Article
Biochemical Research Methods
Wenqi Zhang, Sheng Wu, Weiliang Wen, Xianju Lu, Chuanyu Wang, Wenbo Gou, Yuankun Li, Xinyu Guo, Chunjiang Zhao
Summary: This study proposed a method for organ segmentation of maize tassels based on point cloud data and developed an automated maize tassel phenotype analysis system called MaizeTasselSeg. Six phenotypic traits related to morphological structure were automatically extracted from the segmentation point cloud, achieving high segmentation accuracy and correlation.
Article
Plant Sciences
Qiujie Li, Yu Yan, Weizheng Li
Summary: In this paper, a method for segmenting individual street trees from a street side-view point cloud is proposed, and its high accuracy and superior performance are demonstrated through experiments.
URBAN FORESTRY & URBAN GREENING
(2023)
Article
Plant Sciences
Honghao Zhou, Yang Zhou, Wei Long, Bin Wang, Zhichun Zhou, Yue Chen
Summary: In this study, an improved approach was proposed to automatically calculate five key parameters in the seeding stage of Pinus massoniana plants. The algorithm showed a high correlation between the predicted value and the manual measurement. The accuracies of the main stem diameter, main stem length, and leaf length met the requirements of real applications.
FRONTIERS IN PLANT SCIENCE
(2023)
Article
Agronomy
Naimin Xu, Guoxiang Sun, Yuhao Bai, Xinzhu Zhou, Jiaqi Cai, Yinfeng Huang
Summary: Automatic plant phenotype measurement technology based on rapid and accurate reconstruction of maize structures at the seedling stage is essential for early variety selection, cultivation, and scientific management of maize. A global 3D reconstruction algorithm was proposed to achieve high-throughput detection of maize phenotypic traits.
Article
Plant Sciences
Binbin Han, Yaqin Li, Zhilong Bie, Chengli Peng, Yuan Huang, Shengyong Xu
Summary: This paper proposes a novel framework for point cloud segmentation and completion, aiming to achieve accurate measurement of leaf area in melon seedlings. The proposed framework enhances measurement accuracy by effectively filtering out outliers in the point cloud data and utilizing a new network for simultaneous segmentation and completion. Experimental results demonstrate that the proposed methods outperform other competitors and provide more accurate measurement results.
Article
Agriculture, Multidisciplinary
Teng Miao, Chao Zhu, Tongyu Xu, Tao Yang, Na Li, Yuncheng Zhou, Hanbing Deng
Summary: The study proposes an automatic segmentation method for maize plants from 3D point clouds, achieving high precision and recall rates. It enables accurate measurement of phenotypic traits and skeleton extraction. This approach is crucial for further maize research and applications, offering benefits like genotype-to-phenotype studies and geometric reconstruction.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2021)
Article
Construction & Building Technology
Eva Agapaki, Ioannis Brilakis
Summary: The CLOI framework generates accurate individual labeled point clusters of the most important shapes in existing industrial facilities with minimal manual effort. It uses deep learning and geometric methods to segment points and instances, achieving 82% class segmentation accuracy and estimated time savings of 30% compared to current practices. CLOI is the first framework of its kind to achieve geometric digital twinning for important objects in industrial factories, laying the foundation for further research in semantically enriched digital twins.
JOURNAL OF CONSTRUCTION ENGINEERING AND MANAGEMENT
(2021)
Article
Forestry
Xiao Zhang, Lintao Huo, Ying Liu, Zilong Zhuang, Yutu Yang, Binli Gou
Summary: This paper proposes an improved structure from motion (SFM) and patch-based multi-view stereo (PMVS) algorithm for three-dimensional reconstruction of green plums. The results show that this algorithm has a shorter running time and higher reconstruction accuracy compared to traditional methods. By using an improved adaptive segmentation algorithm based on the Lab color space, the point cloud of green plum micro-defects can be effectively segmented. Micro-defect information of green plums is extracted through clustering and plane fitting, providing a theoretical model for improving the accuracy of sorting their appearance quality.
Article
Biology
Teng Miao, Weiliang Wen, Yinglun Li, Sheng Wu, Chao Zhu, Xinyu Guo
Summary: The study presents a semi-automatic point cloud segmentation algorithm for maize shoots, achieving segmentation and annotation through multiple steps. The tool has high accuracy in coarse segmentation and detailed fine segmentation, providing a practical data annotation tool for further research.
