Journal of Computer Applications ›› 2021, Vol. 41 ›› Issue (10): 3004-3009.DOI: 10.11772/j.issn.1001-9081.2020111795

Special Issue: 多媒体计算与计算机仿真

• Multimedia computing and computer simulation • Previous Articles     Next Articles

Unmanned aerial vehicle image positioning algorithm based on scene graph division

ZHANG Chi1, LI Zhuhong2, LIU Zhou3, SHEN Weiming1   

  1. 1. State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing(Wuhan University), Wuhan Hubei 430079, China;
    2. School of Software Engineering, Huazhong University of Science and Technology, Wuhan Hubei 430074, China;
    3. School of Computer Science, Wuhan University, Wuhan Hubei 430072, China
  • Received:2020-11-17 Revised:2021-02-27 Online:2021-10-10 Published:2021-10-27
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61771014).


张驰1, 李铸洪2, 刘舟3, 沈未名1   

  1. 1. 测绘遥感信息工程国家重点实验室(武汉大学), 武汉 430079;
    2. 华中科技大学 软件学院, 武汉 430074;
    3. 武汉大学 计算机学院, 武汉 430072
  • 通讯作者: 沈未名
  • 作者简介:张驰(1997-),男,江苏徐州人,硕士研究生,主要研究方向:三维重建、深度学习;李铸洪(2002-),北京人,主要研究方向:计算机视觉;刘舟(1989-),湖北应城人,博士,主要研究方向:图像处理、计算机视觉;沈未名(1966-),男,湖北武汉人,教授,博士,主要研究方向:视频编码、多媒体通信、嵌入式多媒体系统、图像模式识别、计算机视觉。
  • 基金资助:

Abstract: Due to the problems of slow speed and error drift in the positioning of large-scale long-sequence Unmanned Aerial Vehicle (UAV) images, a positioning algorithm of UAV images based on scene graph division was proposed according to the characteristics of UAV images. Firstly, the Global Positioning System (GPS) ancillary information was used to narrow the spatial search scope for feature matching, so as to accelerate the extraction of corresponding points. After that, visual consistency and spatial consistency were combined to construct the scene graphs, and Normalized Cut (Ncut) was used to divide them. Then, incremental reconstruction was performed to each group of scene graphs. Finally, all scene graphs were fused to establish a 3S scene model by Bundle Adjustment (BA). In addition, the GPS spatial constraint information was added to the cost function in the BA stage. In the experiments on four UAV image datasets, compared with COLMAP and other Structure From Motion (SFM) algorithms, the proposed algorithm has the positioning speed increased by 50%, the reprojection error decreased by 41%, and the positioning error was controlled within 0.5 m. Through the experimental comparison of algorithms with or without GPS assistance, it can be seen that BA with relative and absolute GPS constraints solves the problem of error drift, avoids the ambiguous results and greatly reduces positioning error.

Key words: Unmanned Aerial Vehicle (UAV) image positioning, scene graph division, Structure From Motion (SFM), Bundle Adjustment (BA), Normalized Cut (Ncut)

摘要: 针对大规模长序列无人机(UAV)影像定位中存在的速度慢、误差漂移等问题,结合UAV影像的特点,提出了一种基于场景图划分的UAV影像定位算法。首先,利用全球定位系统(GPS)辅助信息缩小特征匹配的空间搜索范围,从而加速同名点的提取;之后结合视觉一致性和空间一致性来构建场景图,并利用归一化割(Ncut)对其进行划分;接着,对各组场景图进行增量重建;最后,利用光束法平差(BA)融合场景图从而计算出场景的三维模型。此外,在BA阶段,所提算法对代价函数进行扩充,即加入了GPS空间约束信息。在四个UAV影像数据集上的实验结果表明,与COLMAP等多种运动恢复结构(SFM)算法相比,所提算法的定位速度提升了50%,重投影误差减小了41%,定位误差控制在0.5m之内。此外,通过有无GPS辅助下的算法的实验对比,可以得知引入相对和绝对GPS约束的BA有效解决了误差漂移问题,避免了出现歧义性结果,并且极大地减小了定位误差。

关键词: 无人机影像定位, 场景图划分, 运动恢复结构, 光束法平差, 归一化割

CLC Number: