Recognition of Planar Segments in Point Cloud Based on Wavelet Transform
Апстракт
Within industrial automation systems, three-dimensional (3-D) vision provides very useful feedback information in autonomous operation of various manufacturing equipment (e.g., industrial robots, material handling devices, assembly systems, and machine tools). The hardware performance in contemporary 3-D scanning devices is suitable for online utilization. However, the bottleneck is the lack of real-time algorithms for recognition of geometric primitives (e.g., planes and natural quadrics) from a scanned point cloud. One of the most important and the most frequent geometric primitive in various engineering tasks is plane. In this paper, we propose a new fast one-pass algorithm for recognition (segmentation and fitting) of planar segments from a point cloud. To effectively segment planar regions, we exploit the orthonormality of certain wavelets to polynomial function, as well as their sensitivity to abrupt changes. After segmentation of planar regions, we estimate the parameters of cor...responding planes using standard fitting procedures. For point cloud structuring, a z-buffer algorithm with mesh triangles representation in barycentric coordinates is employed. The proposed recognition method is tested and experimentally validated in several real-world case studies.
Кључне речи:
three-dimensional (3-D) vision / reverse engineering (RE) / object segmentation / object recognition / manufacturing automation / intelligent manufacturing systems / Industrial automation systemsИзвор:
IEEE Transactions on Industrial Informatics, 2015, 11, 2, 342-352Издавач:
- IEEE - Inst Electrical Electronics Engineers Inc, Piscataway
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)
- Развој нове генерације домаћих обрадних система (RS-MESTD-Technological Development (TD or TR)-35022)
DOI: 10.1109/TII.2015.2389195
ISSN: 1551-3203
WoS: 000352290400005
Scopus: 2-s2.0-84926452916
Колекције
Институција/група
Mašinski fakultetTY - JOUR AU - Jakovljević, Živana AU - Puzović, Radovan AU - Pajić, Miroslav PY - 2015 UR - https://machinery.mas.bg.ac.rs/handle/123456789/2195 AB - Within industrial automation systems, three-dimensional (3-D) vision provides very useful feedback information in autonomous operation of various manufacturing equipment (e.g., industrial robots, material handling devices, assembly systems, and machine tools). The hardware performance in contemporary 3-D scanning devices is suitable for online utilization. However, the bottleneck is the lack of real-time algorithms for recognition of geometric primitives (e.g., planes and natural quadrics) from a scanned point cloud. One of the most important and the most frequent geometric primitive in various engineering tasks is plane. In this paper, we propose a new fast one-pass algorithm for recognition (segmentation and fitting) of planar segments from a point cloud. To effectively segment planar regions, we exploit the orthonormality of certain wavelets to polynomial function, as well as their sensitivity to abrupt changes. After segmentation of planar regions, we estimate the parameters of corresponding planes using standard fitting procedures. For point cloud structuring, a z-buffer algorithm with mesh triangles representation in barycentric coordinates is employed. The proposed recognition method is tested and experimentally validated in several real-world case studies. PB - IEEE - Inst Electrical Electronics Engineers Inc, Piscataway T2 - IEEE Transactions on Industrial Informatics T1 - Recognition of Planar Segments in Point Cloud Based on Wavelet Transform EP - 352 IS - 2 SP - 342 VL - 11 DO - 10.1109/TII.2015.2389195 ER -
@article{ author = "Jakovljević, Živana and Puzović, Radovan and Pajić, Miroslav", year = "2015", abstract = "Within industrial automation systems, three-dimensional (3-D) vision provides very useful feedback information in autonomous operation of various manufacturing equipment (e.g., industrial robots, material handling devices, assembly systems, and machine tools). The hardware performance in contemporary 3-D scanning devices is suitable for online utilization. However, the bottleneck is the lack of real-time algorithms for recognition of geometric primitives (e.g., planes and natural quadrics) from a scanned point cloud. One of the most important and the most frequent geometric primitive in various engineering tasks is plane. In this paper, we propose a new fast one-pass algorithm for recognition (segmentation and fitting) of planar segments from a point cloud. To effectively segment planar regions, we exploit the orthonormality of certain wavelets to polynomial function, as well as their sensitivity to abrupt changes. After segmentation of planar regions, we estimate the parameters of corresponding planes using standard fitting procedures. For point cloud structuring, a z-buffer algorithm with mesh triangles representation in barycentric coordinates is employed. The proposed recognition method is tested and experimentally validated in several real-world case studies.", publisher = "IEEE - Inst Electrical Electronics Engineers Inc, Piscataway", journal = "IEEE Transactions on Industrial Informatics", title = "Recognition of Planar Segments in Point Cloud Based on Wavelet Transform", pages = "352-342", number = "2", volume = "11", doi = "10.1109/TII.2015.2389195" }
Jakovljević, Ž., Puzović, R.,& Pajić, M.. (2015). Recognition of Planar Segments in Point Cloud Based on Wavelet Transform. in IEEE Transactions on Industrial Informatics IEEE - Inst Electrical Electronics Engineers Inc, Piscataway., 11(2), 342-352. https://doi.org/10.1109/TII.2015.2389195
Jakovljević Ž, Puzović R, Pajić M. Recognition of Planar Segments in Point Cloud Based on Wavelet Transform. in IEEE Transactions on Industrial Informatics. 2015;11(2):342-352. doi:10.1109/TII.2015.2389195 .
Jakovljević, Živana, Puzović, Radovan, Pajić, Miroslav, "Recognition of Planar Segments in Point Cloud Based on Wavelet Transform" in IEEE Transactions on Industrial Informatics, 11, no. 2 (2015):342-352, https://doi.org/10.1109/TII.2015.2389195 . .