HDR IMAGE CONSTRUCTION FROM TRIFOCAL MULTIEXPOSURE IMAGES

Date

2021-10-06

Author

KOZ, ALPER
Demirkılıç, Barış
Kurt, Yunus Bilge
Akyüz, Ahmet Oğuz
Kalkan, Sinan
Alatan, Abdullah Aydın
Chalmers, Alan

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

72
views

0
downloads

With the progress of autonomous vehicles, the sensing of the environment in more detail with higher dynamic ranges has become more important to classify surrounding objects and obstacles. While stereo HDR images for this purpose can provide advantages compared to the conventional LDR images, they suffer from limited dynamic ranges and spike-like noises due to the inaccuracies in disparity estimation. In this paper, we formulate the HDR image construction problem from trifocal multi-exposure images and develop a method which improves disparity estimation for better HDR image construction. Given the symmetric geometry of the trifocal setup, the proposed method uses the equivalence of disparities from middle to left and middle to right images to determine the reliable regions. The HDR radiance for the pixels in these reliable regions are estimated by using the weighted average of the warped images in different exposures and the middle image, whereas the radiance values outside the reliable regions are estimated by using only the middle image. The experiments with different exposure combinations for left, middle and right images reveal better performances of the proposed method compared to the stereo HDR imaging. It is also observed that the improvements are more apparent for larger disparities between the cameras.

Subject Keywords

High dynamic range, HDR, multi-exposure, disparity estimation, autonomous vehicles

URI

https://attend.ieee.org/mmsp-2021/technical-program/
https://hdl.handle.net/11511/100594

DOI

https://doi.org/10.1109/mmsp53017.2021.9733440

Conference Name

IEEE MMSP

Collections

Department of Computer Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

Object Detection for Autonomous Driving: High-Dynamic Range vs. Low-Dynamic Range Images Kocdemir, Ismail H.; Akyüz, Ahmet Oğuz; Koz, Alper; Chalmers, Alan; Alatan, Abdullah Aydın; Kalkan, Sinan (2022-01-01) An important problem in autonomous driving is to perceive objects even under challenging illumination conditions. Despite this problem, existing solutions use low-dynamic range (LDR) images for object detection for autonomous driving. In this paper, we provide a novel analysis on whether high-dynamic range (HDR) images can provide better performance for object detection for autonomous driving. To this end, we choose a seminal deep object detector and systematically evaluate its performance when trained with...
Feedback motion planning of unmanned surface vehicles via random sequential composition Ege, Emre; Ankaralı, Mustafa Mert (SAGE Publications, 2019-08-01) In this paper, we propose a new motion planning method that aims to robustly and computationally efficiently solve path planning and navigation problems for unmanned surface vehicles (USVs). Our approach is based on synthesizing two different existing methodologies: sequential composition of dynamic behaviours and rapidly exploring random trees (RRT). The main motivation of this integrated solution is to develop a robust feedback-based and yet computationally feasible motion planning algorithm for USVs. In ...
Mobility-on-demand scenarios relying on lightweight autonomous and connected vehicles for large pedestrian areas and intermodal hubs Kumru, Murat; Makarem, Laleh; Gillet, Dens (null; 2017-10-05) This paper presents Mobility-On-Demand (MoD) scenarios relying on lightweight autonomous and connected vehicles to ease commuting in large pedestrian areas and intermodal hubs. In particular, we discuss the case of the EPFL campus as an example of a large pedestrian area and the case of the main Zurich train station as an example of a large intermodal hub. These two scenarios help to investigate the potential benefits and the implementation challenges of innovative lightweight autonomous and connected vehic...
Semi-supervised iterative teacher-student learning for monocular depth estimation Süvari, Cemal Barışkan; Halıcı, Uğur; Department of Electrical and Electronics Engineering (2021-2-18) Advances in robotics area and autonomous vehicles have increased the need for accurate depth measurements. Depth estimation is one of the oldest problems of computer vision area. While the depth can be estimated by using many methods, finding a cheap and efficient way of doing it was studied for many years. Although, depth measurements using Lidar sensors or RGB-D cameras provides accurate results, due to cost and narrow applicability they are not very effective. On the other hand, using deep learning archi...
Aerothermodynamic Design Optimization of Hypersonic Vehicles Eyi, Sinan; Boyd, Iain D. (American Institute of Aeronautics and Astronautics (AIAA), 2019-04-01) The objective of this study is to develop a reliable and efficient design optimization method for hypersonic vehicles focused on aerothermodynamic environments. Considering the nature of hypersonic flight, a high-fidelity aerothermodynamic analysis code is used for the simulation of weakly ionized hypersonic flows in thermochemical nonequilibrium. A gradient-based method is implemented for optimization. Bezier or nonuniform rational basis spline curves are used to parametrize the geometry or the geometry ch...

Citation Formats

A. KOZ et al., “HDR IMAGE CONSTRUCTION FROM TRIFOCAL MULTIEXPOSURE IMAGES,” presented at the IEEE MMSP, Tampere, Finlandiya, 2021, Accessed: 00, 2022. [Online]. Available: https://attend.ieee.org/mmsp-2021/technical-program/.