ABSTRACT
This paper proposes an efficient and robust four-step process to extracting fruit shape from background. At first, point clouds is divided into octree cells by an adaptive subdivision; Second, converting teach octree cell into a splat and approximating its local surface with MLS; Third, estimating geometric properties of each splat by Principal Component Analysis (PCA) and covariance analysis; Forth, a recursive incremental process is employed to finding geometric similarity splats and generating ultimate splats set of fruit. Paper provides, finally, eleven angles range scans of an apple and demonstrates segmentation of apple shape from leaves. The result proves the validity and practicability of this method in segmentation.
- G. Sithole, G. Vosselman. 2003. Automatic Structure Detection In a Point Cloud of an Urban Landscape. Proceedings 2nd GRSS/ISPRS Joint Workshop on Remote Sensing and Data Fusion over Urban Areas. 67--71Google ScholarCross Ref
- Jae-Young Sim, Sang-Uk Lee, Chang-Su Kim. 2009. Construction of Regular 3D Point Clouds Using Octree Partitioning and Resampling. IEEE International Symposium on Circuits and Systems (ISCAS). 956--959.Google Scholar
- Jyun-Yuan Chen and Chao-Hung Lin. 2010. Neighborhood Selection for Differential Coordinates of 3D Point Clouds. International Journal of Innovative Computing, Information and Control, vol.6, no.6, 2393--2406.Google Scholar
- LiuJie, Zhang Jianqing, Xu Jia. 2008. Cultural Relic 3D Reconstruction from Digital Images and Laser Point Clouds. Congress on Image and Signal Processing. 349--353. Google ScholarDigital Library
- Lleo L, Barreiro P, Ruiz-Altisent M, et al. 2009. Investigation of the Effect of Shape on the Acoustic Response of 'Conference' Pears by Finite Element Modelling, Journal of Food Engineering. vol.93, no.2, 229--235.Google ScholarCross Ref
- Marc Rioux, Tony Bird. 1992. White Laser Synced Scan (3D Scanner). IEEE Computer Graphics and Applications. vol.13, no.3, 15--17. Google ScholarDigital Library
- Markus Gross, Hanspeter Pfister, et al. 2007. Point-Based Graphics. Morgan Kaufmann Publishers. 149--166, 109--127, 408--412. Google ScholarDigital Library
- Matthias Zwicker, Hanspeter Pfister, Jeroen van Baar, et al. 2001. Surface Splatting in Computer Graphics. SIGGRAPH 2001 Proceedings. 371--378. Google ScholarDigital Library
- Rosell, Joan R, Llorens Jordi, Sanz Ricardo, et al. 2009. Obtaining the Three-Dimensional Structure of Tree Orchards From Remote 2D Terrestrial LIDAR Scanning. Agricultural and Forest Meteorology. vol.149, no.9, 1505--1515.Google Scholar
- Smith LI. 2002. A Tutorial on Principal Components Analysis. Cornell University, USA.Google Scholar
- Uyar R, Erdogdu F. 2009. Potential Use of 3-Dimensional Scanners for Food Process Modeling. Journal of Food Engineering: vol.93, no.3, 337--343.Google ScholarCross Ref
- Wang Shi dong, Chen Yang, Zhang Ben fu, et al. 2006. The Application of Octrees In 3D Modeling, Journal of Anhui Institute of Architecture & Industry. 96--98.Google Scholar
Index Terms
- A novel algorithm for segmenting fruit from unorganized point clouds
Recommendations
Automatic stem-leaf segmentation of maize shoots using three-dimensional point cloud
Highlights- The proposed stem-leaf segmentation approach is fully automatic.
- The stem-leaf ...
AbstractThe application of 3D point cloud data in maize research is increasingly extensive. Currently, there are many approaches to acquiring three-dimensional (3D) point clouds of maize plants. However, automatic stem-leaf segmentation of ...
Semi-automatic segmentation of 3d point clouds skeleton without explicit computation for critical points
PRICAI'12: Proceedings of the 12th Pacific Rim international conference on Trends in Artificial IntelligenceSegmentation of 3D point clouds is vigorously discussed in recent years. Many existing techniques pre-process the data to identify critical points for meaningful features. Very often, the critical points are predicted at curvature objects and this does ...
Computing refined skeletal features from medial point clouds
We present methods for computing refined features from 3D medial-surface point clouds.Features include: medial point classification, medial surface decomposition into sheets, Y-network extraction, and robust regularization.We compute our refined ...
Comments