Recognition of one class of quadrics from 3D point clouds
Апстракт
Within cyber physical production systems 3D vision as a source of information from real-world provides enormous possibilities. While the hardware of contemporary 3D scanners is characterized by high speed along with high resolution and accuracy, there is a lack of real-time online data processing algorithms that would give certain elements of intelligence to the sensory system. Critical elements of data processing software are efficient, real-time applicable methods for fully automatic recognition of high level geometric primitives from point cloud (surface segmentation and fitting). This paper presents a method for recognition of one class of quadrics from 3D point clouds, in particular for recognition of cylinders, elliptical cylinders and ellipsoids. The method is based on the properties of scatter matrix during direct least squares fitting of ellipsoids. Presented recognition procedure can be employed for segmentation of regions with G1 or higher continuity, and this is its compara...tive advantage to similar methods. The applicability of the method is illustrated and experimentally verified using two case studies. First case study refers to a synthesized, and the second to a real-world scanned point cloud.
Кључне речи:
surface recognition / parametric model / 3D point cloudИзвор:
Procedia CIRP - 49th CIRP Conference on Manufacturing Systems (CIRP-CMS 2016), 2016, 57, 292-297Издавач:
- Elsevier B.V.
Финансирање / пројекти:
- Интелигентни роботски системи за екстремно диверзификовану производњу (RS-MESTD-Technological Development (TD or TR)-35007)
- Истраживање и развој метода моделирања и поступака израде денталних надокнада применом савремених технологија и рачунаром подржаних система (RS-MESTD-Technological Development (TD or TR)-35020)
DOI: 10.1016/j.procir.2016.11.051
ISSN: 2212-8271
WoS: 000398053800050
Scopus: 2-s2.0-85006992395
Колекције
Институција/група
Mašinski fakultetTY - CONF AU - Jakovljević, Živana AU - Marković, Veljko AU - Puzović, Radovan AU - Majstorović, Vidosav D. PY - 2016 UR - https://machinery.mas.bg.ac.rs/handle/123456789/2388 AB - Within cyber physical production systems 3D vision as a source of information from real-world provides enormous possibilities. While the hardware of contemporary 3D scanners is characterized by high speed along with high resolution and accuracy, there is a lack of real-time online data processing algorithms that would give certain elements of intelligence to the sensory system. Critical elements of data processing software are efficient, real-time applicable methods for fully automatic recognition of high level geometric primitives from point cloud (surface segmentation and fitting). This paper presents a method for recognition of one class of quadrics from 3D point clouds, in particular for recognition of cylinders, elliptical cylinders and ellipsoids. The method is based on the properties of scatter matrix during direct least squares fitting of ellipsoids. Presented recognition procedure can be employed for segmentation of regions with G1 or higher continuity, and this is its comparative advantage to similar methods. The applicability of the method is illustrated and experimentally verified using two case studies. First case study refers to a synthesized, and the second to a real-world scanned point cloud. PB - Elsevier B.V. C3 - Procedia CIRP - 49th CIRP Conference on Manufacturing Systems (CIRP-CMS 2016) T1 - Recognition of one class of quadrics from 3D point clouds EP - 297 SP - 292 VL - 57 DO - 10.1016/j.procir.2016.11.051 ER -
@conference{ author = "Jakovljević, Živana and Marković, Veljko and Puzović, Radovan and Majstorović, Vidosav D.", year = "2016", abstract = "Within cyber physical production systems 3D vision as a source of information from real-world provides enormous possibilities. While the hardware of contemporary 3D scanners is characterized by high speed along with high resolution and accuracy, there is a lack of real-time online data processing algorithms that would give certain elements of intelligence to the sensory system. Critical elements of data processing software are efficient, real-time applicable methods for fully automatic recognition of high level geometric primitives from point cloud (surface segmentation and fitting). This paper presents a method for recognition of one class of quadrics from 3D point clouds, in particular for recognition of cylinders, elliptical cylinders and ellipsoids. The method is based on the properties of scatter matrix during direct least squares fitting of ellipsoids. Presented recognition procedure can be employed for segmentation of regions with G1 or higher continuity, and this is its comparative advantage to similar methods. The applicability of the method is illustrated and experimentally verified using two case studies. First case study refers to a synthesized, and the second to a real-world scanned point cloud.", publisher = "Elsevier B.V.", journal = "Procedia CIRP - 49th CIRP Conference on Manufacturing Systems (CIRP-CMS 2016)", title = "Recognition of one class of quadrics from 3D point clouds", pages = "297-292", volume = "57", doi = "10.1016/j.procir.2016.11.051" }
Jakovljević, Ž., Marković, V., Puzović, R.,& Majstorović, V. D.. (2016). Recognition of one class of quadrics from 3D point clouds. in Procedia CIRP - 49th CIRP Conference on Manufacturing Systems (CIRP-CMS 2016) Elsevier B.V.., 57, 292-297. https://doi.org/10.1016/j.procir.2016.11.051
Jakovljević Ž, Marković V, Puzović R, Majstorović VD. Recognition of one class of quadrics from 3D point clouds. in Procedia CIRP - 49th CIRP Conference on Manufacturing Systems (CIRP-CMS 2016). 2016;57:292-297. doi:10.1016/j.procir.2016.11.051 .
Jakovljević, Živana, Marković, Veljko, Puzović, Radovan, Majstorović, Vidosav D., "Recognition of one class of quadrics from 3D point clouds" in Procedia CIRP - 49th CIRP Conference on Manufacturing Systems (CIRP-CMS 2016), 57 (2016):292-297, https://doi.org/10.1016/j.procir.2016.11.051 . .