Search

In response to the structural changes of tomato seedlings, traditional image techniques are difficult to accurately quantify key morphological parameters, such as leaf area, internode length, and mutual occlusion between organs. Therefore, this paper proposes a tomato point cloud stem and leaf segmentation framework based on Elite Strategy-based Improved Red-billed Blue Magpie Optimization (ES-RBMO) Algorithm. The framework uses a four-layer Convolutional Neural Network (CNN) for stem and leaf segmentation by incorporating an improved swarm intelligence algorithm with an accuracy of 0.965. Four key phenotypic parameters of the plant were extracted. The phenotypic parameters of plant height, stem thickness, leaf area and leaf inclination were analyzed by comparing the values extracted by manual measurements with the values extracted by the 3D point cloud technique. The results showed that the coefficients of determination (R2) for these parameters were 0.932, 0.741, 0.938 and 0.935, respectively, indicating high correlation. The root mean square error (RMSE) was 0.511, 0.135, 0.989 and 3.628, reflecting the level of error between the measured and extracted values. The absolute percentage errors (APE) were 1.970, 4.299, 4.365 and 5.531, which further quantified the measurement accuracy. In this study, an efficient and adaptive intelligent optimization framework was constructed, which is capable of optimizing data processing strategies to achieve efficient and accurate processing of tomato point cloud data. This study provides a new technical tool for plant phenotyping and helps to improve the intelligent management in agricultural production. [ABSTRACT FROM AUTHOR]

Phenotypic analysis of mature soybeans is a critical aspect of soybean breeding. However, manually obtaining phenotypic parameters not only is time-consuming and labor intensive but also lacks objectivity. Therefore, there is an urgent need for a rapid, accurate, and efficient method to collect the phenotypic parameters of soybeans. This study develops a novel pipeline for acquiring the phenotypic traits of mature soybeans based on three-dimensional (3D) point clouds. First, soybean point clouds are obtained using a multi-view stereo 3D reconstruction method, followed by preprocessing to construct a dataset. Second, a deep learning-based network, PVSegNet (Point Voxel Segmentation Network), is proposed specifically for segmenting soybean pods and stems. This network enhances feature extraction capabilities through the integration of point cloud and voxel convolution, as well as an orientation-encoding (OE) module. Finally, phenotypic parameters such as stem diameter, pod length, and pod width are extracted and validated against manual measurements. Experimental results demonstrate that the average Intersection over Union (IoU) for semantic segmentation is 92.10%, with a precision of 96.38%, recall of 95.41%, and F1-score of 95.87%. For instance segmentation, the network achieves an average precision (AP@50) of 83.47% and an average recall (AR@50) of 87.07%. These results indicate the feasibility of the network for the instance segmentation of pods and stems. In the extraction of plant parameters, the predicted values of pod width, pod length, and stem diameter obtained through the phenotypic extraction method exhibit coefficients of determination ( R 2 ) of 0.9489, 0.9182, and 0.9209, respectively, with manual measurements. This demonstrates that our method can significantly improve efficiency and accuracy, contributing to the application of automated 3D point cloud analysis technology in soybean breeding. [ABSTRACT FROM AUTHOR]

Point cloud segmentation is necessary for obtaining highly precise morphological traits in plant phenotyping. Although a huge development has occurred in point cloud segmentation, the segmentation of point clouds from complex plant leaves still remains challenging. Rapeseed leaves are critical in cultivation and breeding, yet traditional two-dimensional imaging is susceptible to reduced segmentation accuracy due to occlusions between plants. The current study proposes the use of binocular stereo-vision technology to obtain three-dimensional (3D) point clouds of rapeseed leaves at the seedling and bolting stages. The point clouds were colorized based on elevation values in order to better process the 3D point cloud data and extract rapeseed phenotypic parameters. Denoising methods were selected based on the source and classification of point cloud noise. However, for ground point clouds, we combined plane fitting with pass-through filtering for denoising, while statistical filtering was used for denoising outliers generated during scanning. We found that, during the seedling stage of rapeseed, a region-growing segmentation method was helpful in finding suitable parameter thresholds for leaf segmentation, and the Locally Convex Connected Patches (LCCP) clustering method was used for leaf segmentation at the bolting stage. Furthermore, the study results show that combining plane fitting with pass-through filtering effectively removes the ground point cloud noise, while statistical filtering successfully denoises outlier noise points generated during scanning. Finally, using the region-growing algorithm during the seedling stage with a normal angle threshold set at 5.0/180.0* M_PI and a curvature threshold set at 1.5 helps to avoid the under-segmentation and over-segmentation issues, achieving complete segmentation of rapeseed seedling leaves, while the LCCP clustering method fully segments rapeseed leaves at the bolting stage. The proposed method provides insights to improve the accuracy of subsequent point cloud phenotypic parameter extraction, such as rapeseed leaf area, and is beneficial for the 3D reconstruction of rapeseed. [ABSTRACT FROM AUTHOR]

Graph Convolutional Neural Networks (GCNs) have demonstrated significant efficiency and flexibility in processing irregular data. And since point clouds are essentially irregular points discretely distributed in space, GCNs have great potential for application in point cloud segmentation tasks. However, current GCNs struggle to learn global structure and local details efficiently. Furthermore, their excessive use of Max pooling results in the substantial loss of contextual structural information. To address the above problems, we present a novel hierarchical graph structure learning network (SGSLNet), which mainly consists of structure-aware Adaptive Graph Convolution (GAdaptive Conv) and Stratified Contextual Graph Pooling (SCGP). GAdaptive Conv is used to dynamically learn local geometric structures, while SCGP is employed to aggregate features and model global contextual structures. Our method not only learns global structure and local details concurrently but also reduces the loss of contextual structure information. We conduct extensive experiments on various datasets, including ShapeNetPart, S3DIS, and ScanNet v2. The results show that SGSLNet achieves state-of-the-art segmentation performance. [ABSTRACT FROM AUTHOR]

