Affiliation:
1. School of Technology, Beijing Forestry University, Beijing 100083, China
Abstract
Deep learning classification based on 3D point clouds has gained considerable research interest in recent years.The classification and quantitative analysis of wood defects are of great significance to the wood processing industry. In order to solve the problems of slow processing and low robustness of 3D data. This paper proposes an improvement based on littlepoint CNN lightweight deep learning network, adding BN layer. And based on the data set made by ourselves, the test is carried out. The new network bnlittlepoint CNN has been improved in speed and recognition rate. The correct rate of recognition for non defect log, non defect log and defect log as well as defect knot and dead knot can reach 95.6%.Finally, the "dead knot" and "loose knot" are quantitatively analyzed based on the "integral" idea, and the volume and surface area of the defect are obtained to a certain extent,the error is not more than 1.5% and the defect surface reconstruction is completed based on the triangulation idea.
Publisher
North Atlantic University Union (NAUN)
Subject
Electrical and Electronic Engineering,Signal Processing
Reference33 articles.
1. Date, H., Kaneta, Y., Hatsukaiwa, A., et al. (2012). Object recognition in terrestrial laser scan data using spin images. Computer-Aided Design and Applications, 9(2), 187-197.
2. Holmgren, J., Persson, A. (2004). Identifying species of individual trees using airborne laser scanner. Remote Sensing of Environment, 90(4), 415-423.
3. Janoch, A., Karayev, S., Jia, Y., et al. (2012). A category-level 3D object dataset: putting the kinect to work. London: Springer, 141-165.
4. Wang Y , Sun Y , Liu Z , et al. Dynamic Graph CNN for Learning on Point Clouds[J]. 2018.
5. Qi, C. R., Su, H., Mo, K., et al. (2016). Point Net: Deep learning on point sets for 3D classification and segmentation. ar Xiv preprint ar Xiv:1612.00593, 77-85.