FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4315781540> ?p ?o ?g. }

• W4315781540 endingPage "440" @default.
• W4315781540 startingPage "440" @default.
• W4315781540 abstract "Fast and high-accuracy detection of underwater targets based on side scan sonar images has great potential for marine fisheries, underwater security, marine mapping, underwater engineering and other applications. The following problems, however, must be addressed when using low-resolution side scan sonar images for underwater target detection: (1) the detection performance is limited due to the restriction on the input of multi-scale images; (2) the widely used deep learning algorithms have a low detection effect due to their complex convolution layer structures; (3) the detection performance is limited due to insufficient model complexity in training process; and (4) the number of samples is not enough because of the bad dataset preprocessing methods. To solve these problems, an improved neural network for underwater target detection—which is based on side scan sonar images and fully utilizes spatial pyramid pooling and online dataset preprocessing based on the You Look Only Once version three (YOLO V3) algorithm—is proposed. The methodology of the proposed approach is as follows: (1) the AlexNet, GoogleNet, VGGNet and the ResNet networks and an adopted YOLO V3 algorithm were the backbone networks. The structure of the YOLO V3 model is more mature and compact and has higher target detection accuracy and better detection efficiency than the other models; (2) spatial pyramid pooling was added at the end of the convolution layer to improve detection performance. Spatial pyramid pooling breaks the scale restrictions when inputting images to improve feature extraction because spatial pyramid pooling enables the backbone network to learn faster at high accuracy; and (3) online dataset preprocessing based on YOLO V3 with spatial pyramid pooling increases the number of samples and improves the complexity of the model to further improve detection process performance. Three-side scan imagery datasets were used for training and were tested in experiments. The quantitative evaluation using Accuracy, Recall, Precision, mAP and F1-Score metrics indicates that: for the AlexNet, GoogleNet, VGGNet and ResNet algorithms, when spatial pyramid pooling is added to their backbone networks, the average detection accuracy of the three sets of data was improved by 2%, 4%, 2% and 2%, respectively, as compared to their original formulations. Compared with the original YOLO V3 model, the proposed ODP+YOLO V3+SPP underwater target detection algorithm model has improved detection performance through the mAP qualitative evaluation index has increased by 6%, the Precision qualitative evaluation index has increased by 13%, and the detection efficiency has increased by 9.34%. These demonstrate that adding spatial pyramid pooling and online dataset preprocessing can improve the target detection accuracy of these commonly used algorithms. The proposed, improved neural network with spatial pyramid pooling and online dataset preprocessing based on the YOLO V3 method achieves the highest scores for underwater target detection results for sunken ships, fish flocks and seafloor topography, with mAP scores of 98%, 91% and 96% for the above three kinds of datasets, respectively." @default.
• W4315781540 created "2023-01-13" @default.
• W4315781540 creator A5015182080 @default.
• W4315781540 creator A5035664262 @default.
• W4315781540 creator A5035672412 @default.
• W4315781540 creator A5058010200 @default.
• W4315781540 creator A5070369693 @default.
• W4315781540 creator A5075945352 @default.
• W4315781540 creator A5082938331 @default.
• W4315781540 creator A5086797639 @default.
• W4315781540 date "2023-01-11" @default.
• W4315781540 modified "2023-10-16" @default.
• W4315781540 title "Improved Neural Network with Spatial Pyramid Pooling and Online Datasets Preprocessing for Underwater Target Detection Based on Side Scan Sonar Imagery" @default.
• W4315781540 cites W1930528368 @default.
• W4315781540 cites W1965126626 @default.
• W4315781540 cites W1974307287 @default.
• W4315781540 cites W2018135653 @default.
• W4315781540 cites W2019117580 @default.
• W4315781540 cites W2046119925 @default.
• W4315781540 cites W2064046252 @default.
• W4315781540 cites W2087731396 @default.
• W4315781540 cites W2109255472 @default.