The extraction of geometric features such as holes, arcs, and surfaces of mechanical parts is crucial for quality control. The existing methods for geometrical feature segmentations on 3D point clouds still have limitations, especially for simultaneously extracting multiple types of geometric features from comprehensive workpieces. To this end, this study investigates segmentation methods that take 3D point cloud datasets of mechanical parts as inputs, and employs an improved PointNet++ deep learning model to solve this extraction difficulty. Firstly, the Set Abstraction module in PointNet++ was modified by incorporating Self-Attention mechanisms to increase interactivity and global correlation among data points. Then, the local feature extraction Multilayer Perceptron (MLP) from PointNet-Transformer was integrated to enhance the feature extraction accuracy. Due to the inherent class imbalance issue, the Focal Tversky Loss is employed as the loss function to ensure that geometric features with relatively lower proportions can be fully trained. Finally, the Statistical filtering algorithm is utilized to mitigate noise and attenuate subtle irregularities, such that the smoothness of geometric features can be substantially enhanced. The experimental results demonstrate that the proposed model achieves an accuracy of 86.6% on geometric feature segmentations and a mean Intersection over Union (mIoU) of 0.84. The comparison with the original PointNet++ proves that the proposed method can improve accuracy and mIoU by 3.7% and 0.03 respectively. [ABSTRACT FROM AUTHOR]

Automation in the construction has seen progress in using modern techniques, which has opened new perspectives for the verification of construction structures using point clouds. This paper discusses wall structure geometry verification, using point cloud data with geometry information extracted from building information modeling models as reference data. The research is focusing on automating the verification of wall structures using a software solution developed in Python. It involves processing and extracting geometric data from models in industry foundation classes' format, comparing the data and visualization of deviation. Results, conclusion, and future workplans are given for achieving better understanding. [ABSTRACT FROM AUTHOR]

Intelligent analysis of 3D point clouds has become a frontier in emerging fields such as autonomous driving, digital twins, and the metaverse. Precise segmentation of 3D point clouds is particularly important within these domains; however, it faces several challenges: (1) point cloud data inherently lacks structured topological information; (2) point cloud shapes are complex and highly variable, making it difficult to utilize semantic priors; and (3) the sampling process of point clouds may result in sparse and uneven data. To address these issues, this paper proposes a novel Point Cloud Segmentation Network based on multi-scale feature fusion and Transformer architecture (MFFTNet). MFFTNet enhances the performance of existing segmentation methods by globally modeling the overall point cloud shape and embedding local point cloud details. Specifically, MFFTNet divides the segmentation task into encoding and decoding stages. The encoder is designed as a hierarchical pyramid structure that extracts relatively sparse local center points and fuses local features during progressive downsampling. It also utilizes a Transformer for global feature modeling to establish multi-scale topological and semantic information of the point cloud. Subsequently, multi-scale feature fusion further enhances the network’s perception of local features and global structure. The decoder progressively upsamples to restore the original point cloud and injects multi-scale feature information to achieve precise segmentation. Based on the aforementioned encoding-decoding structure and multi-scale feature fusion, MFFTNet outperforms existing methods on the point cloud semantic segmentation datasets ShapeNetPart and S3DIS.

Identifying shapeless granular materials in complex construction scenarios is critical for achieving automation in engineering equipment such as wheel loaders. The challenges of segmenting point clouds for granular materials involve dealing with sparsity, real-time processing requirements, the lack of distinct shape representation, and the issue of different materials sharing similar shapes. This paper proposes MVSRF, a real-time multi-view based point cloud semantic segmentation method incorporating a single-frame re-segmentation component and a multi-frame semantic filter to enhance accuracy and robustness. First, the segmentation system generates a sparse pixel-depth grid map via semantic projection to encapsulate global points and their behaviors, while employing an edge detector to label boundary points around objects. Second, a zero-shot re-segmentation algorithm involving seed extension, novel one-dimensional DBSCAN, Delaunay triangulation, and semantic reassignment corrects mis-segmented points caused by mapping bias. Finally, a lightweight semantic filter is designed to suppress semantic noise during multiple observations. We have built a multi-sensor platform on a wheel loader and collected experimental data to verify the effectiveness of our method. Two optimization components illustrated exceptional performance on the annotated dataset. The MVSRF method possesses strong robustness against external calibration errors, camera pose estimation errors, and inaccurate image segmentation, providing a practical solution for real-time perception of granular materials. [ABSTRACT FROM AUTHOR]

Airborne laser scanning (ALS) point clouds have emerged as a predominant data source for the generation of digital elevation models (DEM) in recent years. Traditionally, the generation of DEM using ALS point clouds involves the steps of point cloud classification or ground point filtering to extract ground points and labor-intensive post-processing to correct the misclassified ground points. The current deep learning techniques leverage the ability of geometric recognition for ground point classification. However, the deep learning classifiers are generally trained using 3D point clouds with simple geometric terrains, which decrease the performance of model inferencing. In this study, a point-based deep learning model with boosting ensemble learning and a set of geometric features as the model inputs is proposed. With the ensemble learning strategy, this study integrates specialized ground point classifiers designed for different terrains to boost classification robustness and accuracy. In experiments, ALS point clouds containing various terrains were used to evaluate the feasibility of the proposed method. The results demonstrated that the proposed method can improve the point cloud classification and the quality of generated DEMs. The classification accuracy and F1 score are improved from 80.9% to 92.2%, and 82.2% to 94.2%, respectively, by using the proposed methods. In addition, the DEM generation error, in terms of mean squared error (RMSE), is reduced from 0.318–1.362 m to 0.273–1.032 m by using the proposed ensemble learning. [ABSTRACT FROM AUTHOR]

Installation quality check is essential for ensuring the construction quality of prefabrication construction. The existing techniques for assessing the installation quality of prefabricated wall panels heavily depend on manual inspection and contact-type measurements, which is labor intensive and slow. Laser scanning was previously adopted in construction quality check, however, few studies have focused on using laser scanners to assess the verticality of prefabricated wall panels, and no method has been developed for effective practical implementation. This study proposes a streamlined laser scanning approach for onsite verticality check of prefabricated wall panels. Based on systematic experiments of using the point cloud data collected by different types of laser scanners, and 25 prefabrication wall panels of four shapes, this study validates the proposed method and compares the use of different laser scanners. To facilitate an effective streamlined process for practical use, this study identifies the point cloud segmentation parameters under different laser scanning data sets and suggests suitable parameters for these case scenarios. These parameters can be adopted directly or used as references for practical application of the proposed laser scanning method in the installation verticality check. This study contributes to improving the efficiency of installation quality check of prefabrication construction, and facilitating the digital evolution of the construction industry. Practical Applications: Checking the verticality of the installed prefabricated wall panels is crucial in construction quality control. However, traditional methods for assessing the installation quality of prefabricated wall panels heavily depend on manual inspection and contact-type measurements, which is labor-intensive, slow, and costly. For project involves a large number of same or similar type of prefabricated construction elements, this repetitive work also causes human fatigue and in-efficiency. This paper proposes a laser scanning method to streamline the quality check process for the installation of prefabricated wall panels. By systematically experimenting with the point cloud data collected by different types of laser scanners for various wall panels of different shapes, this study validates the effectiveness of the proposed method. Another major contribution of this research is preidentification of optimal segmentation parameters for laser scanning point cloud. This means construction professionals can use these parameters directly or as references for identifying suitable segmentation parameters for other projects. The streamlined laser scanning method contributes greatly to improving the efficiency of installation quality check of prefabrication construction practice, especially when large number of identical or similar elements are used. [ABSTRACT FROM AUTHOR]

