摘要
高效匹配对选择和影像特征匹配直接决定无人机影像运动恢复结构(structure from motion,SfM)的效率。联合词汇树的倒排和正向索引结构,提出无人机影像匹配对选择和特征匹配加速算法。首先,利用词汇树的单词-影像倒排索引结构,基于影像相似性的空间分布特征,设计了自适应阈值的词汇树检索算法;然后,利用词汇树的影像-单词正向索引结构,将显式最近邻描述子搜索简化为词汇树单词映射,设计了词汇树引导匹配算法。4组无人机影像的试验结果表明,所提的自适应阈值词汇树检索算法能够有效地筛选匹配对,避免传统固定阈值或比例算法导致的匹配对数量过多或不足的问题;在保证匹配精度的前提下,词汇树引导匹配算法的加速比达到156~228,并在无人机影像SfM空三中取得与经典最近邻搜索匹配相当的精度。
Objectives Efficient match pair selection and image feature matching directly affect the efficiency of structure from motion(SfM)-based 3D reconstruction for unmanned aerial vehicle(UAV)images.This paper combines the inverted and direct index structure of the vocabulary tree to achieve the speedup of match pair selection and feature matching for UAV images.Methods First,for match pair selection,vocabulary tree-based image retrieval has been the commonly used technique.However,it depends on the fixed number or fixed ratio threshold for match pair selection,which may cause many redundant match pairs.An adaptive vocabulary tree-based retrieval algorithm is designed for match pair selection by using the word-image index structure and the spatial distribution of similarity scores,and it can avoid the drawback of depending on fixed thresholds.Second,for feature matching,the nearest neighbor searching method attempts to compute the Euclidean distance exhaustively between two sets of feature descriptors,which causes high computational costs and generates high outlier ratios.Thus,a guided feature matching(GFM)algorithm is presented which casts the explicit closest descriptor searching as the direct assignment by using the image-word index structure of the vocabulary tree.Combining the match pair selection and GFM algorithm,an integrated workflow is finally presented to achieve feature matching of both ordered and unordered UAV images with high precision and efficiency.Results The proposed workflow is verified using four UAV datasets and compared comprehensively with classical nearest neighbor searching algorithms and commercial software packages.Conclusions The experimental results verify that the proposed method can achieve efficient match pair selection and avoid the problem of retrieving too many or too few match pairs that are usually caused by traditional methods using fixed threshold or number strategies.Without the sacrifice of matching precision,the speedup ratio of direct assign based feature matching ranges from 156 to 228,and competitive accuracy is also obtained from 3D reconstruction compared with the nearest neighbor searching method.
作者
姜三
江万寿
郭丙轩
JIANG San;JIANG Wanshou;GUO Bingxuan(School of Computer Science,China University of Geosciences(Wuhan),Wuhan 430074,China;Guangdong Laboratory of Artificial Intelligence and Digital Economy(Shenzhen),Shenzhen 518060,China;Engineering Research Center of Natural Resource Information Management and Digital Twin Engineering Software,Ministry of Education,Wuhan 430074,China;State Key Laboratory of Information Engineering in Surveying,Mapping and Remote Sensing,Wuhan University,Wuhan 430079,China)
出处
《武汉大学学报（信息科学版）》
EI
CAS
CSCD
北大核心
2024年第9期1597-1609,共13页
Geomatics and Information Science of Wuhan University
基金
国家自然科学基金(42371442,42001413)
湖北省自然科学基金(2023AFB568)
人工智能与数字经济广东省实验室(深圳)开放课题(GML-KF-22-08)
智能地学信息处理湖北省重点实验室开放研究课题(KLIGIP-2021B11)。
关键词
无人机
影像匹配对选择
特征匹配
词汇树检索
运动恢复结构
三维重建
unmanned aerial vehicle(UAV)
match pair selection
feature matching
vocabulary tree-based retrieval
structure from motion(SfM)
3D reconstruction
