Ghosting in HDR Video

Akyüz, Ahmet Oğuz
Telalovic, Jasminka
Hadziabdic, Kanita
HDR video capture is a very important problem, the solution of which can facilitate the transition to an end-to-end HDR video pipeline. This problem is currently being tackled using various approaches. On the hardware front, there exist designs with a judicious combination of multiple off-the-shelf components such as lenses, mirrors, beam-splitters, and sensors, as well as designs that involve high dynamic range sensors. On the software front, many HDR video deghosting algorithms exist that enable creation of HDR videos from differently exposed successive frames. These algorithms need to deal with motion within the captured scene, as well as the motion of the capture device to produce artifact-free HDR videos. This chapter provides an overview of the most notable algorithms in both approaches, with an emphasis on HDR video deghosting algorithms. For further reading, we refer the interested readers to other excellent resources on this topic.


Directional coding of backward compatible high dynamic range (HDR) image coding residues
Feyiz, Kutan; Kamışlı, Fatih; Department of Electrical and Electronics Engineering (2018)
High dynamic range (HDR) image and video formats are proposed to overcome limitations of widely accepted standard 8-bit low dynamic range (LDR) image and video representations. The main aim of these formats is to encode the whole luminance range of real world scenes which changes from extreme darkness ( 10 − 6 cd/ m 2 ) to bright sunshine ( 10 8 cd/ m 2 ), and to generate and store such scenes independent from the display technology. To achieve a successful transition from LDR to HDR technology, backward ...
Evaluation of tone mapping and exposure fusion algorithms on HDR videos for face detection and recognition
Çavdarlı, Fehime Betül; Akyüz, Ahmet Oğuz; Department of Computer Engineering (2022-2-08)
High dynamic range (HDR) images have become popular recently especially for video surveillance systems. One of the most important reasons for this is that in areas where there is under or over-exposure, classical low dynamic range (LDR) images are insufficient to capture details, while HDR images have better visual details and contain wide range illumination values. However, since HDR images cannot be viewed on conventional LDR displays, additional processing such as tonemapping and/or fusion are required t...
An Evaluation of ghost removal algorithms for exposure fusion
Kutlu, Tuğser; Akar, Gözde; Department of Electrical and Electronics Engineering (2015)
In high dynamic range imaging (HDR), the goal is to capture a scene with a higher dynamic range than the camera capable of capturing with a single exposure. Similar to HDR, exposure fusion is a process that takes multiple images and combines them to create a single dynamically enhanced image by only keeping the properly exposed elements. When using multiple images, local motion of objects can influence the quality of the final image in such a way that local motion of objects causes a ghost artifact. In this...
Privacy protection of tone-mapped HDR images using false colours
ÇİFTÇİ, Serdar; Akyüz, Ahmet Oğuz; PİNHEİRO, Antonio M. G.; Ebrahimi, Touradj (2017-12-01)
High dynamic range (HDR) imaging has been developed for improved visual representation by capturing a wide range of luminance values. Owing to its properties, HDR content might lead to a larger privacy intrusion, requiring new methods for privacy protection. Previously, false colours were proved to be effective for assuring privacy protection for low dynamic range (LDR) images. In this work, the reliability of false colours when used for privacy protection of HDR images represented by tone-mapping operators...
Deep joint deinterlacing and denoising for single shot dual-ISO HDR reconstruction
Çoğalan, Uğur; Akyüz, Ahmet Oğuz; Department of Computer Engineering (2019)
HDR (High Dynamic Range) images have traditionally been obtained by merging multiple exposures each captured with a different exposure time. However, this approach entails longer capture times and necessitates deghosting if the captured scene contains moving objects. With the advent of modern camera sensors that can perform per-pixel exposure modulation, it is now possible to capture all of the required exposures within a single shot. The new challenge then becomes how to best combine different pixels with ...
Citation Formats
A. O. Akyüz, J. Telalovic, and K. Hadziabdic, Ghosting in HDR Video. 2016, p. 44.