Road Region Mapping for Shielded Areas Using Image-Map Differences

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional methods struggle to accurately handle shielding regions in road maps due to obstacles like tunnels, overhead crossings, and high-rise buildings, leading to incomplete and inaccurate map information for automatic driving and driving assistance systems.

Innovation Solution

An information processing device and method that utilizes satellite and aerial images to estimate road regions, compare them with map data, and update the map information by considering shielding regions, using neural networks and structured verification units to determine the reliability and accuracy of road and lane information.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a plurality of microphones are disposed at a plurality of locations to improve noise removal performance, then the noise removal capability is improved, but the device complexity increases

Engineering Contradiction:
Improvenoise removal capabilityVSAvoidmicrophone array complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The sound collection device is designed to perform multiple functions: it collects sound waves for speech recognition, removes noise through beamforming, and can operate in different modes (noise removal mode and sound collection mode). This multi-functionality allows a single device to replace what would otherwise require separate systems, reducing overall complexity while maintaining noise removal effectiveness.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent implements a hierarchical processing architecture where the sound collection device first collects raw audio signals, then the noise removal unit processes these signals to eliminate background noise, and finally the speech recognition unit processes the cleaned signals. This nested processing structure allows each component to focus on a specific task, improving overall system efficiency without requiring excessive complexity in individual components.

Inventive Principle:
Principle #7Nested doll (Nesting)

2Measurement precision

If deep learning technology is used to improve noise removal accuracy, then the noise removal precision is improved, but the processing time increases

Engineering Contradiction:
Improvenoise removal precisionVSAvoidspeech recognition time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary noise removal processing before speech recognition, using beamforming techniques to pre-process the audio signals. This preliminary action reduces the complexity of the subsequent speech recognition task by providing cleaner input signals, thereby reducing the overall processing time while maintaining high noise removal precision through the combination of beamforming and deep learning.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The sound collection device operates in different modes periodically or based on conditions: in noise removal mode, it applies deep learning-based noise suppression; in sound collection mode, it prioritizes rapid signal acquisition. This periodic switching allows the system to balance between noise removal precision and processing speed based on real-time requirements.

Inventive Principle:
Principle #19Periodic action

3Measurement precision

If noise removal processing is performed before speech recognition to improve recognition accuracy, then the recognition precision is improved, but the processing complexity increases

Engineering Contradiction:
Improvespeech recognition precisionVSAvoidprocessing pipeline complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The speech processing system is segmented into distinct functional modules: a sound collection device for acquiring audio signals, a noise removal unit for eliminating background noise using beamforming, and a speech recognition unit for converting cleaned signals to text. This segmentation allows each module to be optimized independently and simplifies the overall processing pipeline by creating clear interfaces between stages, reducing system-level complexity while improving recognition precision.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP4318439B1Information processing device and information processing method
Publication Date: 2026.05.06 ASTEMO LTD
  • EP4318439B1 patent drawingFigure 1
  • EP4318439B1 patent drawingFigure 2
  • EP4318439B1 patent drawingFigure 3

AI summary

An information processing device and an information processing method capable of appropriately handling a shielding region of a road are provided. The information processing device includes a first information conversion unit 15 that estimates a first road region from an image obtained by imaging the road, a second information conversion unit 17 that estimates a second road region from map information stored in a map information storage unit 11, and a difference extraction unit 16 that extracts difference information representing a difference between the first road region and the second road region. Further, in the information processing method, a computer estimates the first road region from the image obtained by imaging the road, estimates the second road region from the map information, and extracts the difference information indicating the difference between the first road region and the second road region.