<?xml version='1.0' encoding='UTF-8'?>
<OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd">
  <responseDate>2026-04-20T22:54:54Z</responseDate>
  <request verb="GetRecord" metadataPrefix="jpcoar_1.0" identifier="oai:ipsj.ixsq.nii.ac.jp:02001756">https://ipsj.ixsq.nii.ac.jp/oai</request>
  <GetRecord>
    <record>
      <header>
        <identifier>oai:ipsj.ixsq.nii.ac.jp:02001756</identifier>
        <datestamp>2025-05-01T05:06:53Z</datestamp>
        <setSpec>581:11839:11843</setSpec>
      </header>
      <metadata>
        <jpcoar:jpcoar xmlns:datacite="https://schema.datacite.org/meta/kernel-4/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:dcndl="http://ndl.go.jp/dcndl/terms/" xmlns:dcterms="http://purl.org/dc/terms/" xmlns:jpcoar="https://github.com/JPCOAR/schema/blob/master/1.0/" xmlns:oaire="http://namespace.openaire.eu/schema/oaire/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:rioxxterms="http://www.rioxx.net/schema/v2.0/rioxxterms/" xmlns:xs="http://www.w3.org/2001/XMLSchema" xmlns="https://github.com/JPCOAR/schema/blob/master/1.0/" xsi:schemaLocation="https://github.com/JPCOAR/schema/blob/master/1.0/jpcoar_scm.xsd">
          <dc:title xml:lang="ja">深層学習と車載超音波センサによる歩行者検出手法</dc:title>
          <dc:title xml:lang="en">Pedestrian Detection Method Using Deep Learning and Automotive Ultrasonic Sensors</dc:title>
          <jpcoar:creator>
            <jpcoar:creatorName>浅利,一斗</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName>菅江,一平</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName>井奈波,恒</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName>高須,淳宏</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName>橋爪,宏達</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName>杉本,雅則</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName xml:lang="en">Kazuto Asari</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName xml:lang="en">Ippei Sugae</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName xml:lang="en">Hisashi Inaba</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName xml:lang="en">Atsuhiro Takasu</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName xml:lang="en">Hiromichi Hashizume</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName xml:lang="en">Masanori Sugimoto</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:subject subjectScheme="Other">[一般論文] 超音波センシング，距離減衰，synthetic data generation，Convolutional LSTM</jpcoar:subject>
          <datacite:description descriptionType="Other">自動運転や先進運転支援システムの実現において各種車載センサは重要な役割を担う．超音波センシングはその中でも主に低速域で用いられる手法である．発信から受信までの時刻差を基に反射体の距離を計算するのが手法の原理であるため，現状で得られる情報は反射体の有無とその位置情報のみとなっている．一方で，超音波反射波には単純な飛行時間以外にも多くの情報を含んでいると考えられる．本稿では車載センサとしての応用を目指し，受信波形をConvolutional LSTMによって分類することによる歩行者の検出手法を提案する．また，アクティブ音響センシングにおいて深層学習を用いる際に遭遇するデータ収集の課題を示し，これを解決するための合成データセット作成手法を提案する．これらの手法により，人形の存在不在と存在位置によって定義された4クラスに属する30種類の反射体配置に対して，4値分類正確度92.75%，存在不在の2値分類正確度98.25%で人形の検出が可能であることを確認した．また，床面環境が取得波形に与える影響を示した．</datacite:description>
          <datacite:description descriptionType="Other">Various in-vehicle sensors play an important role in the realization of automatic driving and advanced driver assistance systems. Ultrasonic sensing is a method mainly used at low speeds. Since the principle of the method is to calculate the distance to a reflector based on the time difference between signal transmission and reception, the only information used by automobiles currently available in the market is the presence or absence of the reflector and its location. We propose a method for simultaneous pedestrian detection and distance estimation by using convolutional LSTM classification, and a synthetic data generation method for solving the data collection problems encountered when using deep learning in active acoustic sensing. The proposed method can detect pedestrian dummies with a 4-value classification accuracy of 92.75% and a 2-value classification accuracy of 98.25% in the 30 obstacle configurations categorized to the 4 classes defined by the presence/absence and its location.</datacite:description>
          <dc:publisher xml:lang="ja">情報処理学会</dc:publisher>
          <datacite:date dateType="Issued">2025-04-15</datacite:date>
          <dc:language>jpn</dc:language>
          <dc:type rdf:resource="http://purl.org/coar/resource_type/c_6501">journal article</dc:type>
          <jpcoar:identifier identifierType="DOI">https://doi.org/10.20729/0002001756</jpcoar:identifier>
          <jpcoar:identifier identifierType="URI">https://ipsj.ixsq.nii.ac.jp/records/2001756</jpcoar:identifier>
          <jpcoar:identifierRegistration identifierType="JaLC">10.20729/0002001756</jpcoar:identifierRegistration>
          <jpcoar:sourceIdentifier identifierType="ISSN">1882-7764</jpcoar:sourceIdentifier>
          <jpcoar:sourceIdentifier identifierType="NCID">AN00116647</jpcoar:sourceIdentifier>
          <jpcoar:sourceTitle>情報処理学会論文誌</jpcoar:sourceTitle>
          <jpcoar:volume>66</jpcoar:volume>
          <jpcoar:issue>4</jpcoar:issue>
          <jpcoar:pageStart>722</jpcoar:pageStart>
          <jpcoar:pageEnd>734</jpcoar:pageEnd>
          <jpcoar:file>
            <jpcoar:URI label="IPSJ-JNL6604012.pdf">https://ipsj.ixsq.nii.ac.jp/record/2001756/files/IPSJ-JNL6604012.pdf</jpcoar:URI>
            <jpcoar:mimeType>application/pdf</jpcoar:mimeType>
            <jpcoar:extent>24.6 MB</jpcoar:extent>
            <datacite:date dateType="Available">2027-04-15</datacite:date>
          </jpcoar:file>
        </jpcoar:jpcoar>
      </metadata>
    </record>
  </GetRecord>
</OAI-PMH>