• W4315781540 cites W2132847054 @default.
• W4315781540 cites W2412479940 @default.
• W4315781540 cites W2464755555 @default.
• W4315781540 cites W2558580397 @default.
• W4315781540 cites W2588557298 @default.
• W4315781540 cites W2597769985 @default.
• W4315781540 cites W2747872086 @default.
• W4315781540 cites W2783265781 @default.
• W4315781540 cites W2789876780 @default.
• W4315781540 cites W2790710362 @default.
• W4315781540 cites W2798371872 @default.
• W4315781540 cites W2805508018 @default.
• W4315781540 cites W2806354237 @default.
• W4315781540 cites W2890474333 @default.
• W4315781540 cites W2891315279 @default.
• W4315781540 cites W2894651257 @default.
• W4315781540 cites W2902459419 @default.
• W4315781540 cites W2905499766 @default.
• W4315781540 cites W2905544033 @default.
• W4315781540 cites W2908524565 @default.
• W4315781540 cites W2922073769 @default.
• W4315781540 cites W2940927643 @default.
• W4315781540 cites W2943210864 @default.
• W4315781540 cites W2963771536 @default.
• W4315781540 cites W2968648382 @default.
• W4315781540 cites W2972623730 @default.
• W4315781540 cites W2972838552 @default.
• W4315781540 cites W2996444175 @default.
• W4315781540 cites W3004591935 @default.
• W4315781540 cites W3009131247 @default.
• W4315781540 cites W3012472557 @default.
• W4315781540 cites W3013467123 @default.
• W4315781540 cites W3021941048 @default.
• W4315781540 cites W3035156651 @default.
• W4315781540 cites W3035422681 @default.
• W4315781540 cites W3044680161 @default.
• W4315781540 cites W3046857037 @default.
• W4315781540 cites W3048717798 @default.
• W4315781540 cites W3090532574 @default.
• W4315781540 cites W3095056294 @default.
• W4315781540 cites W3109055651 @default.
• W4315781540 cites W3111032204 @default.
• W4315781540 cites W3133256990 @default.
• W4315781540 cites W3135410486 @default.
• W4315781540 cites W3148703355 @default.
• W4315781540 cites W3165909822 @default.
• W4315781540 cites W3180954604 @default.
• W4315781540 cites W3197539865 @default.
• W4315781540 cites W3198258937 @default.
• W4315781540 cites W3203183117 @default.
• W4315781540 cites W3209885737 @default.
• W4315781540 cites W3210550848 @default.
• W4315781540 cites W3214849203 @default.
• W4315781540 cites W4200006813 @default.
• W4315781540 cites W4200545987 @default.
• W4315781540 cites W4280534250 @default.
• W4315781540 cites W4280601076 @default.
• W4315781540 cites W4292247424 @default.
• W4315781540 cites W4295129612 @default.
• W4315781540 cites W4308441228 @default.
• W4315781540 cites W4312677938 @default.
• W4315781540 cites W2602847783 @default.
• W4315781540 doi "https://doi.org/10.3390/rs15020440" @default.
• W4315781540 hasPublicationYear "2023" @default.
• W4315781540 type Work @default.
• W4315781540 citedByCount "10" @default.
• W4315781540 countsByYear W43157815402023 @default.
• W4315781540 crossrefType "journal-article" @default.
• W4315781540 hasAuthorship W4315781540A5015182080 @default.
• W4315781540 hasAuthorship W4315781540A5035664262 @default.
• W4315781540 hasAuthorship W4315781540A5035672412 @default.
• W4315781540 hasAuthorship W4315781540A5058010200 @default.
• W4315781540 hasAuthorship W4315781540A5070369693 @default.
• W4315781540 hasAuthorship W4315781540A5075945352 @default.
• W4315781540 hasAuthorship W4315781540A5082938331 @default.
• W4315781540 hasAuthorship W4315781540A5086797639 @default.

• next