A high-performance object detection system using hdr images obtained from ldr cameras in autonomous vehicles

EP4440902A4Pending Publication Date: 2025-03-19ORTA DOGU TEKNIK UNIVERSITESI
1 Cites 0 Cited by

Patent Information

Application Number
EP2022917078
Authority / Receiving Office
EP · EP
Patent Type
Applications
Current Assignee / Owner
Priority Date
2021-12-29
Filing Date
2022-12-28
Publication Date
2025-03-19

AI Technical Summary

Technical Problem

Autonomous vehicles equipped with Low Dynamic Range (LDR) cameras struggle to distinguish and recognize objects in scenes with high illumination differences, such as tunnels or sunset conditions, due to the inability to handle varying light levels effectively, which can lead to accidents.

Method used

A high-performance object detection system is developed using HDR images generated from LDR cameras by combining the output of at least three standard cameras with different exposure values, predicting disparity values, and applying exposure fusion and gamma correction to create a High Dynamic Range (HDR) image, which is then input into object detection algorithms or enhanced using tone mapping algorithms for improved detection.

Benefits of technology

This system enables accurate object detection and recognition in high illumination difference conditions, enhancing the safety of autonomous vehicles by generating HDR images that overcome the limitations of LDR cameras, preventing accidents caused by glare or dark areas.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The present invention relates to a high-performance object detection system using HDR images obtained from LDR cameras, which allows for the separation and recognition of detected objects in images under high illumination difference conditions (tunnels, sunrise or sunset, etc.) and prevents autonomous vehicles from causing undesired accidents.
Need to check novelty before this filing date? Find Prior Art