Registration method of point clouds using improved digital image correlation coefficient

Liu, Shifan; Liang, Jin; Gong, Chunyuan; Pai, Wenyan

doi:10.1117/1.oe.57.11.113104

Cited by 6 publications

(5 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It could be seen from Figure 9 that the three evaluation indicators of the error based on the inverse distance weighted Studies have shown that spatial interpolation methods have proven to be an important technique in point cloud data preprocessing (Liu S. F. et al, 2018). In addition to the three interpolation methods used in this study, Agüera-Vega et al ( 2020) also compared inverse distance weighting (IDW), multiple quadratic radial basis functions (MRBF), kriging (KR) and linear interpolation triangulation (TLI) in processing point clouds extracted from drone images, which shows that the interpolation method has great potential, especially the point cloud data has been widely used.…”

Section: Comparison Results Of Different Interpolation Methodsmentioning

confidence: 99%

Identification lodging degree of wheat using point cloud data and convolutional neural network

Yang²,

Zhou³

et al. 2022

Front. Plant Sci.

View full text Add to dashboard Cite

Wheat is one of the important food crops, and it is often subjected to different stresses during its growth. Lodging is a common disaster in filling and maturity for wheat, which not only affects the quality of wheat grains, but also causes severe yield reduction. Assessing the degree of wheat lodging is of great significance for yield estimation, wheat harvesting and agricultural insurance claims. In particular, point cloud data extracted from unmanned aerial vehicle (UAV) images have provided technical support for accurately assessing the degree of wheat lodging. However, it is difficult to process point cloud data due to the cluttered distribution, which limits the wide application of point cloud data. Therefore, a classification method of wheat lodging degree based on dimensionality reduction images from point cloud data was proposed. Firstly, 2D images were obtained from the 3D point cloud data of the UAV images of wheat field, which were generated by dimensionality reduction based on Hotelling transform and point cloud interpolation method. Then three convolutional neural network (CNN) models were used to realize the classification of different lodging degrees of wheat, including AlexNet, VGG16, and MobileNetV2. Finally, the self-built wheat lodging dataset was used to evaluate the classification model, aiming to improve the universality and scalability of the lodging discrimination method. The results showed that based on MobileNetV2, the dimensionality reduction image from point cloud obtained by the method proposed in this paper has achieved good results in identifying the lodging degree of wheat. The F1-Score of the classification model was 96.7% for filling, and 94.6% for maturity. In conclusion, the point cloud dimensionality reduction method proposed in this study could meet the accurate identification of wheat lodging degree at the field scale.

show abstract

Section: Comparison Results Of Different Interpolation Methodsmentioning

confidence: 99%

Identification lodging degree of wheat using point cloud data and convolutional neural network

Yang²,

Zhou³

et al. 2022

Front. Plant Sci.

View full text Add to dashboard Cite

show abstract

“…To obtain accurate model data, the inverse scanning method is used to obtain the point cloud data of the 3D model of the helmet through the scanner [15] . To form a more accurate model in the later stage, the scanning points are pasted on the helmet mold in turn, and the positions with larger curvature need to be set more.…”

Section: Build a 3d Model Of The Helmetmentioning

confidence: 99%

Research on topology optimization of carbon fiber reinforced composite electric vehicle helmet based on deep learning

Zhang,

Wei,

et al. 2024

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

To study the topology optimization of carbon fiber composite helmets, a method of optimizing the three-dimensional (hereinafter referred to as 3D) model based on a deep learning network after dimensionality reduction is proposed. In this method, the 3D shell model is expanded and tiled into two-dimensional (hereinafter referred to as 2D) grids based on the one-step inverse forming method. The variable density method (Isotropic Material Penalty Density method) is used to collect the data set required for deep learning training, and the U-Net neural network is built to complete the training. To obtain the input tensor of the neural network, the mechanical analysis of the 3D model is carried out, and the physical properties are imported into the network for learning. In this way, the 2D optimization results of the helmet model are obtained and then reflected in the 3D model according to the unit topology relationship to obtain the final optimization results. Then, the ordinary helmet and the optimized helmet are simulated and compared under the same quality to test their mechanical properties. The results show that the stiffness performance and energy absorption effect of the optimized helmet are stronger when the quality of the two helmets is the same.

show abstract

“…Therefore, we select the principal curvature as the descriptor. Although the two principal curvature directions can be estimated by PCA after projecting neighboring normal vectors onto the tangent plane [25], it is a complex and time-consuming procedure. To address this problem, we build a 3 × 3 matrix to describe the two principal curvatures according to the distribution of neighboring normal vectors.…”

Section: Generation Of Geometrical Descriptormentioning

confidence: 99%

An edge-sensitive simplification method for scanned point clouds

Liu¹,

Liang²,

Ren³

et al. 2020

Meas. Sci. Technol.

View full text Add to dashboard Cite

Point cloud simplification is concerned with reducing the number of redundant points and preserving geometric features, so as to provide a better representation of the underlying surface. In early research, many researchers focused on the moving least squares (MLS) method, volume data, and iterative simplification. MLS is used to construct local surfaces implicitly [3,4], and points are projected to the surface for down sampling. Kobbelt et al [5] simplified point clouds by extracting feature-sensitive surfaces based on volume data. Lipman et al [6] proposed a locally optimal projection (LOP) operator and applied it to raw scanned data with complex shapes. Huang et al [7] developed a weighted locally optimal projection (WLOP) operator based on LOP, which has proven to be less sensitive to noise and has the advantage of producing an evenly distributed point cloud. To reduce the computational complexity of WLOP, Yang et al [8] focused on the decomposition of a point cloud and created multiple output results by Measurement Science and Technology

show abstract

Registration method of point clouds using improved digital image correlation coefficient

Cited by 6 publications

References 23 publications

Identification lodging degree of wheat using point cloud data and convolutional neural network

Identification lodging degree of wheat using point cloud data and convolutional neural network

Research on topology optimization of carbon fiber reinforced composite electric vehicle helmet based on deep learning

An edge-sensitive simplification method for scanned point clouds

Contact Info

Product

Resources

About