Position Identification Program Correcting GPS Deviation Using Depth Images
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing evacuation assistance tools inaccurately identify the position of obstacles during disasters due to deviations between the captured image position and the actual position, leading to incorrect evacuation routes.
Innovation Solution
A position identification program that uses a combination of GPS, electronic compass, and machine learning models to estimate the depth and segment images, correcting the deviation and accurately identifying the position of obstacles on a map by analyzing depth changes and image segmentation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GPS and electronic compass are used to determine position, then the system can acquire location data, but the identified position deviates from the actual position leading to incorrect evacuation routes
Solution Approach 1:
The patent introduces an intermediary approach by using image data and depth information as a mediator between the GPS position and the actual obstacle position. The system captures images at the GPS location, processes depth information to identify obstacles and road regions, and uses this visual intermediary data to correct the positional deviation and accurately identify obstacle positions for evacuation routing.
2Measurement precision
If depth information is added to image processing, then obstacle position can be identified, but the system complexity increases
Solution Approach 1:
The patent applies segmentation by dividing the image processing into distinct functional modules: capturing captured images, processing depth information, identifying road regions, and determining obstacle positions. This segmentation allows each module to handle specific tasks independently, making the complex system more manageable and maintainable while achieving precise obstacle position identification through coordinated operation of these segmented functions.
Data Source
AI summary
A recording medium stores a program for causing a computer to execute processing including acquiring a captured image and a depth image that represents a distance from an imaging position, identifying a road region and another region in contact with the road region from the captured image, calculating a change in a depth of a first region that corresponds to the road region and a change in a depth of a second region that corresponds to the another region included in the depth image, determining whether or not the another region is a detection target based on the change in the depth of the first region and the change in the depth of the second region, and identifying a position of a subject included in the another region based on the depth of the second region and the imaging position when the another region is the detection target.