Matches in SemOpenAlex for { <https://semopenalex.org/work/W3046063500> ?p ?o ?g. }
- W3046063500 endingPage "015404" @default.
- W3046063500 startingPage "015404" @default.
- W3046063500 abstract "Abstract In the underwater environment, the backscattering and attenuation of wavelength-dependent light degrade the quality of underwater vision. Low-quality underwater vision will reduce the accuracy of underwater robot visual navigation and pattern recognition. A novel semi-supervised deep convolutional neural network composed of a supervised learning branch and an unsupervised learning branch is proposed herein to improve underwater visual quality with poor visibility in real time. The network is constrained by a supervised loss function consisting of mean square, underwater index, and adversarial loss. The supervised branch serves as the baseline of the image enhancement algorithm to learn the basic feature information of the images and restore the original colors. The unsupervised learning branch, which makes the generated images more realistic and reduces reliance on the quality of the simulation model of synthetic data, applies underwater dark channel prior loss and total variation loss to learn the feature domain information of real images. Experiments show that the results of the proposed method show less color shift, lower fogging and blurring, and more pleasing high-quality vision. The enhanced images can extract more useful feature information, which is promising in the online visual navigation of underwater robots." @default.
- W3046063500 created "2020-08-03" @default.
- W3046063500 creator A5018277217 @default.
- W3046063500 creator A5034101348 @default.
- W3046063500 creator A5046330935 @default.
- W3046063500 date "2020-10-23" @default.
- W3046063500 modified "2023-09-25" @default.
- W3046063500 title "Semi-supervised advancement of underwater visual quality" @default.
- W3046063500 cites W1119591675 @default.
- W3046063500 cites W125693051 @default.
- W3046063500 cites W1558248518 @default.
- W3046063500 cites W1968707439 @default.
- W3046063500 cites W1971693194 @default.
- W3046063500 cites W1976263166 @default.
- W3046063500 cites W1982471090 @default.
- W3046063500 cites W1983445572 @default.
- W3046063500 cites W2009071067 @default.
- W3046063500 cites W2014191529 @default.
- W3046063500 cites W2016628928 @default.
- W3046063500 cites W2055447163 @default.
- W3046063500 cites W2081140338 @default.
- W3046063500 cites W2089621500 @default.
- W3046063500 cites W2091420866 @default.
- W3046063500 cites W2094185466 @default.
- W3046063500 cites W2097900287 @default.
- W3046063500 cites W2128254161 @default.
- W3046063500 cites W2135001643 @default.
- W3046063500 cites W2141704978 @default.
- W3046063500 cites W2144288821 @default.
- W3046063500 cites W2150955789 @default.
- W3046063500 cites W2155586404 @default.
- W3046063500 cites W2194775991 @default.
- W3046063500 cites W2293581118 @default.
- W3046063500 cites W2293894573 @default.
- W3046063500 cites W2294668072 @default.
- W3046063500 cites W2342792048 @default.
- W3046063500 cites W2461710545 @default.
- W3046063500 cites W2474628748 @default.
- W3046063500 cites W2519481857 @default.
- W3046063500 cites W2523532944 @default.
- W3046063500 cites W2565506808 @default.
- W3046063500 cites W2585635281 @default.
- W3046063500 cites W2587107113 @default.
- W3046063500 cites W2616936297 @default.
- W3046063500 cites W2755509443 @default.
- W3046063500 cites W2758376227 @default.
- W3046063500 cites W2763503841 @default.
- W3046063500 cites W2765521864 @default.
- W3046063500 cites W2778341433 @default.
- W3046063500 cites W2783488367 @default.
- W3046063500 cites W2794405642 @default.
- W3046063500 cites W2884601889 @default.
- W3046063500 cites W2892845027 @default.
- W3046063500 cites W2913152041 @default.
- W3046063500 cites W2948400274 @default.
- W3046063500 cites W2950055287 @default.
- W3046063500 cites W2963928582 @default.
- W3046063500 cites W2966501856 @default.
- W3046063500 cites W2966516593 @default.
- W3046063500 cites W2971483169 @default.
- W3046063500 cites W2977423750 @default.
- W3046063500 cites W2988209803 @default.
- W3046063500 cites W2990176100 @default.
- W3046063500 cites W2999811308 @default.
- W3046063500 cites W3099025816 @default.
- W3046063500 cites W3099562471 @default.
- W3046063500 cites W3100034292 @default.
- W3046063500 doi "https://doi.org/10.1088/1361-6501/abaa1d" @default.
- W3046063500 hasPublicationYear "2020" @default.
- W3046063500 type Work @default.
- W3046063500 sameAs 3046063500 @default.
- W3046063500 citedByCount "4" @default.
- W3046063500 countsByYear W30460635002021 @default.
- W3046063500 countsByYear W30460635002023 @default.
- W3046063500 crossrefType "journal-article" @default.
- W3046063500 hasAuthorship W3046063500A5018277217 @default.
- W3046063500 hasAuthorship W3046063500A5034101348 @default.
- W3046063500 hasAuthorship W3046063500A5046330935 @default.
- W3046063500 hasConcept C111368507 @default.
- W3046063500 hasConcept C120665830 @default.
- W3046063500 hasConcept C121332964 @default.
- W3046063500 hasConcept C123403432 @default.
- W3046063500 hasConcept C127162648 @default.
- W3046063500 hasConcept C127313418 @default.
- W3046063500 hasConcept C136389625 @default.
- W3046063500 hasConcept C138885662 @default.
- W3046063500 hasConcept C153180895 @default.
- W3046063500 hasConcept C154945302 @default.
- W3046063500 hasConcept C2776401178 @default.
- W3046063500 hasConcept C31258907 @default.
- W3046063500 hasConcept C31972630 @default.
- W3046063500 hasConcept C41008148 @default.
- W3046063500 hasConcept C41895202 @default.
- W3046063500 hasConcept C50644808 @default.
- W3046063500 hasConcept C81363708 @default.
- W3046063500 hasConcept C98083399 @default.
- W3046063500 hasConceptScore W3046063500C111368507 @default.
- W3046063500 hasConceptScore W3046063500C120665830 @default.