Seepage failure of levees can cause landslides and other hazards. Three-dimensional (3D) laser-scanning technology has become a new method for collecting levee hazard data. In this study, the 3D characteristics of landslide point clouds were investigated through systematic indoor model tests, and a feature recognition algorithm applicable to levee landslides was proposed. The major outcomes of this study are as follows: 1) the formulation of an adaptive random sampling boundary extraction (A-R-B) algorithm, which integrates random sample consensus plane segmentation, adaptive distance threshold calculation, and boundary extraction for levee landslide disaster recognition; 2) through feasibility analyses and accuracy tests of the A-R-B algorithm, this study demonstrated the capacity of the proposed method to accurately recognise the features of levee landslides, with a relative accuracy of 1 cm and an absolute accuracy of 3.5 cm in the extraction process; 3) the testing of the A-R-B algorithm and optimal parameters for the recognised levee landslide features using the point clouds obtained from laboratory models. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Mine Automation is the property of Industry & Mine Automation Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This work focuses on the improvement of the density peaks clustering (DPC) algorithm and its application to point cloud segmentation in LiDAR. The improvement of DPC focuses on avoiding the manual determination of the cut-off distance and the manual selection of cluster centers. And the clustering process of the improved DPC is automatic without manual intervention. The cut-off distance is avoided by forming a voxel structure and using the number of points in the voxel as the local density of the voxel. The automatic selection of cluster centers is realized by selecting the voxels whose gamma values are greater than the gamma value of the inflection point of the fitted γ curve as cluster centers. Finally, a new merging strategy is introduced to overcome the over-segmentation problem and obtain the final clustering result. To verify the effectiveness of the improved DPC, experiments on point cloud segmentation of LiDAR under different scenes were conducted. The basic DPC, K-means, and DBSCAN were introduced for comparison. The experimental results showed that the improved DPC is effective and its application to point cloud segmentation of LiDAR is successful. Compared with the basic DPC, K-means, the improved DPC has better clustering accuracy. And, compared with DBSCAN, the improved DPC has comparable or slightly better clustering accuracy without nontrivial parameters. [ABSTRACT FROM AUTHOR]

Maize growth parameters are key pieces of information describing the growth, development and yield of plants, and they are of great significance for high quality and high yield maize breeding. Plants counting, row spacing, and plant spacing are closely related to maize sowing quality and yield. Plant height is closely related to maize photosynthetic rate and biomass. The main problem with measuring phenotypic parameters during the maize seedling stage is that maize plants are small, making it difficult to segment maize plant point clouds from ground point clouds, and there is a lack of automatic methods for measuring growth parameters. A point cloud intensity segmentation and improved Euclidean clustering method for single plant segmentation was proposed based on terrestrial laser scanning (TLS) technical, and an automatic measuring method of growth parameters of maize seedling stage was realized. First, TLS was used to scan maize plants at two planting densities at V1 (first leaf is fully expanded) and V2 (second leaf is fully expanded) stages. Second, the segmentation based on point cloud intensity method and the improved Euclidean clustering single plant segmentation method were used to achieve the segmentation of a single maize plant. Finally, the automatic measurement of maize plants counting, row spacing, plant spacing, and plant height were realized. When plants counting of maize, the percentage error was lower than 1.70%. In the measurement of row spacing, plant spacing and plant height of maize plants, the mean absolute percentage error (MAPE) were lower than 1.50%, 5.50% and 3.10%, respectively. These results demonstrate that the point cloud intensity segmentation and growth parameters measurement method is feasible for maize V1 and V2 stages and different planting densities. The automatic measurement values of the number of maize plants, row spacing, plant spacing and plant height has high measurement accuracy and small error. This study provides a rapid, automatic and accurate measurement method for researchers to measure maize growth parameters.

ObjectiveThe body size parameter of cattle is a key indicator reflecting the physical development of cattle, and is also a key factor in the cattle selection and breeding process. In order to solve the demand of measuring body size of beef cattle in the complex environment of large-scale beef cattle ranch, an image acquisition device and an automatic measurement algorithm of body size were designed.MethodsFirstly, the walking channel of the beef cattle was established, and when the beef cattle entered the restraining device through the channel, the RGB and depth maps of the image on the right side of the beef cattle were acquired using the Inter RealSense D455 camera. Secondly, in order to avoid the influence of the complex environmental background, an improved instance segmentation network based on Mask2former was proposed, adding CBAM module and CA module, respectively, to improve the model's ability to extract key features from different perspectives, extracting the foreground contour from the 2D image of the cattle, partitioning the contour, and comparing it with other segmentation algorithms, and using curvature calculation and other mathematical methods to find the required body size measurement points. Thirdly, in the processing of 3D data, in order to solve the problem that the pixel point to be measured in the 2D RGB image was null when it was projected to the corresponding pixel coordinates in the depth-valued image, resulting in the inability to calculate the 3D coordinates of the point, a series of processing was performed on the point cloud data, and a suitable point cloud filtering and point cloud segmentation algorithm was selected to effectively retain the point cloud data of the region of the cattle's body to be measured, and then the depth map was 16. Then the depth map was filled with nulls in the field to retain the integrity of the point cloud in the cattle body region, so that the required measurement points could be found and the 2D data could be returned. Finally, an extraction algorithm was designed to combine 2D and 3D data to project the extracted 2D pixel points into a 3D point cloud, and the camera parameters were used to calculate the world coordinates of the projected points, thus automatically calculating the body measurements of the beef cattle.Results and DiscussionsFirstly, in the part of instance segmentation, compared with the classical Mask R-CNN and the recent instance segmentation networks PointRend and Queryinst, the improved network could extract higher precision and smoother foreground images of cattles in terms of segmentation accuracy and segmentation effect, no matter it was for the case of occlusion or for the case of multiple cattles. Secondly, in three-dimensional data processing, the method proposed in the study could effectively extract the three-dimensional data of the target area. Thirdly, the measurement error of body size was analysed, among the four body size measurement parameters, the smallest average relative error was the height of the cross section, which was due to the more prominent position of the cross section, and the different standing positions of the cattle have less influence on the position of the cross section, and the largest average relative error was the pipe circumference, which was due to the influence of the greater overlap of the two front legs, and the higher requirements for the standing position. Finally, automatic body measurements were carried out on 137 beef cattle in the ranch, and the automatic measurements of the four body measurements parameters were compared with the manual measurements, and the results showed that the average relative errors of body height, cross section height, body slant length, and tube girth were 4.32%, 3.71%, 5.58% and 6.25%, respectively, which met the needs of the ranch. The shortcomings were that fewer body-size parameters were measured, and the error of measuring circumference-type body-size parameters was relatively large. Later studies could use a multi-view approach to increase the number of body rule parameters to be measured and improve the accuracy of the parameters in the circumference category.ConclusionsThe article designed an automatic measurement method based on two-dimensional and three-dimensional contactless body measurements of beef cattle. Moreover, the innovatively proposed method of measuring tube girth has higher accuracy and better implementation compared with the current research on body measurements in beef cattle. The relative average errors of the four body tape parameters meet the needs of pasture measurements and provide theoretical and practical guidance for the automatic measurement of body tape in beef cattle.

