FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4293387332> ?p ?o ?g. }

• W4293387332 endingPage "116848" @default.
• W4293387332 startingPage "116848" @default.
• W4293387332 abstract "Low-light image (LLI) enhancement is an important image processing task that aims at improving the illumination of images taken under low-light conditions. Recently, a remarkable progress has been made in utilizing deep learning (DL) approaches for LLI enhancement. This paper provides a concise and comprehensive review and comparative study of the most recent DL models used for LLI enhancement. To our knowledge, this is the first comparative study dedicated to DL-based models for LLI enhancement. We address LLI enhancement in two ways: (i) standalone, as a separate task, and (ii) end-to-end, as a pre-processing stage embedded within another high-level computer vision task, namely object detection and classification. The paper consists of six logical parts. First, we provide an overview of the background and literature in LLI enhancement. Second, we describe the test data and experimental setup of the study. Third, we present a quantitative and qualitative comparison of the visual and perceptual quality achieved by 10 of the most recent DL-based LLI enhancement models. Fourth, we present a comparative analysis for object detection and classification performance achieved by 4 different object detection models applied on LLIs and their enhanced counterparts. Fifth, we perform a feature analysis of DL feature maps extracted from normal, low-light, and enhanced images, and perform the occlusion experiment to better understand the effect of LLI enhancement on the object detection and classification task. Finally, we provide our conclusions and highlight future steps and potential directions. • Evaluates Deep Learning (DL) models for Low-light Image (LLI) enhancement. • Compares 10 LLI enhancement models and 4 object detection and classification models. • Provides a quantitative and qualitative comparison of visual and perceptual quality. • Evaluates impact of LLI enhancement on object detecting and classification quality. • Performs occlusion experiment to study LLI enhancement’s effect on object detection." @default.
• W4293387332 created "2022-08-28" @default.
• W4293387332 creator A5084446270 @default.
• W4293387332 creator A5088417940 @default.
• W4293387332 date "2022-11-01" @default.
• W4293387332 modified "2023-10-12" @default.
• W4293387332 title "Comparing deep learning models for low-light natural scene image enhancement and their impact on object detection and classification: Overview, empirical evaluation, and challenges" @default.
• W4293387332 cites W1436538595 @default.
• W4293387332 cites W1849277567 @default.
• W4293387332 cites W1861492603 @default.
• W4293387332 cites W1930824406 @default.
• W4293387332 cites W1971014006 @default.
• W4293387332 cites W1976478698 @default.
• W4293387332 cites W1982471090 @default.
• W4293387332 cites W1986086122 @default.
• W4293387332 cites W2003884262 @default.
• W4293387332 cites W2012554041 @default.
• W4293387332 cites W2016622085 @default.
• W4293387332 cites W2025768430 @default.
• W4293387332 cites W2027898483 @default.
• W4293387332 cites W2031489346 @default.
• W4293387332 cites W2046119925 @default.
• W4293387332 cites W2054814429 @default.
• W4293387332 cites W2055745001 @default.
• W4293387332 cites W2078807908 @default.
• W4293387332 cites W2087671401 @default.
• W4293387332 cites W2102166818 @default.
• W4293387332 cites W2110158442 @default.
• W4293387332 cites W2110405746 @default.
• W4293387332 cites W2114582993 @default.
• W4293387332 cites W2116973876 @default.
• W4293387332 cites W2121900453 @default.
• W4293387332 cites W2125732958 @default.
• W4293387332 cites W2133665775 @default.
• W4293387332 cites W2141983208 @default.
• W4293387332 cites W2145744030 @default.
• W4293387332 cites W2150721269 @default.
• W4293387332 cites W2161920802 @default.
• W4293387332 cites W2164847484 @default.
• W4293387332 cites W2176950688 @default.
• W4293387332 cites W2183341477 @default.
• W4293387332 cites W2194775991 @default.
• W4293387332 cites W2254039850 @default.
• W4293387332 cites W2289697716 @default.
• W4293387332 cites W2296548841 @default.
• W4293387332 cites W2468596194 @default.
• W4293387332 cites W2503339013 @default.
• W4293387332 cites W2556068545 @default.
• W4293387332 cites W2735974062 @default.
• W4293387332 cites W2736611505 @default.
• W4293387332 cites W2741137940 @default.
• W4293387332 cites W2768814045 @default.
• W4293387332 cites W2783399029 @default.
• W4293387332 cites W2783573276 @default.
• W4293387332 cites W2791071401 @default.
• W4293387332 cites W2798844427 @default.
• W4293387332 cites W2799265886 @default.
• W4293387332 cites W2807563922 @default.
• W4293387332 cites W2892529932 @default.
• W4293387332 cites W2900662096 @default.
• W4293387332 cites W2905637987 @default.
• W4293387332 cites W2907859765 @default.
• W4293387332 cites W2908954495 @default.
• W4293387332 cites W2911504749 @default.
• W4293387332 cites W2916894988 @default.
• W4293387332 cites W2925108882 @default.
• W4293387332 cites W2929906481 @default.
• W4293387332 cites W2935842779 @default.
• W4293387332 cites W2948354154 @default.
• W4293387332 cites W2952046917 @default.
• W4293387332 cites W2962785568 @default.
• W4293387332 cites W2962976294 @default.
• W4293387332 cites W2963150697 @default.
• W4293387332 cites W2963351448 @default.
• W4293387332 cites W2963766909 @default.
• W4293387332 cites W2965836860 @default.
• W4293387332 cites W2968847413 @default.
• W4293387332 cites W2970060060 @default.
• W4293387332 cites W2970103540 @default.
• W4293387332 cites W2971483169 @default.
• W4293387332 cites W2971719842 @default.
• W4293387332 cites W2981718299 @default.
• W4293387332 cites W2983177375 @default.
• W4293387332 cites W2999032021 @default.
• W4293387332 cites W3003838261 @default.
• W4293387332 cites W3008811564 @default.
• W4293387332 cites W3013338555 @default.
• W4293387332 cites W3035731588 @default.
• W4293387332 cites W3091618893 @default.
• W4293387332 cites W3103635814 @default.
• W4293387332 cites W3106250896 @default.
• W4293387332 cites W3121661546 @default.
• W4293387332 cites W3126143330 @default.
• W4293387332 cites W3148464841 @default.
• W4293387332 cites W3166415362 @default.
• W4293387332 cites W3214864283 @default.
• W4293387332 cites W4200367127 @default.
• W4293387332 cites W4230472795 @default.

• next