1.中山大学航空航天学院,广东 深圳 518107
2.中山大学人工智能学院, 广东 珠海 519080
卜祥鹏(1999年生),男;研究方向:视觉感知;E-mail:buxp3@mail2.sysu.edu.cn
胡天江(1979年生),男;研究方向:群体智能,集群系统;E-mail:hutj3@mail.sysu.edu.cn
收稿:2025-04-12,
录用:2025-04-26,
网络首发:2026-01-02,
纸质出版:2026-01-25
移动端阅览
卜祥鹏,赵涂昊,翟浩州等.面向消防救援指挥的无人机航拍快速成图方法[J].中山大学学报(自然科学版)(中英文),2026,65(01):76-84.
BU Xiangpeng,ZHAO Tuhao,ZHAI Haozhou,et al.A rapid mapping method for UAV aerial photography in fire rescue[J].Acta Scientiarum Naturalium Universitatis Sunyatseni,2026,65(01):76-84.
卜祥鹏,赵涂昊,翟浩州等.面向消防救援指挥的无人机航拍快速成图方法[J].中山大学学报(自然科学版)(中英文),2026,65(01):76-84. DOI: 10.11714/acta.snus.ZR20250069.
BU Xiangpeng,ZHAO Tuhao,ZHAI Haozhou,et al.A rapid mapping method for UAV aerial photography in fire rescue[J].Acta Scientiarum Naturalium Universitatis Sunyatseni,2026,65(01):76-84. DOI: 10.11714/acta.snus.ZR20250069.
提出一种基于语义信息的航拍图像拼接方法。第1阶段,基于三维向量旋转的投影变换粗配准方法,通过地理坐标转换、视锥体建模、平面交会计算以及投影矩阵构建,实现了航拍图像到统一高程平面的高效粗配准。第2阶段,基于语义分割与LightGlue特征匹配的行间误差优化方法,将粗配准后的每行图像作为独立优化单元,通过语义分割获取道路拓扑结构,结合轻量化特征匹配网络与几何约束优化,实现高精度行间配准。实验结果表明,通过构建双阶段优化模型有效克服了相机内参的依赖,最终以可视化的方式在地理信息系统界面上展示准确的受灾地点,全面、系统记录了灾情特征。
This study proposes a semantic information-based aerial image stitching methodology. In the first stage, a coarse registration method using projection transformation based on 3D vector rotation is adopted. Through geographic coordinate conversion, view frustum modeling, plane intersection calculation, and projection matrix estimation, efficient coarse registration of aerial images onto a unified elevation plane is achieved. In the second stage, a semantic segmentation and LightGlue feature based optimization method is utilized. Each row of images after coarse registration is treated as an independent optimization unit: road topological structures are obtained via semantic segmentation, and high-precision registration is realized by combining a lightweight feature matching network with geometric constraint optimization. Experimental results show that the proposed two-stage optimization model effectively overcomes the dependence of camera intrinsics. Finally, the accurate disaster-stricken locations are visualized on the geographic system interface, enabling comprehensive and systematic recording of disaster characteristics.
李聪颖 , 2021 . 无人机遥感技术在城市火灾救援中的实践应用 [C]// 灭火与应急救援技术学术研讨会 . 天津 : 67 - 69 .
魏巍 , 2015 . 低空航拍图像正射全景拼图方法研究 [D]. 长沙 : 国防科学技术大学 .
ALRAYES F S , ALOTAIBI S S , ALISSA K A , et al , 2022 . Artificial intelligence-based secure communication and classification for drone-enabled emergency monitoring systems [J]. Drones , 6 ( 9 ): 222 .
CHEN J , XU Q , LUO L , et al , 2019 . A robust method for automatic panoramic UAV image mosaic [J]. Sensors , 19 ( 8 ): 1898 .
HUANG H , LIN L , TONG R , et al , 2020 . UNet3+:A full-scale connected UNet for medical image segmentation [C]// IEEE International Conference on Acoustics, Speech and Signal Processing . Barcelona, Spain : 1055 - 1059 .
LI L , HAN L , DING M , et al , 2020 . Remote sensing image registration based on deep learning regression model [J]. IEEE Geosci Remote Sens Lett , 19 : 1 - 5 .
LIANG Z , DU Y L , LIN H P , et al , 2020 . A novel region-based image registration method for multisource remote sensing images via CNN [J]. IEEE J Sel Top Appl Earth Obs Remote Sens , 14 : 1821 - 1831 .
LINDENBERGER P , SARLIN P E , POLLEFEYS M , 2023 . LightGlue: Local feature matching at light speed [C]// IEEE/CVF International Conference on Computer Vision . Paris, France : 17627 - 17638 .
LIU Q , HAN M , WANG J , 2021 . An aerial image stitching algorithm based on long-distance features [C]// The 11th International Conference on Information Science and Technology . Chengdu, China : 217 - 223 .
IZ S A , UNEL M , 2023 . Aerial image stitching using IMU data from a UAV [C]// The 8th International Conference on Image, Vision and Computing . Dalian,China : 513 - 518 .
NIU H , CHEN E , QI L , et al , 2015 . Image registration based on fractional Fourier transform [J]. Optik , 126 ( 23 ): 3889 - 3893 .
PHAM N T , PARK S , PARK C S , 2021 . Fast and efficient method for large-scale aerial image stitching [J]. IEEE Access , 9 : 127852 - 127865 .
SHAH S , DEY D , LOVETT C , et al , 2018 . AirSim: High-fidelity visual and physical simulation for autonomous vehicles [C]// Field and Service Robotics: Results of the 11th International Conference . Cham : Springer : 621 - 635 .
YANG H , FU Y , CHEN D , et al , 2022 . A fast and effective panorama stitching algorithm on UAV aerial images [C]// The 14th International Conference on Computer Research and Development . Shenzhen, China : 266 - 275 .
YUAN Y , FANG F , ZHANG G , 2020 . Superpixel-based seamless image stitching for UAV images [J]. IEEE Geosci Remote Sens Lett , 59 ( 2 ): 1565 - 1576 .
ZHANG T , ZHU M , 2019 . GPS-assisted aerial image stitching based on optimization algorithm [C]// 2019 Chinese Control Conference . Guangzhou, China : 3485 - 3490 .
ZHOU Y , RUI T , LI Y , et al , 2019 . A UAV patrol system using panoramic stitching and object detection [J]. Comput Electr Eng , 80 ( 4 ): 106473 .
0
浏览量
110
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621
