Matches in SemOpenAlex for { <https://semopenalex.org/work/W4283722204> ?p ?o ?g. }
- W4283722204 endingPage "7912" @default.
- W4283722204 startingPage "7912" @default.
- W4283722204 abstract "For accurate and effective automatic vehicle identification, morphological detection and deep convolutional networks were combined to propose a method for locating and identifying vehicle models from unmanned aerial vehicle (UAV) videos. First, the region of interest of the video frame image was sketched and grey-scale processing was performed; sub-pixel-level skeleton images were generated based on the Canny edge detection results of the region of interest; then, the image skeletons were decomposed and reconstructed. Second, a combination of morphological operations and connected domain morphological features were applied for vehicle target recognition, and a deep learning image benchmark library containing 244,520 UAV video vehicle samples was constructed. Third, we improved the AlexNet model by adding convolutional layers, pooling layers, and adjusting network parameters, which we named AlexNet*. Finally, a vehicle recognition method was established based on a candidate target extraction algorithm with AlexNet*. The validation analysis revealed that AlexNet* achieved a mean F1 of 85.51% for image classification, outperforming AlexNet (82.54%), LeNet (63.88%), CaffeNet (46.64%), VGG16 (16.67%), and GoogLeNet (14.38%). The mean values of Pcor, Pre, and Pmiss for cars and buses reached 94.63%, 6.87%, and 4.40%, respectively, proving that this method can effectively identify UAV video targets." @default.
- W4283722204 created "2022-07-01" @default.
- W4283722204 creator A5018558510 @default.
- W4283722204 creator A5031229827 @default.
- W4283722204 creator A5083605950 @default.
- W4283722204 creator A5086236332 @default.
- W4283722204 date "2022-06-29" @default.
- W4283722204 modified "2023-10-15" @default.
- W4283722204 title "Vehicle Recognition from Unmanned Aerial Vehicle Videos Based on Fusion of Target Pre-Detection and Deep Learning" @default.
- W4283722204 cites W2012708800 @default.
- W4283722204 cites W2017745767 @default.
- W4283722204 cites W2032432801 @default.
- W4283722204 cites W2038642313 @default.
- W4283722204 cites W2049773954 @default.
- W4283722204 cites W2057121930 @default.
- W4283722204 cites W2065324030 @default.
- W4283722204 cites W2133059825 @default.
- W4283722204 cites W2155195832 @default.
- W4283722204 cites W2293579146 @default.
- W4283722204 cites W2605995529 @default.
- W4283722204 cites W2618530766 @default.
- W4283722204 cites W2741245733 @default.
- W4283722204 cites W2788055254 @default.
- W4283722204 cites W2798027129 @default.
- W4283722204 cites W2801303340 @default.
- W4283722204 cites W2891527471 @default.
- W4283722204 cites W2915476573 @default.
- W4283722204 cites W2950418233 @default.
- W4283722204 cites W2952743010 @default.
- W4283722204 cites W3011824281 @default.
- W4283722204 cites W3015842520 @default.
- W4283722204 cites W3119427296 @default.
- W4283722204 cites W3167368946 @default.
- W4283722204 cites W4250615654 @default.
- W4283722204 cites W4376848448 @default.
- W4283722204 doi "https://doi.org/10.3390/su14137912" @default.
- W4283722204 hasPublicationYear "2022" @default.
- W4283722204 type Work @default.
- W4283722204 citedByCount "0" @default.
- W4283722204 crossrefType "journal-article" @default.
- W4283722204 hasAuthorship W4283722204A5018558510 @default.
- W4283722204 hasAuthorship W4283722204A5031229827 @default.
- W4283722204 hasAuthorship W4283722204A5083605950 @default.
- W4283722204 hasAuthorship W4283722204A5086236332 @default.
- W4283722204 hasBestOaLocation W42837222041 @default.
- W4283722204 hasConcept C108583219 @default.
- W4283722204 hasConcept C115961682 @default.
- W4283722204 hasConcept C126042441 @default.
- W4283722204 hasConcept C13280743 @default.
- W4283722204 hasConcept C14705441 @default.
- W4283722204 hasConcept C153180895 @default.
- W4283722204 hasConcept C154945302 @default.
- W4283722204 hasConcept C185798385 @default.
- W4283722204 hasConcept C193536780 @default.
- W4283722204 hasConcept C205649164 @default.
- W4283722204 hasConcept C2776429412 @default.
- W4283722204 hasConcept C31972630 @default.
- W4283722204 hasConcept C41008148 @default.
- W4283722204 hasConcept C52622490 @default.
- W4283722204 hasConcept C76155785 @default.
- W4283722204 hasConcept C81363708 @default.
- W4283722204 hasConcept C9417928 @default.
- W4283722204 hasConceptScore W4283722204C108583219 @default.
- W4283722204 hasConceptScore W4283722204C115961682 @default.
- W4283722204 hasConceptScore W4283722204C126042441 @default.
- W4283722204 hasConceptScore W4283722204C13280743 @default.
- W4283722204 hasConceptScore W4283722204C14705441 @default.
- W4283722204 hasConceptScore W4283722204C153180895 @default.
- W4283722204 hasConceptScore W4283722204C154945302 @default.
- W4283722204 hasConceptScore W4283722204C185798385 @default.
- W4283722204 hasConceptScore W4283722204C193536780 @default.
- W4283722204 hasConceptScore W4283722204C205649164 @default.
- W4283722204 hasConceptScore W4283722204C2776429412 @default.
- W4283722204 hasConceptScore W4283722204C31972630 @default.
- W4283722204 hasConceptScore W4283722204C41008148 @default.
- W4283722204 hasConceptScore W4283722204C52622490 @default.
- W4283722204 hasConceptScore W4283722204C76155785 @default.
- W4283722204 hasConceptScore W4283722204C81363708 @default.
- W4283722204 hasConceptScore W4283722204C9417928 @default.
- W4283722204 hasFunder F4320321001 @default.
- W4283722204 hasIssue "13" @default.
- W4283722204 hasLocation W42837222041 @default.
- W4283722204 hasLocation W42837222042 @default.
- W4283722204 hasOpenAccess W4283722204 @default.
- W4283722204 hasPrimaryLocation W42837222041 @default.
- W4283722204 hasRelatedWork W2080322084 @default.
- W4283722204 hasRelatedWork W2279398222 @default.
- W4283722204 hasRelatedWork W2340360913 @default.
- W4283722204 hasRelatedWork W2763966779 @default.
- W4283722204 hasRelatedWork W3146545704 @default.
- W4283722204 hasRelatedWork W3156786002 @default.
- W4283722204 hasRelatedWork W4299822940 @default.
- W4283722204 hasRelatedWork W4320731732 @default.
- W4283722204 hasRelatedWork W4366492315 @default.
- W4283722204 hasRelatedWork W4368362586 @default.
- W4283722204 hasVolume "14" @default.
- W4283722204 isParatext "false" @default.
- W4283722204 isRetracted "false" @default.