Three-Dimensional Reconstruction of Soybean Canopy Based on Multivision Technology for Calculation of Phenotypic Traits
16
Citation
27
Reference
10
Related Paper
Citation Trend
Abstract:
Precise reconstruction of the morphological structure of the soybean canopy and acquisition of plant traits have great theoretical significance and practical value for soybean variety selection, scientific cultivation, and fine management. Since it is difficult to obtain all-around information on living plants with traditional single or binocular machine vision, this paper proposes a three-dimensional (3D) method of reconstructing the soybean canopy for calculation of phenotypic traits based on multivision. First, a multivision acquisition system based on the Kinect sensor was constructed to obtain all-around point cloud data of soybean in three viewpoints, with different fertility stages of soybean as the research object. Second, conditional filtering and K-nearest neighbor filtering (KNN) algorithms were used to preprocess the raw 3D point cloud. The point clouds were matched and fused by the random sample consensus (RANSAC) and iterative closest point (ICP) algorithms to accomplish the 3D reconstruction of the soybean canopy. Finally, the plant height, leafstalk angle and crown width of soybean were calculated based on the 3D reconstruction of soybean canopy. The experimental results showed that the average deviations of the method was 2.84 cm, 4.0866° and 0.0213 m, respectively. The determination coefficients between the calculated values and measured values were 0.984, 0.9195 and 0.9235. The average deviation of the RANSAC + ICP was 0.0323, which was 0.0214 lower thanthe value calculated by the ICP algorithm. The results enable the precise 3D reconstruction of living soybean plants and quantitative detection for phenotypic traits.Keywords:
RANSAC
3D Reconstruction
RANSAC
Benchmark (surveying)
Iterative closest point
Representation
Cite
Citations (39)
Many low- or middle-level three-dimensional reconstruction algorithms involve a robust estimation and selection step whereby parameters of the best model are estimated and inliers fitting this model are selected. The RANSAC (RANdom SAmple consensus) algorithm is the most widely used robust algorithm for this task. A new version of RANSAC, called distributed RANSAC (D-RANSAC), is proposed, to save computation time and improve accuracy. The authors compare their results with those of classical RANSAC and randomised RANSAC (R-RANSAC). Experiments show that D-RANSAC is superior to RANSAC and R-RANSAC in computational complexity and accuracy in most cases, particularly when the inlier proportion is below 65%.
RANSAC
Cite
Citations (29)
For interactive visualization in AR devices, feature descriptors of point clouds (as-designed model and as-built model) are corresponded and registered. However, point cloud of indoor environment has lots of similar feature descriptors (e.g., indoor scene with similar doors and windows), which leads to many false correspondences and affect registration accuracy. This paper proposes a random sample consensus (RANSAC)-based false correspondence rejection to compute accurate transformation for the registration of such 3D point clouds. Point cloud data is collected from rooms and a hallway of a campus building, and transformation accuracy for the registration of those point clouds is tested. The results show that RANSAC-based false correspondence rejection gives transformation accuracy of 0.017 radians and 0.1924 meters in aligning two point cloud models, and hence the proposed registration approach of a model point cloud with scene point cloud may provide a foundation to accurately implement the AR on a construction jobsite.
RANSAC
Feature (linguistics)
Rigid transformation
Cite
Citations (9)
RANSAC
Feature (linguistics)
Cite
Citations (43)
3D reconstruction of point cloud data is the research focus at present, but there isn't a universal 3D reconstruction method for point cloud data which is scattered topology structure. At the same time, 3D reconstruction method of point cloud data also exist many problem, such as: 3D modeling efficiency is low, 3D reconstruction model exist holes, 3D model isn't quite true. To solve these problems in 3D reconstruction of point cloud data, this paper provides a 3D reconstruction method for laser spiral scanning point cloud, the 3D reconstruction method which has high efficiency, true model and retains model details can solve the problem of 3D reconstruction .To verify the effectiveness of algorithm, this paper choose a set of spiral point cloud which will be sorted and optimized, finally these point cloud data have been transferred into 3D expected solid model which will provide a good basic for future usage of point cloud data.
Laser Scanning
3D Reconstruction
Solid modeling
Surface reconstruction
3D modeling
Cite
Citations (3)
Quantitative assessment is essential to ensure correct diagnosis and effective treatment of chronic wounds. So far, devices with depth cameras and infrared sensors have been used for the computer-aided diagnosis of cutaneous wounds. However, these devices have limited accessibility and usage. On the other hand, smartphones are commonly available, and threedimensional (3D) reconstruction using smartphones can be an important tool for wound assessment. In this paper, we analyze various open source libraries for smartphone-based 3D reconstruction of wounds. For this, point clouds are obtained from cutaneous wound regions using Google ARCore and Structure from Motion (SfM) libraries. These point clouds are subjected to de-noising filters to remove outliers and to improve the density of the point cloud. Subsequently, surface reconstruction is performed on the point cloud to generate a 3D model. Six different mesh-reconstruction algorithms namely Delaunay triangulation, convex hull, point crust, Poisson surface reconstruction, alpha complex, and marching cubes are considered. The performances are evaluated using the quality metrics such as complexity, the density of point clouds, the accuracy of depth information and the efficacy of the reconstruction algorithm. The result shows that the point clouds are able to perform 3D reconstruction of wounds using open source libraries. It is found that the point clouds obtained from SfM have higher density and accuracy as compared to ARCore. Comparatively, the Poisson surface reconstruction is found to be the best algorithm for effective 3D reconstruction from the point clouds. However, research is still required on the techniques to enhance the quality of point clouds obtained through the smartphones and to reduce the computational cost associated with point cloud based 3D-reconstruction.
Surface reconstruction
3D Reconstruction
Structure from Motion
Cite
Citations (5)
During the course of 3d surface reconstruction,there are a large number of noises and isolated 3d points in raw 3d point clouds,which obtained from images.If we directly use these data to reconstruct surface,the algorithm will make surface sharply prominent and ineffective reconstruction.Because of above problems,a method that sieving 3d point clouds based on DBSCAN is presented in this paper,and then 3d surface is reconstructed using filtered 3d point clouds.Experiments show that good 3d surface reconstruction is obtained using this algorithm.
Surface reconstruction
3D Reconstruction
DBSCAN
3d model
Cite
Citations (0)
3D Reconstruction
Cite
Citations (1)
Abstract Surface reconstruction technology has always been an important research area in graphic image. However, efficiently processing massive amounts of high-precision point cloud data is still a problem worth studying. Based on the characteristics of point cloud data and the existing research results, this paper proposes a RANSAC algorithm based on voxel segmentation and applies it to 3D surface reconstruction. By analyzing the characteristics of the original point cloud data, the method improves the reconstruction speed of the 3D model while retaining a large amount of effective feature information and ensuring high precision. The experimental results show that compared with the reconstruction algorithm based on the original RANSAC algorithm, the proposed algorithm can effectively reduce the surface reconstruction time of 47.51%, and the model error after processing is only one thousandth compared with the original model.
RANSAC
Surface reconstruction
3D Reconstruction
Feature (linguistics)
Bundle adjustment
Coplanarity
Cite
Citations (1)
3D Reconstruction
Surface reconstruction
Representation
Cite
Citations (0)