Article
Chemistry, Multidisciplinary
Mingrui Dai, Guohua Li
Summary: As the usage of three-dimensional (3D) laser scanner becomes prevalent for forest inventory, the analysis and processing of point cloud data captured with a 3D laser scanner have gained significant research attention. Extracting individual trees from point cloud data is crucial for further investigation at the tree-level analysis, such as tree counting and trunk analysis, leading to multiple advancements in this area. However, accurately and automatically obtaining the tree crown silhouette from the point cloud data is challenging due to the frequent overlap between adjacent tree crowns. To address this issue, a soft segmentation method utilizing K-Nearest Neighbor (KNN) and contour shape constraints has been proposed, resulting in improved visual effect and precision of point cloud segmentation. In conclusion, the proposed method demonstrates a successful approach for tree crown segmentation and silhouette reconstruction from terrestrial laser scanning point cloud data of forests.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Software Engineering
Wendong Mao, Mingjie Wang, Hui Huang, Minglun Gong
Summary: Two neural networks are proposed in this study: a matching network trained on binocular stereo datasets to handle textureless regions and a second network that consolidates 3D point clouds through point projection for aligning individual patches. Together, these networks show comparable results to existing state-of-the-art approaches on the DTU dataset.
Article
Environmental Sciences
Bo Xu, Zhen Chen, Qing Zhu, Xuming Ge, Shengzhi Huang, Yeting Zhang, Tianyang Liu, Di Wu
Summary: This work proposes a robust geometrical segmentation algorithm for detecting inherent shapes from dense point clouds. The algorithm divides the points into voxels based on connectivity and normal consistency, classifies the voxels into different shapes, and extracts multiple shapes including spheres, cylinders, and cones. A hybrid voting RANSAC algorithm is then used to separate the point clouds into corresponding segments. The proposed method also considers point-shape distance, normal difference, and voxel size as weight terms for evaluating the proposed shape. Graph-cut-based optimization is adopted to handle competition among different segments. Experimental results show that the proposed method achieves reliable segmentation results and outperforms benchmark methods.
Article
Agronomy
Yu Sun, Xindong Guo, Hua Yang
Summary: This article proposes a window-based Transformer (Win-Former) network for organic segmentation of maize point clouds. By projecting the points onto a sphere and using window partition and local self-attention, the relationship between points is computed. A Cross-Window self-attention module strengthens the connection between windows. Experimental results show that Win-Former outperforms other networks in maize organ segmentation.
Article
Agriculture, Multidisciplinary
Tingting Yang, Junhua Ye, Suyin Zhou, Aijun Xu, Jianxin Yin
Summary: This study proposes an autonomous alignment method for seedling point clouds, which enables low-cost and fast 3D reconstruction of batch seedlings. By using a special turntable and a low-cost camera, accurate and stable 3D seedling models and phenotypic parameters can be obtained efficiently.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2022)
Article
Chemistry, Analytical
Marco A. Barreto, Jorge Perez-Gonzalez, Hugh M. Herr, Joel C. Huegel
Summary: This work aims to design, prototype, and test a functional system for scanning plaster cast molds, which could be used for lower limb reconstruction applications. The image capture system, consisting of 5 cameras and algorithms, shows good segmentation metrics and visual similarity with the actual images.
Article
Materials Science, Multidisciplinary
Baoquan Wan, Ming-Sheng Zheng, Xing Yang, Xiaodi Dong, Yuchao Li, Yiu-Wing Mai, George Chen, Jun-Wei Zha
Summary: Recyclability and self-healing are crucial factors in developing sustainable polymers. This study successfully prepared a dynamic cross-linked polyimide insulation film with full closed-loop recyclability and good self-healing ability. The film maintains its mechanical properties, thermal stability, and insulation property even after being recycled and self-healed, making it a promising insulation material for electrical power and micro-electronics.
ENERGY & ENVIRONMENTAL MATERIALS
(2023)
Article
Chemistry, Applied
Zhixuan Cui, Xinxin Gao, Pingping Jiang, Yan Leng, Zhenhua Li, Yuchao Li, Pingbo Zhang
Summary: By synthesizing aminouracil zinc maleate (AM-Zn), a thermal stabilizer with a multifunctional molecular structure was obtained, which can effectively improve the thermal stability of poly(vinyl chloride) (PVC) materials. The synergistic use of AM-Zn and CaSt(2) showed superior thermal stabilization effect compared to commercially available CaSt(2)/ZnSt(2).
JOURNAL OF VINYL & ADDITIVE TECHNOLOGY
(2023)
Article
Automation & Control Systems
Xiaolin Xie, Xiaobing Han, Zhihong Zhang, Yibo Qin, Yuchao Li, Zixiang Yan
Summary: This article designs an agricultural power chassis suitable for driving in complex terrain and narrow fields in hilly and mountainous areas. The chassis has good ground adaptability and steering maneuverability. Theoretical analysis and performance testing confirm its excellent driving performance and stable operation capability.
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
(2023)
Article
Chemistry, Inorganic & Nuclear
Qian Gu, PingPing Jiang, Kai Zhang, Yan Leng, Pingbo Zhang, Phyu Thin Wai, Agus Haryono, Zhenhua Li, Yuchao Li, Lingen Pan, Jie Pan
Summary: Phenyl was successfully doped into heptaazine ring of g-C3N4 by co-polymerization, leading to improved photoelectric properties and photocarrier separation efficiency. The phenyl-doped porous C3N4 exhibited excellent photocatalytic activity for selective oxidation of benzyl alcohol, achieving a conversion rate of 94.5% under 8 hours of solar radiation, which was 2.1 times higher than pure porous C3N4.
