A New Method of Different Neural Network Depth and Feature Map Size on Remote Sensing Small Target Detection

<?xml version="1.0" encoding="UTF-8"?><modsCollection xmlns="http://www.loc.gov/mods/v3" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.loc.gov/mods/v3 http://www.loc.gov/standards/mods/v3/mods-3-8.xsd">
<mods version="3.8">
<titleInfo>
<title>A New Method of Different Neural Network Depth and Feature Map Size on Remote Sensing Small Target Detection</title>
</titleInfo>
<name type="personal" usage="primary" xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="MAPA20210034671">
<namePart>Cao, Yaming</namePart>
<nameIdentifier>MAPA20210034671</nameIdentifier>
</name>
<name type="personal" xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="MAPA20210034688">
<namePart>Yang, Zhen</namePart>
<nameIdentifier>MAPA20210034688</nameIdentifier>
</name>
<name type="personal" xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="MAPA20210034695">
<namePart>Gao, Chen</namePart>
<nameIdentifier>MAPA20210034695</nameIdentifier>
</name>
<typeOfResource>text</typeOfResource>
<genre authority="marcgt">periodical</genre>
<originInfo>
<place>
<placeTerm type="code" authority="marccountry">esp</placeTerm>
</place>
<dateIssued encoding="marc">2021</dateIssued>
<issuance>serial</issuance>
</originInfo>
<language>
<languageTerm type="code" authority="iso639-2b">spa</languageTerm>
</language>
<physicalDescription>
<form authority="marcform">print</form>
<internetMediaType>application/pdf</internetMediaType>
</physicalDescription>
<abstract displayLabel="Summary">Convolutional neural networks (CNNs) have shown strong learning capabilities in computer vision tasks such as classification and detection. Especially with the introduction of excellent detection models such as YOLO (V1, V2 and V3) and Faster R-CNN, CNNs have greatly improved detection efficiency and accuracy. However, due to the special angle of view, small size, few features, and complicated background, CNNs that performs well in the ground perspective dataset, fails to reach a good detection accuracy in the remote sensing image dataset. To this end, based on the YOLO V3 model, we used feature maps of different depths as detection outputs to explore the reasons for the poor detection rate of small targets in remote sensing images by deep neural networks. We also analyzed the effect of neural network depth on small target detection, and found that the excessive deep semantic information of neural network has little effect on small target detection. Finally, the verification on the VEDAI dataset shows, that the fusion of shallow feature maps with precise location information and deep feature maps with rich semantics in the CNNs can effectively improve the accuracy of small target detection in remote sensing images.

</abstract>
<accessCondition type="use and reproduction">La copia digital se distribuye bajo licencia "Attribution 4.0 International (CC BY NC 4.0)"</accessCondition>
<note type="statement of responsibility">Yaming Cao, Zhen Yang, Chen Gao</note>
<subject xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="MAPA20080611200">
<topic>Inteligencia artificial</topic>
</subject>
<classification authority="">922.134</classification>
<relatedItem type="host">
<titleInfo>
<title>Revista Iberoamericana de Inteligencia Artificial</title>
</titleInfo>
<originInfo>
<publisher> : IBERAMIA, Sociedad Iberoamericana de Inteligencia Artificial , 2018-</publisher>
</originInfo>
<identifier type="issn">1988-3064</identifier>
<identifier type="local">MAP20200034445</identifier>
<part>
<text>04/10/2021 Volumen 24 Número 68 - octubre 2021 , p. 21-32</text>
</part>
</relatedItem>
<recordInfo>
<recordContentSource authority="marcorg">MAP</recordContentSource>
<recordCreationDate encoding="marc">211027</recordCreationDate>
<recordChangeDate encoding="iso8601">20220911185812.0</recordChangeDate>
<recordIdentifier source="MAP">MAP20210031236</recordIdentifier>
<languageOfCataloging>
<languageTerm type="code" authority="iso639-2b">spa</languageTerm>
</languageOfCataloging>
</recordInfo>
</mods>
</modsCollection>