Grain is a common bulk cargo. To ensure optimal utilization of transportation space and prevent overflow accidents, it is necessary to observe the grain's shape and determine the loading status during the loading process. Traditional methods often rely on manual judgment, which results in high labor intensity, poor safety, and low loading efficiency. Therefore, this paper proposes a method for recognizing the bulk grain-loading status based on Light Detection and Ranging (LiDAR). This method uses LiDAR to obtain point cloud data and constructs a deep learning network to perform target recognition and component segmentation on loading vehicles, extract vehicle positions and grain shapes, and recognize and make known the bulk grain-loading status. Based on the measured point cloud data of bulk grain loading, in the point cloud-classification task, the overall accuracy is 97.9% and the mean accuracy is 98.1%. In the vehicle component-segmentation task, the overall accuracy is 99.1% and the Mean Intersection over Union is 96.6%. The results indicate that the method has reliable performance in the research tasks of extracting vehicle positions, detecting grain shapes, and recognizing loading status. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Mine Automation is the property of Industry & Mine Automation Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Smart Agriculture is the property of Smart Agriculture Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Film cooling is an effective technology for improving the thrust-to-weight ratio of an aero-engine. The axial orientation of film cooling holes is one of the key factors determining the film cooling effect. However, the machining quality of cooling holes is still carried out by manual inspection, whose accuracy and consistency cannot be guaranteed. To address this problem, this paper proposes an axial orientation extraction algorithm based on laser point cloud processing. Firstly, the blade surface is scanned by a line laser sensor and a blade point cloud is obtained. Secondly, a single film hole can be segmented from the blade point cloud based on scanning line fitting residual. Thirdly, an improved Gaussian map is to complement the arc belt obtained by Gaussian map to obtain a complete circle along an error-sensitive direction. Finally, the axial orientation is estimated by random sample consensus with an initial value. The accuracy and consistency of the algorithm are verified by comparing the extraction result by the algorithm with those by the Geomagic software. The result shows that the axial accuracy extracted by the algorithm can reach 0.405°. [ABSTRACT FROM AUTHOR]

Weakly-supervised point cloud segmentation with extremely limited labels is highly desirable to alleviate the expensive costs of collecting densely annotated 3D points. This paper explores applying the consistency regularization that is commonly used in weakly-supervised learning, for its point cloud counterpart with multiple data-specific augmentations, which has not been well studied. We observe that the straightforward way of applying consistency constraints to weakly-supervised point cloud segmentation has two major limitations: noisy pseudo labels due to the conventional confidence-based selection and insufficient consistency constraints due to discarding unreliable pseudo labels. Therefore, we propose a novel Reliability-Adaptive Consistency Network (RAC-Net) to use both prediction confidence and model uncertainty to measure the reliability of pseudo labels and apply consistency training on all unlabeled points while with different consistency constraints for different points based on the reliability of corresponding pseudo labels. Experimental results on the S3DIS and ScanNet-v2 benchmark datasets show that our model achieves superior performance in weakly-supervised point cloud segmentation. The code will be released publicly at https://github.com/wu-zhonghua/RAC-Net. [ABSTRACT FROM AUTHOR]

Identifying passable areas is a crucial aspect of autonomous driving technology in mining. Open-pit mining road scenes are characterized by unclear road boundaries and varying surface flatness. When using traditional concentric circle ground segmentation models for fitting mining road planes, misclassification issues often arise, such as disconnection between passable areas and vehicles, and inconsistencies in passable area recognition results across frames. This paper proposed a method for identifying passable areas in mining roads based on spatiotemporal continuous compensation. First, the mining road was modeled using a concentric circle model, and principal component analysis was applied for multi-plane fitting to obtain the initial segmentation results of passable areas. Next, based on spatial connectivity, regional connectivity filtering and point connectivity filtering were performed on the initial passable areas using the region-growing algorithm and density-based spatial clustering of applications with noise algorithm, respectively, to obtain passable areas that meet spatial connectivity criteria. Finally, to eliminate unstable regions with inconsistent passability across different point cloud frames, a grid map was constructed based on a normal distribution transformation algorithm, and temporal stability weights were used to assess grid stability, ultimately filtering out unstable regions through regional grid projection. Test results in mining indicated that the proposed method for identifying passable areas achieved an accuracy of 93.44%, representing a 2.27% improvement over existing mainstream algorithms; the recall rate was 99.14%, reflecting an 8.26% enhancement compared to current mainstream algorithms. The proposed method not only exhibits good spatial connectivity in disconnected areas but also demonstrates strong temporal stability in rugged regions.

Abstract Non‐destructive detection of wire bonding defects in integrated circuits (IC) is critical for ensuring product quality after packaging. Image‐processing‐based methods do not provide a detailed evaluation of the three‐dimensional defects of the bonding wire. Therefore, a method of 3D reconstruction and pattern recognition of wire defects based on stereo vision, which can achieve non‐destructive detection of bonding wire defects is proposed. The contour features of bonding wires and other electronic components in the depth image is analysed to complete the 3D reconstruction of the bonding wires. Especially to filter the noisy point cloud and obtain an accurate point cloud of the bonding wire surface, a point cloud segmentation method based on spatial surface feature detection (SFD) was proposed. SFD can extract more distinct features from the bonding wire surface during the point cloud segmentation process. Furthermore, in the defect detection process, a directional discretisation descriptor with multiple local normal vectors is designed for defect pattern recognition of bonding wires. The descriptor combines local and global features of wire and can describe the spatial variation trends and structural features of wires. The experimental results show that the method can complete the 3D reconstruction and defect pattern recognition of bonding wires, and the average accuracy of defect recognition is 96.47%, which meets the production requirements of bonding wire defect detection.

