Guided feature matching for multi-epoch historical image blocks pose estimation - Archive ouverte HAL Accéder directement au contenu
Proceedings/Recueil Des Communications Année : 2020

Guided feature matching for multi-epoch historical image blocks pose estimation

Résumé

Historical aerial imagery plays an important role in providing unique information about evolution of our landscapes. It possesses many positive qualities such as high spatial resolution, stereoscopic configuration and short time interval. Self-calibration reamains a main bottleneck for achieving the intrinsic value of historical imagery, as it involves certain underdeveloped research points such as detecting inter-epoch tie-points. In this research, we present a novel algorithm to detecting inter-epoch tie-points in historical images which do not rely on any auxiliary data. Using SIFT-detected keypoints we perform matching across epochs by interchangeably estimating and imposing that points follow two mathematical models: at first a 2D spatial similarity, then a 3D spatial similarity. We import GCPs to quantitatively evaluate our results with Digital Elevation Models (DEM) of differences (abbreviated as DoD) in absolute reference frame, and compare the results of our method with other 2 methods that use either the traditional SIFT or few virtual GCPs. The experiments show that far more correct inter-epoch tie-points can be extracted with our guided technique. Qualitative and quantitative results are reported.
Fichier principal
Vignette du fichier
ISPRS2020zll-20200423-final.pdf (27.71 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02563454 , version 1 (05-05-2020)

Identifiants

  • HAL Id : hal-02563454 , version 1

Citer

Lulin Zhang, Ewelina Rupnik, Marc Pierrot-Deseilligny. Guided feature matching for multi-epoch historical image blocks pose estimation. ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., 2020. ⟨hal-02563454⟩

Collections

IGN-ENSG
150 Consultations
10 Téléchargements

Partager

Gmail Facebook X LinkedIn More