Electronic Device Distance Identification Using Neural Network Coordinate Rotation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current electronic devices lack an effective method to accurately identify the distance between themselves and external objects within rotated images using neural networks, which is crucial for applications like augmented reality and automatic driving.
Innovation Solution
An electronic device equipped with a camera, sensor, and processor that rotates image coordinates based on an identified angle, uses a neural network to categorize objects, and calculates distance based on rotated coordinates, enabling precise object identification and distance measurement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If image coordinates are rotated based on identified angle to enable accurate object identification in rotated images, then measurement precision is improved, but device complexity increases due to additional coordinate transformation operations
Solution Approach 1:
The patent applies preliminary action by pre-rotating the image coordinates based on the identified rotation angle before performing object identification and distance measurement. This coordinate transformation is performed in advance to align the rotated image with the neural network's expected input orientation, thereby improving measurement precision without requiring complex real-time adjustments during the main processing stage.
2Reliability
If neural network is used to categorize objects and identify distances in rotated images, then reliability of object identification is improved, but processing time increases
Solution Approach 1:
The patent applies segmentation by dividing the image processing task into distinct stages: first rotating the image coordinates based on the identified angle, then categorizing objects using the neural network, and finally identifying distances. This segmentation allows each component to be optimized independently, improving overall reliability while managing processing time through efficient task distribution.
3Productivity
If coordinate rotation and neural network processing are implemented for distance measurement, then productivity of distance identification is improved, but ease of operation deteriorates due to complex processing steps
Solution Approach 1:
The patent applies self-service by implementing an automated system that autonomously performs coordinate rotation, neural network-based object categorization, and distance measurement without requiring manual intervention. The system automatically identifies the rotation angle, transforms coordinates accordingly, and processes the image through the neural network, thereby improving productivity while minimizing the operational burden on users.
Data Source
AI summary
A processor of an electronic device according to an embodiment may be configured to: obtain an angle rotated about an optical axis of the camera, through the sensor; identify, in an image obtained through the camera, first coordinates with respect to first vertices of an area in which a visual object corresponding to an external object is included; obtain second coordinates by rotating the first coordinates about a center point of the area, according to the angle; based on a category of the external object, which is identified by a neural network to which the image is inputted, identify third coordinates having a size corresponding to the category, from the second coordinates; and identify a distance between the electronic device and the external object, based on the third coordinates.