FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3206508052> ?p ?o ?g. }

• W3206508052 endingPage "8344" @default.
• W3206508052 startingPage "8318" @default.
• W3206508052 abstract "The land cover classification of very high-resolution (VHR) remote sensing images is a challenging task. VHR images depict many complex objects with various shapes in complicated contexts. The deep learning-based method is a solution for such dif- ficult task and feature extraction. Nevertheless, this method cannot efficiently deal with images with complex scene structures. An improved object-based convolutional neural network (IOCNN) is designed to classify VHR images with zone division and convolutional position sampling techniques in this study. The method can achieve the best performance of each zone at its own optimized scales. Based on multi-scale convolutional deep features extracted from VHR images, the objects with irregular shapes can be classified using the approach. In this study, the zone-level scale adaption and multi-scale recognition of complex objects are achieved. The performance of IOCNN is compared with the state-of-the-art methods for feature extraction, including five object-based CNN approaches and two fully convolutional networks (FCNs). The results show that the classification performance of IOCNN is considerably stronger than that of state-of-the-art methods. The overall accuracies of the land cover classification in IOCNN are 91.65% and 93.49% on two tested images. The results demonstrate the practicability of IOCNN." @default.
• W3206508052 created "2021-10-25" @default.
• W3206508052 creator A5025493288 @default.
• W3206508052 creator A5026947952 @default.
• W3206508052 creator A5041407693 @default.
• W3206508052 creator A5053986999 @default.
• W3206508052 creator A5070629154 @default.
• W3206508052 creator A5076752167 @default.
• W3206508052 date "2021-10-02" @default.
• W3206508052 modified "2023-10-16" @default.
• W3206508052 title "Improved object-based convolutional neural network (IOCNN) to classify very high-resolution remote sensing images" @default.
• W3206508052 cites W1707683952 @default.
• W3206508052 cites W1843514792 @default.
• W3206508052 cites W1901129140 @default.
• W3206508052 cites W1903029394 @default.
• W3206508052 cites W1958291604 @default.
• W3206508052 cites W1984792953 @default.
• W3206508052 cites W2044465660 @default.
• W3206508052 cites W2045804185 @default.
• W3206508052 cites W2090424610 @default.
• W3206508052 cites W2096102763 @default.
• W3206508052 cites W2103079830 @default.
• W3206508052 cites W2267317359 @default.
• W3206508052 cites W2500751094 @default.
• W3206508052 cites W2518897583 @default.
• W3206508052 cites W2538244214 @default.
• W3206508052 cites W2564730549 @default.
• W3206508052 cites W2597229673 @default.
• W3206508052 cites W2598551616 @default.
• W3206508052 cites W2607990087 @default.
• W3206508052 cites W2608922915 @default.
• W3206508052 cites W2648242067 @default.
• W3206508052 cites W2760923572 @default.
• W3206508052 cites W2770315464 @default.
• W3206508052 cites W2782934949 @default.
• W3206508052 cites W2789436332 @default.
• W3206508052 cites W2790722307 @default.
• W3206508052 cites W2791006446 @default.
• W3206508052 cites W2791592925 @default.
• W3206508052 cites W2792365373 @default.
• W3206508052 cites W2793445582 @default.
• W3206508052 cites W2793461576 @default.
• W3206508052 cites W2794055043 @default.
• W3206508052 cites W2796232579 @default.
• W3206508052 cites W2803946774 @default.
• W3206508052 cites W2804846062 @default.
• W3206508052 cites W2807619972 @default.
• W3206508052 cites W2810004461 @default.
• W3206508052 cites W2883105896 @default.
• W3206508052 cites W2891367133 @default.
• W3206508052 cites W2899101283 @default.
• W3206508052 cites W2901605078 @default.
• W3206508052 cites W2902055884 @default.
• W3206508052 cites W2909143073 @default.
• W3206508052 cites W2910666603 @default.
• W3206508052 cites W2912834795 @default.
• W3206508052 cites W2914757358 @default.
• W3206508052 cites W2914812315 @default.
• W3206508052 cites W2915971115 @default.
• W3206508052 cites W2919115771 @default.
• W3206508052 cites W2939520333 @default.
• W3206508052 cites W2940726923 @default.
• W3206508052 cites W2943484762 @default.
• W3206508052 cites W2945225376 @default.
• W3206508052 cites W2952045193 @default.
• W3206508052 cites W2963881378 @default.
• W3206508052 cites W2964808389 @default.
• W3206508052 cites W2990979713 @default.
• W3206508052 cites W2991488782 @default.
• W3206508052 cites W3007923660 @default.
• W3206508052 cites W3014060899 @default.
• W3206508052 cites W318364127 @default.
• W3206508052 doi "https://doi.org/10.1080/01431161.2021.1951879" @default.
• W3206508052 hasPublicationYear "2021" @default.
• W3206508052 type Work @default.
• W3206508052 sameAs 3206508052 @default.
• W3206508052 citedByCount "9" @default.
• W3206508052 countsByYear W32065080522022 @default.
• W3206508052 countsByYear W32065080522023 @default.
• W3206508052 crossrefType "journal-article" @default.
• W3206508052 hasAuthorship W3206508052A5025493288 @default.
• W3206508052 hasAuthorship W3206508052A5026947952 @default.
• W3206508052 hasAuthorship W3206508052A5041407693 @default.
• W3206508052 hasAuthorship W3206508052A5053986999 @default.
• W3206508052 hasAuthorship W3206508052A5070629154 @default.
• W3206508052 hasAuthorship W3206508052A5076752167 @default.
• W3206508052 hasConcept C108583219 @default.
• W3206508052 hasConcept C115961682 @default.
• W3206508052 hasConcept C127413603 @default.
• W3206508052 hasConcept C138885662 @default.
• W3206508052 hasConcept C147176958 @default.
• W3206508052 hasConcept C153180895 @default.
• W3206508052 hasConcept C154945302 @default.
• W3206508052 hasConcept C162324750 @default.
• W3206508052 hasConcept C187736073 @default.
• W3206508052 hasConcept C205649164 @default.
• W3206508052 hasConcept C2776401178 @default.
• W3206508052 hasConcept C2778755073 @default.

• next