Phenotypic analysis of mature soybeans is a critical aspect of soybean breeding. However, manually obtaining phenotypic parameters not only is time-consuming and labor intensive but also lacks objectivity. Therefore, there is an urgent need for a rapid, accurate, and efficient method to collect the phenotypic parameters of soybeans. This study develops a novel pipeline for acquiring the phenotypic traits of mature soybeans based on three-dimensional (3D) point clouds. First, soybean point clouds are obtained using a multi-view stereo 3D reconstruction method, followed by preprocessing to construct a dataset. Second, a deep learning-based network, PVSegNet (Point Voxel Segmentation Network), is proposed specifically for segmenting soybean pods and stems. This network enhances feature extraction capabilities through the integration of point cloud and voxel convolution, as well as an orientation-encoding (OE) module. Finally, phenotypic parameters such as stem diameter, pod length, and pod width are extracted and validated against manual measurements. Experimental results demonstrate that the average Intersection over Union (IoU) for semantic segmentation is 92.10%, with a precision of 96.38%, recall of 95.41%, and F1-score of 95.87%. For instance segmentation, the network achieves an average precision (AP@50) of 83.47% and an average recall (AR@50) of 87.07%. These results indicate the feasibility of the network for the instance segmentation of pods and stems. In the extraction of plant parameters, the predicted values of pod width, pod length, and stem diameter obtained through the phenotypic extraction method exhibit coefficients of determination (R2) of 0.9489, 0.9182, and 0.9209, respectively, with manual measurements. This demonstrates that our method can significantly improve efficiency and accuracy, contributing to the application of automated 3D point cloud analysis technology in soybean breeding.

In response to the structural changes of tomato seedlings, traditional image techniques are difficult to accurately quantify key morphological parameters, such as leaf area, internode length, and mutual occlusion between organs. Therefore, this paper proposes a tomato point cloud stem and leaf segmentation framework based on Elite Strategy-based Improved Red-billed Blue Magpie Optimization (ES-RBMO) Algorithm. The framework uses a four-layer Convolutional Neural Network (CNN) for stem and leaf segmentation by incorporating an improved swarm intelligence algorithm with an accuracy of 0.965. Four key phenotypic parameters of the plant were extracted. The phenotypic parameters of plant height, stem thickness, leaf area and leaf inclination were analyzed by comparing the values extracted by manual measurements with the values extracted by the 3D point cloud technique. The results showed that the coefficients of determination (R2) for these parameters were 0.932, 0.741, 0.938 and 0.935, respectively, indicating high correlation. The root mean square error (RMSE) was 0.511, 0.135, 0.989 and 3.628, reflecting the level of error between the measured and extracted values. The absolute percentage errors (APE) were 1.970, 4.299, 4.365 and 5.531, which further quantified the measurement accuracy. In this study, an efficient and adaptive intelligent optimization framework was constructed, which is capable of optimizing data processing strategies to achieve efficient and accurate processing of tomato point cloud data. This study provides a new technical tool for plant phenotyping and helps to improve the intelligent management in agricultural production.

To address the challenges in industrial precision component detection posed by existing point cloud datasets, this research endeavors to amass and construct a point cloud dataset comprising 1101 models of miniature gears. The data collection and processing procedures are elaborated upon in detail. In response to the segmentation issues encountered in point clouds of small industrial components, a novel Point Transformer network incorporating a multiscale feature fusion strategy is proposed. This network extends the original Point Transformer architecture by integrating multiple global feature extraction modules and employing an upsampling module for contextual information fusion, thereby enhancing its modeling capabilities for intricate point cloud structures. The network is trained and tested on the self-constructed gear dataset, yielding promising results. Comparative analysis with the baseline Point Transformer network indicates a notable improvement of 1.1% in mean Intersection over Union (mIoU), substantiating the efficacy of the proposed approach. To further assess the method's effectiveness, several ablation experiments are designed, demonstrating that the introduced modules contribute to varying degrees of segmentation accuracy enhancement. Additionally, a comparative evaluation is conducted against various state-of-the-art point cloud segmentation networks, revealing the superior performance of the proposed methodology. This research not only aids in quality control, structural detection, and optimization of precision industrial components but also provides a scalable network architecture design paradigm for related point cloud processing tasks. [ABSTRACT FROM AUTHOR]

Cotton is an important economic crop; therefore, enhancing cotton yield and cultivating superior varieties are key research priorities. The seedling stage, a critical phase in cotton production, significantly influences the subsequent growth and yield of the crop. Therefore, breeding experts often choose to measure phenotypic parameters during this period to make breeding decisions. Traditional methods of phenotypic parameter measurement require manual processes, which are not only tedious and inefficient but can also damage the plants. To effectively, rapidly, and accurately extract three-dimensional phenotypic parameters of cotton seedlings, precise segmentation of phenotypic organs must first be achieved. This paper proposes a neural network-based segmentation algorithm for cotton seedling organs, which, compared to the average precision of 75.4% in traditional unsupervised learning, achieves an average precision of 96.67%, demonstrating excellent segmentation performance. The segmented leaf and stem point clouds are used for the calculation of phenotypic parameters such as stem length, leaf length, leaf width, and leaf area. Comparisons with actual measurements yield coefficients of determination R 2 of 91.97%, 90.97%, 92.72%, and 95.44%, respectively. The results indicate that the algorithm proposed in this paper can achieve precise segmentation of stem and leaf organs, and can efficiently and accurately extract three-dimensional phenotypic structural information of cotton seedlings. In summary, this study not only made significant progress in the precise segmentation of cotton seedling organs and the extraction of three-dimensional phenotypic structural information, but the algorithm also demonstrates strong applicability to different varieties of cotton seedlings. This provides new perspectives and methods for plant researchers and breeding experts, contributing to the advancement of the plant phenotypic computation field and bringing new breakthroughs and opportunities to the field of plant science research. [ABSTRACT FROM AUTHOR]

