Pregled bibliografske jedinice broj: 1109384
Active vision for 3D indoor scene reconstruction using a 3D camera on a pan-tilt mechanism
Active vision for 3D indoor scene reconstruction using a 3D camera on a pan-tilt mechanism // Advanced Robotics, 35 (2021), 3-4; 153-167 doi:10.1080/01691864.2021.1875042 (međunarodna recenzija, članak, znanstveni)
CROSBI ID: 1109384 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Active vision for 3D indoor scene reconstruction
using a 3D camera on a pan-tilt mechanism
Autori
Hržica, Mateja ; Cupec, Robert ; Petrović, Ivan
Izvornik
Advanced Robotics (0169-1864) 35
(2021), 3-4;
153-167
Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni
Ključne riječi
Active vision ; next-best-view ; iterative closest point registration ; point cloud ; indoor scene reconstruction
Sažetak
We present a novel approach to automatic indoor scene reconstruction from RGB-D images acquired from a single viewpoint using active vision. The proposed method is designed to select the next view with sufficient information for reliable registration. The next view is selected based on the percentage of unexplored scene regions captured inside the field of view and the information content in the overlapping region between the image acquired from the next view and one of the previously acquired images. It is required that this overlapping region contains surfaces with different orientations, whose alignment provides a reliable estimation of the relative camera orientation. The point correspondences between views are established using the assumption of fixed viewpoint, imprecise information about relative view orientation and local surface normal, without need for features based on texture or distinctive local shape. After completing a scan, the 3D scene model is constructed by performing registration of the acquired depth images. Two algorithms are considered for that purpose: a point-to-plane ICP with point weighting based on the properties of the measurement noise and TEASER++. The proposed method is tested on the synthetic dataset Replica.
Izvorni jezik
Engleski
Znanstvena područja
Računarstvo, Temeljne tehničke znanosti, Kognitivna znanost (prirodne, tehničke, biomedicina i zdravstvo, društvene i humanističke znanosti)
POVEZANOST RADA
Projekti:
IP-2014-09-3155 - Napredna 3D percepcija za mobilne robotske manipulatore (ARP3D) (Cupec, Robert, HRZZ - 2014-09) ( CroRIS)
Ustanove:
Fakultet elektrotehnike i računarstva, Zagreb,
Fakultet elektrotehnike, računarstva i informacijskih tehnologija Osijek
Citiraj ovu publikaciju:
Časopis indeksira:
- Current Contents Connect (CCC)
- Web of Science Core Collection (WoSCC)
- Science Citation Index Expanded (SCI-EXP)
- SCI-EXP, SSCI i/ili A&HCI
- Scopus