Multi-Source and Multi-View Aircraft Cognitive Navigation Dataset Construction
| 165 | 1 | 726 |
| 下载次数 | 被引频次 | 阅读次数 |
针对现有大部分飞行器视觉导航数据集特征信息有限的问题，构建了一个多源、多视角、多场景的飞行器认知导航数据集，可有效支撑飞行器的精确地理定位。首先，基于深度特征匹配算法在认知导航区卫星图像内选取导航适配区，并基于SAM(segment anything model)语义分割算法获得特征显著且稳定的典型导航标志物及其语义信息;然后，利用真实无人机航拍和Google Earth提供的3D仿真模型采集充足的导航标志物飞行器视角图像;最后，基于SuperPoint特征点提取算法自动对图像进行标注，并设计基于WordNet体系的认知导航数据集多层级结构，从而最终获得具有地理位置信息和深度语义特征标注的飞行器认知导航数据集。分析评估表明，所构建的数据集覆盖场景广泛、特征信息丰富、数据来源多样，为飞行器认知导航算法的训练和验证提供了高质量的数据样本。
Abstract：To overcome limited feature information in most existing aircraft visual navigation datasets, a multi-source, multi-view, and multi-scene aircraft cognitive navigation dataset was constructed to support accurate aircraft geolocation. First, navigation adaptation zones were selected from satellite images of cognitive navigation regions using a deep feature matching algorithm. Distinctive and stable navigation landmarks, along with their semantic information, were then extracted using the segment anything model(SAM)semantic segmentation algorithm. Subsequently, sufficient aircraft-view images of the navigation landmarks were collected using real drone aerial photography and 3D simulation models provided by Google Earth. Finally, the SuperPoint feature point extraction algorithm was applied to automatically annotate the images. A multi-level structure of cognitive navigation datasets based on the WordNet system was designed, producing an aircraft cognitive navigation dataset annotated with geolocation information and deep semantic features. The evaluation and analysis demonstrate that the constructed dataset covers a wide range of scenarios, provides rich feature information, and incorporates diverse image sources, offering high-quality data samples for the training and validation of aircraft cognitive navigation algorithms.
[1]刘学俊，贺伟，贺小龙．基于卫星影像的无人机全局位姿估计方法[J]．测绘与空间地理信息，2025,48(3):83-86.LIU X J, HE W, HE X L. UAV global pose estimation method based on satellite image[J].Geomatics&Spatial Information Technology,2025,48(3):83-86.
[2] LI Q G,YANG X G,LU R T,et al.VisionICE:air-ground integrated intelligent cognition visual enhancement system based on a UAV[J].Drones,2023,7(4):1-17.
[3] JIN Y F, YU L, CHEN Z, et al. A mono SLAM method based on depth estimation by DenseNet-CNN[J]. IEEE Sensors Journal, 2022,22(3):2447-2455.
[4]周博文，李阳，马鑫骥，等．深度学习的跨视角地理定位方法综述[J]．中国图象图形学报，2024, 29(12):3543-3563.ZHOU B W, LI Y, MA X J, et al. A survey of cross-view geo-localization methods based on deep learning[J]. Journal of Image and Graphics,2024,29(12):3543-3563.
[5] WORKMAN S, SOUVENIR R, JACOBS N.Wide-area image geolocalization with aerial reference imagery[C]//2015 IEEE International Conference on Computer Vision(ICCV).Piscataway,NJ,USA:IEEE,2015:3961-3969.
[6] LIU L, LI H D. Lending orientation to neural networks for cross-view geo-localization[C]//2019IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).Piscataway,NJ,USA:IEEE,2019:5624-5633.
[7] ZHU S J,YANG T,CHEN C.VIGOR:crossview image geo-localization beyond one-to-one retrieval[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).Piscataway,NJ,USA:IEEE,2021:3640-3649.
[8] ZHENG Z D, WEI Y C, YANG Y.University-1652:a multi-view multi-source benchmark for dronebased geo-localization[C]//Proceedings of the 28th ACM International Conference on Multimedia.New York,USA:ACM,2020:1395-1403.
[9] ZHU R Z,YIN L,YANG M Z,et al.SUES-200:a multi-height multi-scene cross-view image benchmark across drone and satellite[J]. IEEE Transactions on Circuits and Systems for Video Technology,2023,33(9):4825-4839.
[10] ZENG Z L, WANG Z, YANG F, et al. Geolocalization via ground-to-satellite cross-view image retrieval[J]. IEEE Transactions on Multimedia,2022,25:2176-2188.
