autonomously captures images, processes depth information, generates point clouds, and calculates bounding boxes to determine object dimensions, eliminating the need for manual point selection while maintaining high measurement accuracy
Solution Approach 2:
The patent replaces the manual mechanical point-selection process with an automated computational system using depth cameras and point cloud processing. The system uses depth information to automatically identify object boundaries and calculate dimensions, substituting user interaction with algorithmic processing to improve both accuracy and ease of operation
2Measurement precision
If single direction depth information is used for measurement, then processing speed is improved, but measurement precision deteriorates due to insufficient object coverage
Solution Approach 1:
The system transitions from single-direction to multi-directional depth information acquisition by capturing images from multiple angles. This dimensional approach allows the system to construct comprehensive point clouds that fully represent three-dimensional objects, improving measurement accuracy by capturing all object surfaces and features from different perspectives
Solution Approach 2:
The patent combines multiple point clouds generated from different viewing directions into a unified comprehensive point cloud. By merging the bounding boxes and depth information from multiple measurements, the system creates a complete three-dimensional representation of the object, ensuring accurate size measurement while managing system complexity through integrated processing
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The device automatically and accurately measures object sizes by generating precise bounding boxes from multiple depth perspectives, reducing user error and enhancing measurement efficiency.
Implementation Method 1
a first depth map of the object based on a first image frame taken by the time of flight sensor in a first direction from the object
Implementation Method 2
a second image frame taken by the red-green-blue image sensor in a second direction from the object
Data Source
AI summary
According to an embodiment, an electronic device includes a display, a memory, and a processor operatively connected to the display and the memory. The memory stores instructions that cause the processor to generate first depth information in a first direction from an object, generate a first point cloud of the object based on the first depth information, generate a first bounding box containing one or more points of the first point cloud, generate second depth information in a second direction from the object, the second direction being different from the first direction, generate a second point cloud of the object based on the second depth information, generate a second bounding box containing one or more points of the second point cloud, generate a third bounding box by combining the first and second bounding boxes, and display the third bounding box on the display. Certain other embodiments are also possible.