In animal husbandry applications, segmenting live pigs in complex farming environments faces many challenges, such as when pigs lick railings and defecate within the acquisition environment. The pig's behavior makes point cloud segmentation more complex because dynamic animal behaviors and environmental changes must be considered. This further requires point cloud segmentation algorithms to improve the feature capture capability. In order to tackle the challenges associated with accurately segmenting point cloud data collected in complex real-world scenarios, such as pig occlusion and posture changes, this study utilizes PointNet++. The SoftPool pooling method is employed to implement a PointNet++ model that can achieve accurate point cloud segmentation for live pigs in complex environments. Firstly, the PointNet++ model is modified to make it more suitable for pigs by adjusting its parameters related to feature extraction and sensory fields. Then, the model's ability to capture the details of point cloud features is further improved by using SoftPool as the point cloud feature pooling method. Finally, registration, filtering, and extraction are used to preprocess the point clouds before integrating them into a dataset for manual annotation. The improved PointNet++ model's segmentation ability was validated and redefined with the pig point cloud dataset. Through experiments, it was shown that the improved model has better learning ability across 529 pig point cloud data sets. The optimal mean Intersection over Union (mIoU) was recorded at 96.52% and the accuracy at 98.33%. This study has achieved the automatic segmentation of highly overlapping pigs and pen point clouds. This advancement enables future animal husbandry applications, such as estimating body weight and size based on 3D point clouds. [ABSTRACT FROM AUTHOR]

Airborne array-interferometric synthetic aperture radar (array-InSAR), one of the implementation methods of tomographic SAR (TomoSAR), has the advantages of all-time, all-weather, high consistency, and exceptional timeliness. As urbanization continues to develop, the utilization of array-InSAR data for building detection holds significant application value. Existing methods, however, face challenges in terms of automation and detection accuracy, which can impact the subsequent accuracy and quality of building modeling. On the other hand, deep learning methods are still in their infancy in SAR point cloud processing. Existing deep learning methods do not adapt well to this problem. Therefore, we propose a Position-Feature Attention Network (PFA-Net), which seamlessly integrates positional encoding with point transformer for SAR point clouds building target segmentation tasks. Experimental results show that the proposed network is better suited to handle the inherent characteristics of SAR point clouds, including high noise levels and multiple scattering artifacts. And it achieves more accurate segmentation results while maintaining computational efficiency and avoiding errors associated with manual labeling. The experiments also investigate the role of multidimensional features in SAR point cloud data. This work also provides valuable insights and references for future research between SAR point clouds and deep learning. [ABSTRACT FROM AUTHOR]

This study introduced an innovative approach for detecting structural anomalies in road manhole covers using structured light cameras. Efforts have been dedicated to enhancing data quality by commencing with the acquisition and preprocessing of point cloud data from real-world manhole cover scenes. The RANSAC algorithm is subsequently employed to extract the road plane and determine the height of the point cloud structure. In the presence of non-planar point cloud exhibiting abnormal heights, the DBSCAN algorithm is harnessed for cluster segmentation, aiding in the identification of individual objects. The method culminates with the introduction of a sector fitting detection model, adept at effectively discerning manhole cover features within the point cloud and delivering comprehensive height and structural information. Experimental findings underscore the method's efficacy in accurately gauging the degree of subsidence in manhole cover structures, with data errors consistently maintained within an acceptable range of 8 percent. Notably, the measurement speed surpasses that of traditional methods, presenting a notably efficient and dependable technical solution for road maintenance. [ABSTRACT FROM AUTHOR]

Non‐destructive detection of wire bonding defects in integrated circuits (IC) is critical for ensuring product quality after packaging. Image‐processing‐based methods do not provide a detailed evaluation of the three‐dimensional defects of the bonding wire. Therefore, a method of 3D reconstruction and pattern recognition of wire defects based on stereo vision, which can achieve non‐destructive detection of bonding wire defects is proposed. The contour features of bonding wires and other electronic components in the depth image is analysed to complete the 3D reconstruction of the bonding wires. Especially to filter the noisy point cloud and obtain an accurate point cloud of the bonding wire surface, a point cloud segmentation method based on spatial surface feature detection (SFD) was proposed. SFD can extract more distinct features from the bonding wire surface during the point cloud segmentation process. Furthermore, in the defect detection process, a directional discretisation descriptor with multiple local normal vectors is designed for defect pattern recognition of bonding wires. The descriptor combines local and global features of wire and can describe the spatial variation trends and structural features of wires. The experimental results show that the method can complete the 3D reconstruction and defect pattern recognition of bonding wires, and the average accuracy of defect recognition is 96.47%, which meets the production requirements of bonding wire defect detection. [ABSTRACT FROM AUTHOR]

The rise of mechanical automation in orchards has sparked research interest in developing robots capable of autonomous tree pruning operations. To achieve accurate pruning outcomes, these robots require robust perception systems that can reconstruct three-dimensional tree characteristics and execute appropriate pruning strategies. Three-dimensional modeling plays a crucial role in enabling accurate pruning outcomes. This paper introduces a specialized tree modeling approach using the space colonization algorithm (SCA) tailored for pruning. The proposed method extends SCA to operate in three-dimensional space, generating comprehensive cherry tree models. The resulting models are exported as normalized point cloud data, serving as the input dataset. Multiple criteria decision analysis is utilized to guide pruning decisions, incorporating various factors such as tree species, tree life cycle stages, and pruning strategies during real-world implementation. The pruning task is transformed into a point cloud neural network segmentation task, identifying the trunks and branches to be pruned. This approach reduces the data acquisition time and labor costs during development. Meanwhile, pruning training in a virtual environment is an application of digital twin technology, which makes it possible to combine the meta-universe with the automated pruning of fruit trees. Experimental results demonstrate superior performance compared to other pruning systems. The overall accuracy is 85%, with mean accuracy and mean Intersection over Union (IoU) values of 0.83 and 0.75. Trunks and branches are successfully segmented with class accuracies of 0.89 and 0.81, respectively, and Intersection over Union (IoU) metrics of 0.79 and 0.72. Compared to using the open-source synthetic tree dataset, this dataset yields 80% of the overall accuracy under the same conditions, which is an improvement of 6%. [ABSTRACT FROM AUTHOR]

At present, three-dimensional laser scanners are used to scan subway shield tunnels and generate point cloud data as the basis for extracting a variety of information about tunnel defects. However, there are obstacles in the tunnel such as pipelines, tracks, and signaling systems that cause noise in the point cloud. Usually, the data of the tunnel point cloud are huge, and the efficiency of artificial denoising is low. Faced with this problem, based on the respective characteristics of the geometric shape and reflection intensity of the tunnel point cloud and their correlation, this paper proposes a tunnel point cloud denoising method. The method includes the following three parts: reflection intensity threshold denoising, joint shape and reflection intensity denoising, and shape denoising. Through the experiment on the single-ring segment point cloud of a shield tunnel, the method proposed in this paper takes 2 min to remove 99.77% of the noise in the point cloud. Compared with manual denoising, the method proposed in this paper takes two fifteenths of the time to achieve the same denoising effect. The method proposed in this paper meets the requirements of a tunnel point cloud data survey. Thus, it provides support for the efficient, accurate, and automatic daily maintenance and surveys of tunnels. [ABSTRACT FROM AUTHOR]

