基于语义似然与高精度地图匹配的智能车辆同时定位与检测
TP242.6; 车载传感器数据与高精度地图的精确匹配是提升智能车辆感知与定位的关键.提出基于语义似然模型(SLM)的高精度地图匹配新算法,实现智能车辆同时定位与目标检测任务.首先通过U-Net提取路面语义目标,利用核密度估计建立SLM.基于粒子滤波框架,利用位姿变换将高精度地图上目标抽样点映射至SLM中,计算该抽样点与传感器数据的匹配程度对每个粒子的权重更新,实现智能车辆的高精度定位.最后利用定位结果完成地图上的要素目标到图像的映射,实现目标的精准检测.利用在校园道路与城市道路环境下采集的数据对所提算法进行验证,实验结果表明,算法的平均定位误差约为14 cm,路面路标检测结果平均交并比(MI...
Saved in:
| Published in | 上海交通大学学报 Vol. 58; no. 10; pp. 1618 - 1628 |
|---|---|
| Main Authors | , , , , |
| Format | Journal Article |
| Language | Chinese |
| Published |
武汉理工大学重庆研究院,重庆 401120
28.10.2024
武汉理工大学信息工程学院,武汉 430070 武汉理工大学智能交通系统研究中心,武汉 430063%武汉理工大学智能交通系统研究中心,武汉 430063 |
| Subjects | |
| Online Access | Get full text |
| ISSN | 1006-2467 |
| DOI | 10.16183/j.cnki.jsjtu.2023.086 |
Cover
| Abstract | TP242.6; 车载传感器数据与高精度地图的精确匹配是提升智能车辆感知与定位的关键.提出基于语义似然模型(SLM)的高精度地图匹配新算法,实现智能车辆同时定位与目标检测任务.首先通过U-Net提取路面语义目标,利用核密度估计建立SLM.基于粒子滤波框架,利用位姿变换将高精度地图上目标抽样点映射至SLM中,计算该抽样点与传感器数据的匹配程度对每个粒子的权重更新,实现智能车辆的高精度定位.最后利用定位结果完成地图上的要素目标到图像的映射,实现目标的精准检测.利用在校园道路与城市道路环境下采集的数据对所提算法进行验证,实验结果表明,算法的平均定位误差约为14 cm,路面路标检测结果平均交并比(MIoU)均大于80.较之深度神经网络等当前最佳(SOTA)的检测方法,所提算法引入高精度地图的先验信息可显著提升智能车辆定位与目标检测性能. |
|---|---|
| AbstractList | TP242.6; 车载传感器数据与高精度地图的精确匹配是提升智能车辆感知与定位的关键.提出基于语义似然模型(SLM)的高精度地图匹配新算法,实现智能车辆同时定位与目标检测任务.首先通过U-Net提取路面语义目标,利用核密度估计建立SLM.基于粒子滤波框架,利用位姿变换将高精度地图上目标抽样点映射至SLM中,计算该抽样点与传感器数据的匹配程度对每个粒子的权重更新,实现智能车辆的高精度定位.最后利用定位结果完成地图上的要素目标到图像的映射,实现目标的精准检测.利用在校园道路与城市道路环境下采集的数据对所提算法进行验证,实验结果表明,算法的平均定位误差约为14 cm,路面路标检测结果平均交并比(MIoU)均大于80.较之深度神经网络等当前最佳(SOTA)的检测方法,所提算法引入高精度地图的先验信息可显著提升智能车辆定位与目标检测性能. |
| Abstract_FL | Accurate matching between in-vehicle sensor data and high-definition(HD)maps is crucial to improve the performance of perception and localization of intelligent vehicles.A novel algorithm of HD map matching based on the developed semantic likelihood model(SLM)is proposed to achieve intelligent vehicle localization and object detection simultaneously.First,semantic pavement objects are extracted from front-view images by using U-Net,and SLM is constructed with kernel density estimation(KDE).Under a particle filter framework,the likelihood between the sensor data and HD map is calculated by projecting each sample point from HD map with pose transformation onto SLM to update the weight of each particle.Simultaneously,accurate detection of pavement markings is accomplished by projecting all elements onto the HD map with the computed localization results.In the experiment,data collected on campus and on urban roads are used to validate the proposed algorithm.The experimental results show that the localization errors in both scenarios are about 14 cm,and the mean intersection over union(MIoU)of road marking detection is above 80.The results demonstrate that the proposed algorithm can significantly improve both localization and detection performance by effectively utilizing the prior information of HD maps,compared with the state of the art(SOTA)methods,such as deep learning-based detection methods. |
| Author | 胡钊政 周哲 万金杰 任靖渊 赖国良 |
| AuthorAffiliation | 武汉理工大学信息工程学院,武汉 430070;武汉理工大学智能交通系统研究中心,武汉 430063%武汉理工大学智能交通系统研究中心,武汉 430063;武汉理工大学重庆研究院,重庆 401120 |
