Travel Assistance Vision Prioritization for Side and Rear Hazard Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing external environment recognition systems fail to accurately detect vehicles approaching from the sides or rear, leading to potential collisions due to insufficient computing power allocation and recognition accuracy.

Innovation Solution

A travel assistance device that includes an information processing section to extract specific regions, derive risk degrees, set processing priorities, and allocate computing resources based on risk, enabling early detection of potential dangers and efficient use of computing power.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If high resolution is set for all regions of the captured image, then recognition accuracy is improved, but computing power requirements exceed current computer capabilities

Engineering Contradiction:
Improverecognition accuracyVSAvoidcomputing power
Core Design Contradiction:
Measurement precisionVSPower

Solution Approach 1:

The patent applies local quality by setting different resolutions for different regions of the captured image. Specifically, the image processing section divides the captured image into multiple regions and sets high resolution for regions with high collision risk (such as regions where vehicles are detected or where the own vehicle is changing direction) while setting low resolution for regions with low collision risk. This allows recognition accuracy to be maintained in critical areas while reducing overall computing power requirements.

Inventive Principle:
Principle #3Local quality

2Power

If high resolution is set for central regions only, then computing power is saved, but recognition accuracy for vehicles approaching from sides or rear deteriorates

Engineering Contradiction:
Improvecomputing powerVSAvoidsafety
Core Design Contradiction:
PowerVSReliability

Solution Approach 1:

The patent applies dynamics by making the resolution setting adaptive rather than static. The image processing section dynamically determines which regions require high resolution based on real-time conditions such as the presence of other vehicles, the own vehicle's travel direction, and calculated collision risks. This allows the system to shift computational resources to different regions as needed, ensuring that safety-critical areas always receive sufficient processing power while optimizing overall resource utilization.

Inventive Principle:
Principle #15Dynamics

3Ease of operation

If uniform processing load is applied to all regions, then processing is simple, but early recognition of dangers in all directions is delayed

Engineering Contradiction:
Improveprocessing simplicityVSAvoidrecognition time
Core Design Contradiction:
Ease of operationVSLoss of time

Solution Approach 1:

The patent applies preliminary action by performing risk assessment and region prioritization before the main recognition processing. The image processing section first identifies regions with high collision risk based on the presence of other vehicles and the own vehicle's travel characteristics, then allocates higher processing loads to these regions. This preliminary classification ensures that dangerous situations are detected and processed with high priority, reducing recognition time for critical threats while maintaining simpler processing for low-risk areas.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP4641541A1Travel assistance device, and travel assistance method for travel assistance device
Publication Date: 2025.10.29 ASTEMO LTD
  • EP4641541A1 patent drawingFigure 1
  • EP4641541A1 patent drawingFigure 2
  • EP4641541A1 patent drawingFigure 3

AI summary

A travel assistance device according to the present invention comprises: a region extraction unit (11) that extracts a specific region that includes traffic participants around a host vehicle from image information of sensor data; a risk derivation unit (15) that derives the degree of risk for safe travel of the host vehicle in relation to the traffic participants in the extracted specific region; a priority-setting unit (16) that sets the processing priority of the specific region according to the degree of risk; a processing-load-setting unit (18) that sets the processing load of information of the specific region according to the processing priority; and a recognition-processing unit (19) that performs traffic participant recognition on the basis of processing load information from the processing-load-setting unit.