Three-dimensional laser scanning technology is widely employed in various fields due to its advantage in rapid acquisition of geographic scene structures. Achieving high precision and automated semantic segmentation of three-dimensional point cloud data remains a vital challenge in point cloud recognition. This study introduces a Multilevel Intuitive Attention Network (MIA-Net) designed for point cloud segmentation. MIA-Net consists of three key components: local trigonometric function encoding, feature sampling, and intuitive attention interaction. Initially, trigonometric encoding captures fine-grained local semantics within disordered point clouds. Subsequently, a multilayer perceptron addresses point-cloud feature pyramid construction, and feature sampling is performed using the point offset mechanism in the different levels. Finally, the multilevel intuitive attention(MIA) mechanism facilitates feature interactions across different layers, enabling the capture of both local attention features and global structure. The point-offset attention scheme introduced in this study significantly reduces computational complexity compared to traditional attention mechanisms, enhancing computational efficiency while preserving the advantages of attention mechanisms. To evaluate the results of MIA-Net, the ISPRS Vaihingen benchmark, LASDU and GML airborne datasets were tested. Experiments show that our network can achieve state-of-art performance in terms of Overall Accuracy(OA) and average F1-score(e.g., reaching 96.2% and 66.7% for GML datasets, respectively).

Due to the influence of underground coal dust and easy obstruction, the laser point cloud data of hydraulic supports is prone to be incomplete. The existing point cloud segmentation algorithms are difficult to obtain fine-grained point cloud features, unable to obtain complete structural information of the point cloud. The algorithms are prone to introducing semantically dissimilar points in the neighborhood, resulting in low precision of laser point cloud segmentation for hydraulic supports. In order to solve the above problems, a laser point cloud segmentation algorithm for hydraulic supports based on neighborhood feature encoding and optimization is proposed. The method introduces a local neighborhood feature aggregation module consisting of neighborhood feature encoding module, neighborhood feature optimization module, and hybrid pooling module. The neighborhood feature encoding module adds polar coordinate encoding and centroid offset to represent the spatial structure of local point clouds on the basis of traditional 3D coordinate encoding, improving the feature extraction capability for incomplete point clouds. The neighborhood feature optimization module optimizes the feature expression in the neighborhood space by judging the feature distance and discarding redundant features, thereby more effectively learning the local fine-grained features of the point cloud and enhancing the local contextual information of the point cloud. The hybrid pooling module combines attention pooling and max pooling to obtain single point features with rich information by aggregating salient and important features within the neighborhood, reducing information loss. A neighborhood expansion module consisting of two sets of local neighborhood feature aggregation modules and residual connections is constructed to capture long-range dependencies between features, expand the local receptive field of individual points, and aggregate more effective features. The experimental results show that the algorithm has an mean intersection over union of 93.26% and an average accuracy of 96.42% on the laser point cloud segmentation dataset of hydraulic supports. It can effectively distinguish different geometric structures of hydraulic supports and achieve accurate segmentation of various components of hydraulic supports.

Multispectral LiDAR can rapidly acquire 3D and spectral information of objects, providing richer features for point cloud semantic segmentation. Despite the remarkable performance of existing graph neural networks in point cloud segmentation, extracting local features still poses challenges in multispectral LiDAR point cloud scenes due to the uneven distribution of geometric and spectral information. To address the prevailing challenges, cutting-edge research predominantly focuses on extracting multiscale local features, compensating for feature extraction shortcomings. Thus, we propose a multiscale adjacency matrix convolutional neural network (MS-AMCNN) for multispectral LiDAR point cloud segmentation. In the MS-AMCNN, a local adjacency matrix convolution module was first proposed to efficiently leverage the point cloud's topological relationships and perceive local geometric features. Subsequently, a multiscale feature extraction architecture was adopted to fuse local geometric features and utilize a global self-attention module to globally model the semantic features of multiscale. The network effectively captures global and local representative features of the point cloud by harnessing the capabilities of convolutional neural networks in local feature modeling and the self-attention mechanism in global semantic feature learning. Experimental results on the Titan dataset demonstrate that the proposed MS-AMCNN network achieves a promising multispectral LiDAR point cloud segmentation performance with an overall accuracy of 94.39% and a mean intersection over union (MIoU) of 86.57%. Compared with other state-of-the-art methods, such as DGCNN, which achieved an MIoU of 85.43%, and RandLA-net, with an MIoU of 85.20%, the proposed approach achieves optimal performance in segmentation.

Aiming at the problem of poor edge effect segmentation in point cloud segmentation, which fails to fully utilize the correlation between the local geometric and semantic features of point cloud.We propose an edge-enhanced graph convolution point cloud segmentation model EdgeGCN-Net, aiming at further exploring the method of point cloud segmentation based on graph convolution neural network. The EdgeGCN-Net employs an enhanced adaptive graph convolutional operator (AdaptConv++) for feature extraction. It constructs semantic and edge branches for joint optimization, aiming to enhance the extraction and comprehension abilities of semantic information and edge features in point clouds. In addition, we propose a graph inference module called AGIM (Attention-based Graph Inference Module), which utilizes the attention mechanism and learnable adjacency matrices to enrich the global knowledge propagation of the channel graph, thus compensating for the loss of geometric information due to the superposition of network layers. Experimental results show that EdgeGCN-Net outperforms previous state-of-the-art segmentation models on both ShapeNetPart and S3DIS datasets with better segmentation performance and higher accuracy, demonstrating its excellent performance in point cloud segmentation tasks.

Point cloud segmentation is a crucial technique for object recognition and localization, widely employed in various applications such as point cloud registration, 3D reconstruction, object recognition, and robotic grasping. However, in practical scenarios, challenges such as sparse object features, significant pose variations, or instances of object adhesion, stacking, and occlusion can lead to difficulties and poor stability in point cloud segmentation. In response to these challenges, this paper proposes a novel point cloud segmentation algorithm based on enhanced Euclidean clustering. To address the issue of over-segmentation and under-segmentation in cases of object adhesion and stacking in unordered scenes, a method is introduced for discriminating collision points based on normal angle constraints. Subsequently, an adaptive search radius is employed to determine the clustering distance threshold, enhancing the algorithm’s ability to handle different object arrangements. Finally, the collision points are reintegrated into the clustering results to ensure the completeness of the segmented target point cloud. Experimental results using the ROBI public dataset and real-world point cloud segmentation scenarios demonstrate that the proposed algorithm effectively resolves challenges associated with the segmentation of adhering and stacking objects. The improved algorithm exhibits higher accuracy and robustness in multi-object segmentation across diverse scenes.

