Change Point Detection for Automated Driving Map Currency
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automated driving systems face challenges in accurately identifying changes in road structures and environments when high-definition maps are outdated, leading to potential control issues due to mismatches between map images and actual vehicle surroundings.
Innovation Solution
A change point detection device and system that uses a processor to analyze images from vehicle cameras, eliminate obstructing objects, and calculate coincidence degrees with stored map information to determine if changes have occurred, with the ability to update map information and transmit change points to other vehicles and a server.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If map information is used for automated driving without real-time updates, then the system operates stably with existing data, but the map information becomes outdated and causes mismatches with actual road structures
Solution Approach 1:
The system captures images of actual road structures, compares them with map information to detect changes, and feeds back updated map information to the automated driving system. This feedback loop ensures map information remains current without disrupting stable system operation.
Solution Approach 2:
The system performs preliminary change detection by comparing captured images with existing map information before automated driving uses the outdated map data. This preliminary action identifies changes in advance, allowing the system to update map information proactively rather than reactively.
2Measurement precision
If the system compares entire images with map information, then comprehensive change detection is achieved, but objects hiding structures cause erroneous detections
Solution Approach 1:
The system extracts and removes objects that hide road structures from the captured images before comparing with map information. This extraction process eliminates the harmful effect of obstructing objects while preserving the actual structural changes for accurate detection.
Solution Approach 2:
The system segments the image processing into distinct steps: first detecting and removing obstructing objects, then comparing the cleaned image with map information. This segmentation allows comprehensive change detection without interference from hiding objects.
3Loss of information
If the system updates map information frequently to maintain accuracy, then map currency is improved, but the computational load and processing time increase
Solution Approach 1:
Instead of processing and updating entire map datasets frequently, the system performs partial updates by detecting and processing only the specific changes identified through image comparison. This reduces computational load while maintaining map currency.
Solution Approach 2:
The system performs change detection periodically by capturing images at regular intervals during automated driving operation. This periodic action maintains map information currency without requiring continuous heavy processing, balancing accuracy with efficiency.
Data Source
AI summary
A change point detection device includes a memory 170 that stores map information representing a structure associated with a traveling condition on and around a road, an object detection unit 162 that detects a shielding object 20 hiding the structure from an image acquired by an in-vehicle camera 110 mounted on a vehicle 100 and representing an environment around the vehicle 100, a collation unit 163 that eliminates the structure hidden by the shielding object 20 in the map information, collates the image with the map information, and calculates a coincidence degree between the image and the map information, and a change point detection unit 164 that determines, when the coincidence degree is less than or equal to a predetermined threshold value, that the structure represented in the image has a change point different from the corresponding structure represented in the map information.