[11] LI J S,YANG C F,QI B J,et al.4SCIG:a four-branch framework to reduce the interference of sky area in cross-view image geo-localization[J].IEEE Transactions on Geoscience and Remote Sensing,2024,62:4703818.
[12] ZHANG X X, WANG C Y, JIN J, et al. Object detection of VisDrone by stronger feature extraction FasterRCNN[J]. Journal of Electronic Imaging,2023,32:013018.
[13] HUANG D H,CHEN Y,LIU Y,et al.Adaptive assignment for geometry aware local feature matching[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).Piscataway,NJ,USA:IEEE,2023:5425-5434.
[14]李邦杰，武健，张大巧，等．基于卷积神经网络的景象匹配区适配性筛选方法[J]．火箭军工程大学学报，2024,38(3):45-50,59.LI B J, WU J, ZHANG D Q, et al. A CNNbased scene matching adaptability screening method[J]. Journal of Rocket Force University of Engineering,2024,38(3):45-50,59.
[15] CHEN Y, HUANG D H, XU S, et al. Guide local feature matching by overlap estimation[J].Proceedings of the AAAI Conference on Artificial Intelligence,2022,36(1):365-373.
[16] KIRILLOV A, MINTUN E, RAVI N, et al.Segment anything[C]//2023 IEEE/CVF International Conference on Computer Vision(ICCV).Piscataway,NJ,USA:IEEE,2023:4015-4026.
[17]黄攀，范继伟，杨小冈，等．智能图像导引头目标数据集制备技术研究[J]．战术导弹技术，2022(2):105-112.HUANG P,FAN J W,YANG X G,et al.Research on target dataset preparation technology of intelligent image seekers[J].Tactical Missile Technology,2022(2):105-112.
[18] DETONE D, MALISIEWICZ T, RABINOVICH A.SuperPoint:self-supervised interest point detection and description[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops(CVPRW). Piscataway, NJ, USA:IEEE,2018:224-236.
[19]FAN B,ZHOU J J,FENG W S,et al.Learning semantic-aware local features for long term visual localization[J]. IEEE Transactions on Image Processing,2022,31:4842-4855.
[20]蔡伟，高蔚洁，蒋昕昊，等．可见光条件下伪装目标智能化分割算法综述[J]．火箭军工程大学学报，2024,38(2):72-87.CAI W,GAO W J,JIANG X H,et al.Review of intelligent camouflaged object segmentation algorithms under visible light[J]. Journal of Rocket Force University of Engineering,2024,38(2):72-87.
[21] HE K M,CHEN X L,XIE S N,et al.Masked autoencoders are scalable vision learners[C]//2022IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).Piscataway,NJ,USA:IEEE,2022:15979-15988.
[22] DOSOVITSKIY A, BEYER L, KOLESNIKOV A,et al.An image is worth 16×16 words:transformers for image recognition at scale[C/OL].(2021-06-03)[2025-04-30].https：//doi.org/10.48550/arXiv.2010.11929.
[23] REVAUD J,LEROY V,WEINZAEPFEL P,et al.PUMP:pyramidal and uniqueness matching priors for unsupervised learning of local descriptors[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway,NJ,USA:IEEE,2022:3916-3926.
[24] SARLIN P E,DETONE D,MALISIEWICZ T,et al. SuperGlue:learning feature matching with graph neural networks[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, NJ, USA:IEEE, 2020:4938-4947.
[25]张琪，范永胜，金独亮．基于MMR和WordNet的新闻文本摘要生成研究[J]．西南师范大学学报（自然科学版），2023,48(5):77-86.ZHANG Q, FAN Y S, JIN D L. Research on news text summarizations generation based on MMR and WordNet[J].Journal of Southwest China Normal University(Natural Science Edition), 2023, 48(5):77-86.
基本信息:
DOI：10.20189/j.cnki.CN/61-1527/E.202503001
中图分类号:V249.3;V448
引用信息:
[1]陈璐,李清格,杨小冈,等.多源多视角飞行器认知导航数据集制备[J].火箭军工程大学学报,2025,39(03):1-9.DOI:10.20189/j.cnki.CN/61-1527/E.202503001.
Citation Information:
[1]CHEN Lu,LI Qingge,YANG Xiaogang ,et al.Multi-Source and Multi-View Aircraft Cognitive Navigation Dataset Construction[J].火箭军工程大学学报,2025,39(03):1-9.DOI:10.20189/j.cnki.CN/61-1527/E.202503001.
基金信息:
国家自然科学基金（62276274）; 陕西省重点研发计划（2024CY2-GJHX-42）
2025-06-16
2025-06-16
2025-06-16