Comparison of Deep Learning and Conventional Demosaicing Algorithms for Mastcam Images
Bayer pattern filters have been used in many commercial digital cameras. In National Aeronautics and Space Administration’s (NASA) mast camera (Mastcam) imaging system, onboard the Mars Science Laboratory (MSL) rover Curiosity, a Bayer pattern filter is being used to capture the RGB (red,...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-03-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2079-9292/8/3/308 |
| _version_ | 1811185248570966016 |
|---|---|
| author | Chiman Kwan Bryan Chou James F. Bell III |
| author_facet | Chiman Kwan Bryan Chou James F. Bell III |
| author_sort | Chiman Kwan |
| collection | DOAJ |
| description | Bayer pattern filters have been used in many commercial digital cameras. In National Aeronautics and Space Administration’s (NASA) mast camera (Mastcam) imaging system, onboard the Mars Science Laboratory (MSL) rover Curiosity, a Bayer pattern filter is being used to capture the RGB (red, green, and blue) color of scenes on Mars. The Mastcam has two cameras: left and right. The right camera has three times better resolution than that of the left. It is well known that demosaicing introduces color and zipper artifacts. Here, we present a comparative study of demosaicing results using conventional and deep learning algorithms. Sixteen left and 15 right Mastcam images were used in our experiments. Due to a lack of ground truth images for Mastcam data from Mars, we compared the various algorithms using a blind image quality assessment model. It was observed that no one algorithm can work the best for all images. In particular, a deep learning-based algorithm worked the best for the right Mastcam images and a conventional algorithm achieved the best results for the left Mastcam images. Moreover, subjective evaluation of five demosaiced Mastcam images was also used to compare the various algorithms. |
| first_indexed | 2024-04-11T13:27:20Z |
| format | Article |
| id | doaj.art-f32bcb6d23b5479aa2d0905090b997af |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-04-11T13:27:20Z |
| publishDate | 2019-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-f32bcb6d23b5479aa2d0905090b997af2022-12-22T04:22:02ZengMDPI AGElectronics2079-92922019-03-018330810.3390/electronics8030308electronics8030308Comparison of Deep Learning and Conventional Demosaicing Algorithms for Mastcam ImagesChiman Kwan0Bryan Chou1James F. Bell III2Applied Research LLC, Rockville, MD 20850, USAApplied Research LLC, Rockville, MD 20850, USASchool of Earth and Space Exploration, Arizona State University, Tempe, AZ 85287, USABayer pattern filters have been used in many commercial digital cameras. In National Aeronautics and Space Administration’s (NASA) mast camera (Mastcam) imaging system, onboard the Mars Science Laboratory (MSL) rover Curiosity, a Bayer pattern filter is being used to capture the RGB (red, green, and blue) color of scenes on Mars. The Mastcam has two cameras: left and right. The right camera has three times better resolution than that of the left. It is well known that demosaicing introduces color and zipper artifacts. Here, we present a comparative study of demosaicing results using conventional and deep learning algorithms. Sixteen left and 15 right Mastcam images were used in our experiments. Due to a lack of ground truth images for Mastcam data from Mars, we compared the various algorithms using a blind image quality assessment model. It was observed that no one algorithm can work the best for all images. In particular, a deep learning-based algorithm worked the best for the right Mastcam images and a conventional algorithm achieved the best results for the left Mastcam images. Moreover, subjective evaluation of five demosaiced Mastcam images was also used to compare the various algorithms.http://www.mdpi.com/2079-9292/8/3/308debayeringcuriosity roverdemosaicingfusionMastcamimage enhancementdeep learning |
| spellingShingle | Chiman Kwan Bryan Chou James F. Bell III Comparison of Deep Learning and Conventional Demosaicing Algorithms for Mastcam Images Electronics debayering curiosity rover demosaicing fusion Mastcam image enhancement deep learning |
| title | Comparison of Deep Learning and Conventional Demosaicing Algorithms for Mastcam Images |
| title_full | Comparison of Deep Learning and Conventional Demosaicing Algorithms for Mastcam Images |
| title_fullStr | Comparison of Deep Learning and Conventional Demosaicing Algorithms for Mastcam Images |
| title_full_unstemmed | Comparison of Deep Learning and Conventional Demosaicing Algorithms for Mastcam Images |
| title_short | Comparison of Deep Learning and Conventional Demosaicing Algorithms for Mastcam Images |
| title_sort | comparison of deep learning and conventional demosaicing algorithms for mastcam images |
| topic | debayering curiosity rover demosaicing fusion Mastcam image enhancement deep learning |
| url | http://www.mdpi.com/2079-9292/8/3/308 |
| work_keys_str_mv | AT chimankwan comparisonofdeeplearningandconventionaldemosaicingalgorithmsformastcamimages AT bryanchou comparisonofdeeplearningandconventionaldemosaicingalgorithmsformastcamimages AT jamesfbelliii comparisonofdeeplearningandconventionaldemosaicingalgorithmsformastcamimages |