| AuthorAffiliation_xml | – name: 武汉理工大学信息工程学院,武汉 430070;武汉理工大学智能交通系统研究中心,武汉 430063%武汉理工大学智能交通系统研究中心,武汉 430063;武汉理工大学重庆研究院,重庆 401120 |
| Author_FL | WAN Jinjie HU Zhaozheng ZHOU Zhe REN Jingyuan LAI Guoliang |
| Author_FL_xml | – sequence: 1 fullname: LAI Guoliang – sequence: 2 fullname: HU Zhaozheng – sequence: 3 fullname: ZHOU Zhe – sequence: 4 fullname: WAN Jinjie – sequence: 5 fullname: REN Jingyuan |
| Author_xml | – sequence: 1 fullname: 赖国良 – sequence: 2 fullname: 胡钊政 – sequence: 3 fullname: 周哲 – sequence: 4 fullname: 万金杰 – sequence: 5 fullname: 任靖渊 |
| BookMark | eNotj8tKw0AYhWdRwVr7Cu5dJM4_M50Zl1K8QdGNrksm6WijpGBa7FKwCtIL7tQquBC6ES8IFhvaPk2Spm9hQFdnc853-JZQxqt5FYRWAJvAQdI117S9k6rp-m69YRJMqIklz6AsYMwNwrhYRHnfrypcAMqF5DiL9qLnIAx6ycdbOLoJx-NZaxj-9Oav97OvaRQMoqfP6HEadUbzq-6s34ofguRykkwGyfQ6uu3Ed8PovR9OuukkfrmIv9vLaEFbp34l_585dLi1eVDcMUr727vFjZLhA2bMsCVVlpRKYgYVcIAIcDBhDvCCLRjGGohNxbpQCjNFJGAtSFolimilJWiaQ6t_3HPL05Z3VHZrjTMvfSz7x27daTZVqs9Sb2D0F_oscSc |
| ClassificationCodes | TP242.6 |
| ContentType | Journal Article |
| Copyright | Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| Copyright_xml | – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| DBID | 2B. 4A8 92I 93N PSX TCJ |
| DOI | 10.16183/j.cnki.jsjtu.2023.086 |
| DatabaseName | Wanfang Data Journals - Hong Kong WANFANG Data Centre Wanfang Data Journals 万方数据期刊 - 香港版 China Online Journals (COJ) China Online Journals (COJ) |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Sciences (General) |
| DocumentTitle_FL | Simultaneous Detection and Localization for Intelligent Vehicles Based on HD Map Matching and Semantic Likelihood Model |
| EndPage | 1628 |
| ExternalDocumentID | shjtdxxb202410014 |
| GrantInformation_xml | – fundername: (国家重点研发计划); (湖北省重点研发计划项目); (重庆市科技创新重大研发项目); (武汉市人工智能创新专项) funderid: (国家重点研发计划); (湖北省重点研发计划项目); (重庆市科技创新重大研发项目); (武汉市人工智能创新专项) |
| GroupedDBID | -03 2B. 4A8 5XA 5XD 92I 93N ABJNI ACGFS ALMA_UNASSIGNED_HOLDINGS CCEZO CEKLB CW9 GROUPED_DOAJ PSX TCJ TGT U1G U5M UY8 |
| ID | FETCH-LOGICAL-s1044-c83ba88b8041e1d1271d024d165c7400f12c3797bb04b2810f720412b2fbf81f3 |
| ISSN | 1006-2467 |
| IngestDate | Thu May 29 03:56:07 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | true |
| Issue | 10 |
| Keywords | 语义似然模型 高精度地图 智能车辆定位 intelligent vehicle localization 粒子滤波 semantic likelihood model(SLM) particle filter high-definition(HD)map |
| Language | Chinese |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-s1044-c83ba88b8041e1d1271d024d165c7400f12c3797bb04b2810f720412b2fbf81f3 |
| PageCount | 11 |
| ParticipantIDs | wanfang_journals_shjtdxxb202410014 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-10-28 |
| PublicationDateYYYYMMDD | 2024-10-28 |
| PublicationDate_xml | – month: 10 year: 2024 text: 2024-10-28 day: 28 |
| PublicationDecade | 2020 |
| PublicationTitle | 上海交通大学学报 |
| PublicationTitle_FL | Journal of Shanghai Jiaotong University |
| PublicationYear | 2024 |
| Publisher | 武汉理工大学重庆研究院,重庆 401120 武汉理工大学信息工程学院,武汉 430070 武汉理工大学智能交通系统研究中心,武汉 430063%武汉理工大学智能交通系统研究中心,武汉 430063 |
| Publisher_xml | – name: 武汉理工大学智能交通系统研究中心,武汉 430063%武汉理工大学智能交通系统研究中心,武汉 430063 – name: 武汉理工大学重庆研究院,重庆 401120 – name: 武汉理工大学信息工程学院,武汉 430070 |