The point segmentation of power lines and towers aims to use unmanned aerial vehicles (UAVs) for the inspection of power facilities, risk detection and modelling. Because of the unclear spatial relationship between the point clouds, the point segmentation of power lines and towers is challenging. In this paper, the power line and tower point datasets are constructed using Light Detection and Ranging (LiDAR) and a point segmentation method is proposed based on multiscale density features and a point-based deep learning network. First, the data are blocked and the neighbourhood is constructed. Second, the point clouds are downsampled to produce sparse point clouds. The point clouds before and after sampling are rotated, and their density is calculated. Next, a direct mapping method is selected to fuse the density information; a lightweight network is built to learn the features. Finally, the point clouds are segmented by concatenating the local features provided by PointCNN. The algorithm performs effectively on different types of power lines and towers. The mean interaction over union is 82.73%, and the overall accuracy can reach 91.76%. This approach can achieve the end-to-end integration of segmentation and provide theoretical support for the segmentation of large scenic point clouds.

ObjectivesLaser scanning technology used in the intelligent installation of ship shafting has such advantages as non-contact, high-speed scanning and high-precision imaging. The laser point cloud data includes the size, position and direction information of space objects. Point cloud segmentation can greatly reduce the calculation scale of the data and improve the measurement efficiency of the relative pose of the butt flange. MethodsIn this paper, deep learning theory is used to study point cloud segmentation and obtain a point cloud dataset of flange parts. The PointNet model is used for training. Optimization strategies are formulated in three aspects, namely dropout regularization, learning rate attenuation and point cloud data enhancement, then tested on a ship shafting intelligent installation platform. ResultsThe convergence results of the model tend to be stable, with the accuracy of the training set reaching 0.88 and that of the verification set reaching 0.65. The flange point cloud segmentation experiment shows clear contour edges. ConclusionThe results of this study show that the proposed method has good convergence and generalization performance, and can improve the efficiency of ship shafting intelligent installation.

An understanding of the spatial information for safety-related architectural features inside a school building is crucial for effective responses to emergency situations such as active shooter or fire incidences. However, efficiently creating high-quality spatial inventory for a wide variety of safety-related assets inside a large school building is a challenge for building owners. This study addresses this challenge by developing an AI-based approach for rapid generation of spatial inventory of safety-related architectural features within school buildings from point cloud data. A method for creating cross-modality data from laser scans is proposed to not only address the limitations in individual 2D and 3D datasets but also enable the transfer of the segmentation and generalization performance from the state-of-the-art Segment Anything model to point cloud segmentation. Additionally, our proposed method also demonstrates great potential to address the challenge of extracting glass façade frames from point cloud datasets.

The point cloud segmentation method plays an important role in practical applications, such as remote sensing, mobile robots, and 3D modeling. However, there are still some limitations to the current point cloud data segmentation method when applied to large-scale scenes. Therefore, this paper proposes an adaptive clustering segmentation method. In this method, the threshold for clustering points within the point cloud is calculated using the characteristic parameters of adjacent points. After completing the preliminary segmentation of the point cloud, the segmentation results are further refined according to the standard deviation of the cluster points. Then, the cluster points whose number does not meet the conditions are further segmented, and, finally, scene point cloud data segmentation is realized. To test the superiority of this method, this study was based on point cloud data from a park in Guilin, Guangxi, China. The experimental results showed that this method is more practical and efficient than other methods, and it can effectively segment all ground objects and ground point cloud data in a scene. Compared with other segmentation methods that are easily affected by parameters, this method has strong robustness. In order to verify the universality of the method proposed in this paper, we test a public data set provided by ISPRS. The method achieves good segmentation results for multiple sample data, and it can distinguish noise points in a scene. [ABSTRACT FROM AUTHOR]

It is of great significance to study the plant morphological structure for improving crop yield and achieving efficient use of resources. Three dimensional (3D) information can more accurately describe the morphological and structural characteristics of crop plants. Automatic acquisition of 3D information is one of the key steps in plant morphological structure research. Taking wheat as the research object, we propose a point cloud data-driven 3D reconstruction method that achieves 3D structure reconstruction and plant morphology parameterization at the phytomer scale. Specifically, we use the MVS-Pheno platform to reconstruct the point cloud of wheat plants and segment organs through the deep learning algorithm. On this basis, we automatically reconstructed the 3D structure of leaves and tillers and extracted the morphological parameters of wheat. The results show that the semantic segmentation accuracy of organs is 95.2%, and the instance segmentation accuracy AP50 is 0.665. The R 2 values for extracted leaf length, leaf width, leaf attachment height, stem leaf angle, tiller length, and spike length were 0.97, 0.80, 1.00, 0.95, 0.99, and 0.95, respectively. This method can significantly improve the accuracy and efficiency of 3D morphological analysis of wheat plants, providing strong technical support for research in fields such as agricultural production optimization and genetic breeding. [ABSTRACT FROM AUTHOR]

Three-dimensional semantic segmentation is crucial for comprehending transmission line structure and environment. This understanding forms the basis for a variety of applications, such as automatic risk assessment of line tripping caused by wildfires, wind, and thunder. However, the performance of current 3D point cloud segmentation methods tends to degrade on imbalanced data, which negatively impacts the overall segmentation results. In this paper, we proposed an imBalanced-Aware Long-Range 3D Semantic Segmentation framework (iBALR3D) which is specifically designed for large-scale transmission line segmentation. To address the unsatisfactory performance on categories with few points, an Enhanced Imbalanced Contrastive Learning module is first proposed to improve feature discrimination between points across sampling regions by contrasting the representations with the assistance of data augmentation. A structural Adaptive Spatial Encoder is designed to capture the distinguish measures across different components. Additionally, we employ a sampling strategy to enable the model to concentrate more on regions of categories with few points. This strategy further enhances the model's robustness in handling challenges associated with long-range and significant data imbalances. Finally, we introduce a large-scale 3D point cloud dataset (500KV3D) captured from high-voltage long-range transmission lines and evaluate iBALR3D on it. Extensive experiments demonstrate the effectiveness and superiority of our approach. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Zhejiang University (Science Edition) is the property of Journal of Zhejiang University (Science Edition) Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)