Dynamic Image Region Setting for Vehicle Periphery Recognition

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing vehicle periphery recognition systems fail to consider various factors when determining the image region for analysis, leading to suboptimal performance during actual driving conditions.

Innovation Solution

An image processing apparatus that uses GPS data, vehicle information, and road information to dynamically set the image region for analysis based on travel speed, steering angle, and lighting conditions, allowing for adaptive extraction of peripheral images.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a fixed size and direction image is captured for analysis, then the analysis process is simple, but the recognition accuracy during actual driving deteriorates because the image region does not adapt to changing vehicle conditions

Engineering Contradiction:
Improverecognition accuracyVSAvoidimage processing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent applies dynamics by making the image capture region and analysis region variable rather than fixed. The control unit dynamically adjusts the capture region based on vehicle speed, steering angle, and other movement information. Additionally, the analysis region is dynamically determined based on the captured image content, allowing the system to adapt to changing driving conditions and maintain high recognition accuracy without excessive complexity.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The patent changes parameters by adjusting the size, position, and shape of the capture region based on vehicle movement parameters (speed, steering angle, tilt angle). The analysis region parameters are also changed based on the captured image content. This parameter adaptation allows the system to optimize recognition accuracy for different driving scenarios while managing processing complexity through selective parameter adjustment.

Inventive Principle:
Principle #35Parameter changes

2Reliability

If the entire peripheral image is processed, then complete coverage is achieved, but processing time and computational load increase significantly

Engineering Contradiction:
Improvedetection completenessVSAvoidprocessing time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent extracts only the necessary portion of the peripheral image for analysis by defining a specific analysis region within the captured image. The control unit determines this analysis region based on the captured image content and vehicle conditions, extracting only the relevant area for processing. This extraction approach maintains detection completeness for important elements while significantly reducing processing time and computational load by avoiding unnecessary processing of the entire image.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent applies partial action by processing only a portion of the captured image rather than the entire image. The analysis region is set to cover only the necessary area based on vehicle conditions and image content, implementing partial processing that maintains adequate detection capability while reducing overall processing time and computational resources required.

Inventive Principle:
Principle #16Partial or excessive action

3Measurement precision

If the image capture region is adjusted based on vehicle movement information, then recognition accuracy improves, but the determination process becomes more complex

Engineering Contradiction:
Improveimage region accuracyVSAvoidregion determination complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent applies preliminary action by pre-establishing the relationship between vehicle movement information (speed, steering angle, tilt angle) and the appropriate capture region settings. The control unit uses predetermined rules and algorithms to quickly determine the capture region based on current vehicle state, avoiding complex real-time calculations. This preliminary preparation maintains high image region accuracy while keeping the determination process relatively simple and efficient.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP2879112B1Image processing device, image pickup device, mobile unit, program and region setting method
Publication Date: 2020.06.17 KYOCERA CORP
  • EP2879112B1 patent drawingFigure 1
  • EP2879112B1 patent drawingFigure 2
  • EP2879112B1 patent drawingFigure 3

AI summary

An image processing apparatus 14 includes a road information receiver 24 and a region setter 25. The road information receiver 24 obtains road information around a movable object. The region setter 25, based on the road information, sets a region of a peripheral image of the movable object to extract.