A Perception-Based Brightness Segmentation Method of High Dynamic Range Infrared Images

Zhang, Feifei; Chen, Qiang; Wu, Yilin; Chen, Guo-Ming; Zhu, Xiongyong; Xu, Jianhui

doi:10.1109/icdh51081.2020.00021

Cited by 2 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As for the processing of the base layer, the main focus is on researching global tone mapping methods for its dynamic range compression. There is relatively more research in this area, recently Zhang et al 22 . proposed a brightness segmentation-based plateau histogram equalization algorithm that can also be applied to tone mapping of the base layer.…”

Section: Discussionmentioning

confidence: 99%

“…Infrared images collected from thermal cameras usually have a high dynamic range (HDR, 14 bit or higher), which means the image has a higher temperature resolution and contains more details 1 – 3 However, most current display devices are based on 8-bit integers (i.e., 256 gray levels), and the brightness can be displayed is very limited, which causes the problem that HDR infrared data collected by infrared imaging cameras is difficult to match with common display devices.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Display method for high dynamic range infrared image based on gradient domain guided image filter

Zhang,

Dai,

Chen

et al. 2024

Opt. Eng.

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Display method for high dynamic range infrared image based on gradient domain guided image filter

Zhang,

Dai,

Chen

et al. 2024

Opt. Eng.

View full text Add to dashboard Cite

“…However, in areas where the grayscale distribution is relatively flat, HE may amplify noise. contrast limited histogram equalization [3] (CLHE) limits the contrast by clipping the peaks of the histogram, this ensures a more balanced distribution of grayscale values and enhances the overall visual quality of the image. Contrast limited adaptive histogram equalization [4] (CLAHE) is an effective method for enhancing the contrast of local regions in an image.…”

Section: Related Workmentioning

confidence: 99%

“…We implemented a widely used objective metric called tone mapping image quality index (TMQI) [16] to ensure that our target image meets a fixed selection criterion. To find the target mapping image for each HDR image, we chosen some mainstream methods, such as HE [2]、BHE[17]、CLHE [3]、CLAHE [4] and FBF [5]. In addition, we used some methods from HDR Toolbox [18], such as AshikhminTMO 、 BanterleTMO 、 BruceExpoBlendTMO 、 DragoTMO 、 DurandTMO 、 KimKautzConsistentTMO 、 KrawczykTMO 、 LischinskiTMO 、 MertensTMO 、 RamanTMO and VanHaterenTMO.…”

Section: Simulationmentioning

confidence: 99%

Grayscale mapping of infrared images based on end-to-end deep neural networks

Cheng,

Hong,

Wang

et al. 2024

Preprint

View full text Add to dashboard Cite

The grayscale mapping of infrared images is an important research direction in the field of infrared imaging. A fast and scene-adaptive grayscale mapping method is crucial for visualizing high dynamic range original infrared images in various standard dynamic range output devices, such as printers and standard monitors. At present, mainstream grayscale mapping methods can only handle high dynamic range images in limited scenes and require extensive parameter adjustments to generate high-quality mapping results. In this paper, we propose a fast, parameter-free, and scene-adaptive grayscale mapping method to address this issue, which can achieve high subjective quality mapping results. Our model not only adapts to various categories of scenes, but also resolves the issues of insufficient contrast and significant loss of details in the grayscale mapping of high dynamic range infrared images. We explored the different impacts of the loss functions and normalization layers in the model on the mapping effect, and ultimately adopted L1 loss, perceptual loss, and batch normalization to accomplish our task. To ensure the production of high-quality mapping results, we used the objective metric of high dynamic range image quality assessment, specifically the tone mapping image quality index, to identify target images for training our model. We evaluated our results from both quantitative and qualitative perspectives, showcasing the high-quality output images generated by our model in a wide range of real-world scenarios. This substantiates the superiority of our approach.

show abstract

A Perception-Based Brightness Segmentation Method of High Dynamic Range Infrared Images

Cited by 2 publications

References 11 publications

Display method for high dynamic range infrared image based on gradient domain guided image filter

Display method for high dynamic range infrared image based on gradient domain guided image filter

Grayscale mapping of infrared images based on end-to-end deep neural networks

Contact Info

Product

Resources

About