| SSID | ssib051367860 ssib002258139 ssib023167927 ssj0040338 ssib001128960 ssib057620143 |
| Score | 2.451588 |
| Snippet | TP242.6; 车载传感器数据与高精度地图的精确匹配是提升智能车辆感知与定位的关键.提出基于语义似然模型(SLM)的高精度地图匹配新算法,实现智能车辆同时定位与目标检测任务.... |
| SourceID | wanfang |
| SourceType | Aggregation Database |
| StartPage | 1618 |
| Title | 基于语义似然与高精度地图匹配的智能车辆同时定位与检测 |
| URI | https://d.wanfangdata.com.cn/periodical/shjtdxxb202410014 |
| Volume | 58 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals issn: 1006-2467 databaseCode: DOA dateStart: 20200101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.doaj.org/ omitProxy: true ssIdentifier: ssj0040338 providerName: Directory of Open Access Journals – providerCode: PRVEBS databaseName: Inspec with Full Text issn: 1006-2467 databaseCode: ADMLS dateStart: 20220401 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.ebsco.com/products/research-databases/inspec-full-text omitProxy: false ssIdentifier: ssib057620143 providerName: EBSCOhost |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnR1daxQxcKn1xRexfuA3RQwosuduNtkkj9neHkWwTy30rdze3lornOBdofRJsApiW3xTq-CD0BfxA8Fij7b_wH9xe73-C2dyuXaxfajCkZtNZiaTmc3ObNhMHOcmr4NXomniiqzKXFYNqVuVsuoKXG9gLBBZhruR70-E41Ps3jSfHjrxu_DV0nwrKdUWj9xX8j9WhTqwK-6S_QfL7jOFCoDBvlCChaE8lo1JzImqkEiTmGEpYxJLoitEl02NIlIZYAx_sSAS4NDUSIOsiI6IktgUURLFyBD46NBwBirPAJFtkmPIE6gkwGWkUhp5xiFRyogBbAMSlRGAEvlIpJV9hh5yQGRhxOBEx8gB5SkbhvuChUQH-BEGABH0FRVj6AGatq2RsMPXzMjmGZ4cL7UwQNmOyAIh0mo-uNeMjCBdOBirER80pytFFBiY9rEDRW3fCnotoACxT7Q0ACiBHrT05RVGOoFYSFwG7RbXXChDZ2X3sOMsMVoYSBz5xpbCKNFICsPW_Khxmk5Qm8aWiAyYHkqLgDKqV2gwTWGCHca_Ay_DPvUK7grXgyjrH2gy8GdcFuetV_BOeDhCIdLxw_6YDnlRQAuMG601Hj0szTXnWvMlUENQ8v5OW24CoebsXCtdWEhQU5jSi51wTlJwsl5hhcNE5xALqbC47ZrLQlJaikkZFN2PhjlmE5QH-BxZmmyU_UCLeUHQ3-lqlWATAKD0d4-U3WzMa2TVxoNCDDl5xjltX_5GdX8mjzhDi7NnnRHrXpujt2wO-NvnnIn8Y7vTXu19-9LZfNnZ2tpd2uj8Wt37_Hb3x07eXs8_fM_f7-TLm3vPV3bXlrrv2r1n273t9d7Oi_z1cvfNRv51rbO9AiTdT0-7P1-dd6Yq8eTYuGuPPnGbvseYW5NBAs_MBLOD1f3Up8JPQbupH_KaALeb-bQWCCWSxGMJlb6X4WFTPk1olmTSz4ILznDjcaN-0RnNaCpSJtPUwz-eJikPvGqiUlZVCVfZJeeGVcqMfbQ1Zw5Z9PJxkK44pw4my1VnuPVkvn4NQvZWct3cCH8ARwq5fA |
| linkProvider | Directory of Open Access Journals |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=%E5%9F%BA%E4%BA%8E%E8%AF%AD%E4%B9%89%E4%BC%BC%E7%84%B6%E4%B8%8E%E9%AB%98%E7%B2%BE%E5%BA%A6%E5%9C%B0%E5%9B%BE%E5%8C%B9%E9%85%8D%E7%9A%84%E6%99%BA%E8%83%BD%E8%BD%A6%E8%BE%86%E5%90%8C%E6%97%B6%E5%AE%9A%E4%BD%8D%E4%B8%8E%E6%A3%80%E6%B5%8B&rft.jtitle=%E4%B8%8A%E6%B5%B7%E4%BA%A4%E9%80%9A%E5%A4%A7%E5%AD%A6%E5%AD%A6%E6%8A%A5&rft.au=%E8%B5%96%E5%9B%BD%E8%89%AF&rft.au=%E8%83%A1%E9%92%8A%E6%94%BF&rft.au=%E5%91%A8%E5%93%B2&rft.au=%E4%B8%87%E9%87%91%E6%9D%B0&rft.date=2024-10-28&rft.pub=%E6%AD%A6%E6%B1%89%E7%90%86%E5%B7%A5%E5%A4%A7%E5%AD%A6%E9%87%8D%E5%BA%86%E7%A0%94%E7%A9%B6%E9%99%A2%2C%E9%87%8D%E5%BA%86+401120&rft.issn=1006-2467&rft.volume=58&rft.issue=10&rft.spage=1618&rft.epage=1628&rft_id=info:doi/10.16183%2Fj.cnki.jsjtu.2023.086&rft.externalDocID=shjtdxxb202410014 |
| thumbnail_s | http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fshjtdxxb%2Fshjtdxxb.jpg |