Image processing device and image processing method

The image processing apparatus enhances drivable area recognition in vehicle environments by segmenting regions based on image features and 3D information, adjusting brightness and contrast to improve visibility and accuracy, addressing the limitations of existing systems without hardware replacements.

WO2026115919A1PCT designated stage Publication Date: 2026-06-04SONY SEMICON SOLUTIONS CORP
View PDF 4 Cites 0 Cited by

Patent Information

Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
SONY SEMICON SOLUTIONS CORP
Filing Date
2025-10-06
Publication Date
2026-06-04

AI Technical Summary

Technical Problem

Existing image processing systems struggle to accurately recognize drivable areas in vehicle environments, particularly in conditions where road surface unevenness, shadows, and obstacles create optical illusions, leading to difficulties in distinguishing drivable from undrivable areas without significant system replacements or additional hardware.

Method used

An image processing apparatus and method that utilizes both image features and three-dimensional information to segment regions, estimate correction targets, and adjust brightness and contrast based on height and feature similarities to enhance visibility of drivable areas, allowing integration into existing systems without replacing recognition models or hardware.

Benefits of technology

Improves visibility and recognition accuracy of drivable areas by correcting image features and heights, enabling accurate identification of road conditions without requiring system replacements, thus enhancing the performance of existing ADAS systems.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure JP2025035423_04062026_PF_FP_ABST
    Figure JP2025035423_04062026_PF_FP_ABST
Patent Text Reader

Abstract

An image processing device according to the present disclosure comprises: a data acquisition unit that acquires image data and three-dimensional information associated with a subject; a region division unit that subjects a subject imaging region to region division based on an image feature amount obtained from the image data, and to region division based on height information obtained from the three-dimensional information; a correction region estimation unit that, on the basis of the result of the region division by the region division unit, estimates a region to be corrected in an image expressed by the image data; and a correction unit that, on the basis of the result of the region division based on the image feature amount and the result of the region division based on the height information, performs image correction on at least the region to be corrected in the image expressed by the image data.
Need to check novelty before this filing date? Find Prior Art