International Society for Photogrammetry and Remote Sensing (ISPRS)
Titel Konferenzpublikation:
XXIII ISPRS Congress, Commission III, 12-19 July 2016, Prague, Czech Republic
Zeitschrift:
ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Heftnummer:
III-3
Veranstalter (Körperschaft):
International Society for Photogrammetry and Remote Sensing (ISPRS)
Konferenztitel:
International Society for Photogrammetry and Remote Sensing Congress (23., 2016, Prag)
Tagungsort:
Prag
Jahr der Konferenz:
2016
Datum Beginn der Konferenz:
12.07.2016
Datum Ende der Konferenz:
19.07.2016
Verlegende Institution:
International Society for Photogrammetry and Remote Sensing (ISPRS)
Jahr:
2016
Seiten von - bis:
99-106
Sprache:
Englisch
Abstract:
This paper presents a Structure from Motion approach for complex unorganized image sets. To achieve high accuracy and robustness, image triplets are employed and (an approximate) camera calibration is assumed to be known. The focus lies on a complete linking of images even in case of large image distortions, e.g., caused by wide baselines, as well as weak baselines. A method for embedding image descriptors into Hamming space is proposed for fast image similarity ranking. The later is employed to limit the number of pairs to be matched by a wide baseline method. An iterative graph-based approach is proposed formulating image linking as the search for a terminal Steiner minimum tree in a line graph. Finally, additional links are determined and employed to improve the accuracy of the pose estimation. By this means, loops in long image sequences are implicitly closed. The potential of the proposed approach is demonstrated by results for several complex image sets also in comparison with VisualSFM. «
This paper presents a Structure from Motion approach for complex unorganized image sets. To achieve high accuracy and robustness, image triplets are employed and (an approximate) camera calibration is assumed to be known. The focus lies on a complete linking of images even in case of large image distortions, e.g., caused by wide baselines, as well as weak baselines. A method for embedding image descriptors into Hamming space is proposed for fast image similarity ranking. The later is employed to... »