基于并行化处理的无人机影像三维重建算法  

Three Dimensional Reconstruction Algorithm of Unmanned Aerial Vehicle Images Based on Parallel Processing

作　　者：陈怀圆 党建武 岳彪 杨景玉[3] Chen Huaiyuan;Dang Jianwu;Yue Biao;Yang Jingyu(key Laboratory of Optoelectronic Technology and Intelligent Control,Ministry of Education,Lanzhou Jiaotong University,Lanzhou 730070,Gansu,China;National Virtual Simulation Experimental Teaching Center of Rail Transit Information and Control,Lanzhou 730070,Gansu,China;School of Electronic and Information Engineering,Lanzhou Jiaotong University,Lanzhou 730070,Gansu,China)

机构地区：[1]兰州交通大学光电技术与智能控制教育部重点实验室,甘肃兰州730070 [2]轨道交通信息与控制国家级虚拟仿真实验教学中心,甘肃兰州730070 [3]兰州交通大学电子与信息工程学院,甘肃兰州730070

出　　处：《激光与光电子学进展》2024年第8期99-107,共9页Laser & Optoelectronics Progress

基　　金：2022年度中央引导地方科技发展资金项目(22ZY1QA002);甘肃省教育科技创新项目(2021jyjbgs-05);甘肃省军民融合专项(2020JG01);甘肃省重点研发计划(21YF5GA158);甘肃省知识产权计划项目(21ZSCQ013)。

摘　　要：针对增量运动恢复结构(SFM)算法在重建大规模无人机影像数据集时效率低、易产生场景漂移的问题,提出一种可并行化处理的增量SFM重建算法。首先,利用词汇树图像检索结果约束图像特征匹配的空间搜索范围,提高图像特征匹配的效率。其次,综合考虑特征匹配数量和无人机平台获取的全球定位系统(GPS)信息构建无向加权场景图,并选用归一化割算法将场景图划分为多个相互重叠的子集。然后,将每个子集分布在多核CPU上并行执行增量SFM重建算法。最后,基于子集间公共重建点和强相关子集优先被合并的策略实现子集合并。此外,结合GPS信息为光束法平差(BA)代价函数添加位置约束项,有效消除每次执行BA优化引入的误差。为了验证所提算法的有效性,在3个无人机数据集上进行实验,实验结果表明,所提算法相比原始增量SFM重建算法不仅显著提高了位姿估计和场景重建的效率,而且合理优化了重建结果的精度。A parallelizable incremental structure from motion(SFM)recovery reconstruction algorithm is employed to address low efficiency and susceptibility to scene drift when reconstructing largescale unmanned aerial vehicle image datasets.First,the vocabulary tree image retrieval results are used to constrain the spatial search range and improve the efficiency of image feature matching.Second,by considering the feature matching number and the global positioning system(GPS)information obtained by the drone platform,an undirected weighted scene map is constructed,and a normalized cut algorithm is selected to divide the scene map into multiple overlapping subsets.Further,each subset is distributed on multicore central processing units(CPUs),and the incremental SFM reconstruction algorithm is executed in parallel.Finally,based on the strategy of common reconstruction points between subsets and priority merging of strongly correlated subsets,subset merging is achieved.In addition,combining GPS information to add positional constraints to the beam adjustment(BA)cost function eliminates the errors introduced by each BA optimization execution.To verify the effectiveness of the algorithm,experiments are conducted on three unmanned aerial vehicle datasets.The experimental results show that the proposed algorithm not only significantly improves the efficiency of pose estimation and scene reconstruction compared with the original incremental SFM reconstruction algorithm but also reasonably optimizes the accuracy of the reconstruction results.

关 键 词：增量运动恢复结构 光束法平差 词汇树图像检索 归一化割 场景合并 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]