JOURNAL OF SOLID STATE CHEMISTRY
(2023)
Article
Polymer Science
Yu-Chao Li, Zong-Pei Wu, Ze-Hao Zong, Xue-Zheng Cao
Summary: This study found that segments of a stiff nanoring (SNR) exhibit more facilitated subdiffusion than those belonging to a flexible counterpart, while the whole SNR is more suppressed by its surroundings. Adding SNRs contributes to achieving sol and gel-like characteristics at high and low shearing frequencies, respectively. This study suggests the promising prospect of exploiting SNRs to concurrently strengthen and toughen target polymer nanocomposites.
Article
Green & Sustainable Science & Technology
Yuchao Li, Lijie Zhang, Jiamin Liu, Xinpei Qiao
Summary: This study examines the impact and mechanism of the dual-credit policy on the performance of listed new energy vehicle companies in China. The results show that the policy significantly improves the performance of these companies, with diminishing marginal utility. Domestic listed companies benefit more from the policy compared to joint venture companies. The policy enhances the competitiveness of these companies mainly through market expectations and competition mechanism. The research contributes to evaluating the economic effect of the dual-credit policy and provides implications for the healthy development of the new energy vehicle industry.
Article
Materials Science, Composites
Zhen Wang, Wenqing Xue, Yongzhi Yang, Yuchao Li, Shuangshuang Wang, Yanhu Zhan, Wei Li, Jigong Hao, Jun-Wei Zha, Chen Liu, Yulin Cao, Zhouguang Lu
Summary: In this study, PMMA brush-modified graphene (rGO-g-PMMA) was successfully incorporated into PVDF matrix, resulting in increased dielectric constant and breakdown strength. The addition of rGO-g-PMMA also suppressed dielectric loss and improved thermal stability and mechanical strength of the obtained films. This research provides a new strategy for obtaining flexible, high strength, and large energy storage dielectric films.
COMPOSITES COMMUNICATIONS
(2023)
Article
Engineering, Environmental
Xiaoyu Li, Yuchao Li
Summary: Land subsidence caused by natural or human factors is a serious geological hazard that affects ground buildings and environments in large cities and economic development zones worldwide. The main causes of land subsidence are complex geological conditions and excessive mining of underground resources. Understanding the formation mechanism and evolution rule of land subsidence is of great significance for disaster prevention and control.
BULLETIN OF ENGINEERING GEOLOGY AND THE ENVIRONMENT
(2023)
Article
Engineering, Environmental
Ming Yin, Guang-Jian Bai, Peng Li, Ji-Gong Hao, Wei Li, Wei-Fang Han, Yu -Chao Li, Chun-Ming Wang, Guo-Rong Li, Peng Fu
Summary: In this study, (Ba(1-x)Bix)(Ti(1-x)Zn0.5xSn0.5x)O3 ceramics were synthesized and the effects of chemical modification on their structure and properties were investigated. The introduction of BZS elements induced the change from normal to relaxor ferroelectric behavior, which enhanced the energy storage performance. BBTZS-0.12 ceramics showed exceptional comprehensive energy storage properties due to the presence of PNRs, making them promising for advanced energy storage applications.
CHEMICAL ENGINEERING JOURNAL
(2023)
Article
Mathematics
Yuchao Li, Mingsong Yang, Qin Zhao, Zongjian Li, Zhaoxi Ma, Yunhe Liu, Xinhong Hei
Summary: Compliance checking is crucial in engineering construction, and automated compliance checking (ACC) has gained increasing attention with the advancement of information technology. However, accurately representing code information and considering relationship constraints, especially spatial geometric relationships, remain challenging. Existing code representation methods often lack the ability to effectively identify non-compliant situations due to semantic ambiguity in the checking results. This paper proposes a code representation method that divides building code information into five parts, facilitates constraint representation of engineering and spatial relationships, and provides distinct checking conditions and requirements with semantic checking results. The proposed method is validated using the China Metro Design Code and an actual Metro model.
Article
Materials Science, Composites
Xueqing Bi, Wenqing Xue, Yongzhi Yang, Zhen Wang, Zi Wang, Yuchao Li, Yanhu Zhan, Wei Li, Weifang Han, Bo Ge, Junwen Ren, Jun-Wei Zha
Summary: By introducing a mixed graphene oxide/epoxy solution into a three-dimensional barium titanate network, hierarchical ceramic network/graphene oxide/epoxy composites with improved dielectric properties were obtained. The addition of graphene oxide prevented electrical breakdown and the ceramic network provided an effective polarization pathway, resulting in significantly enhanced energy storage performance.
COMPOSITES COMMUNICATIONS
(2023)
Article
Agronomy
Jiangtao Ji, Nana Li, Hongwei Cui, Yuchao Li, Xinbo Zhao, Haolei Zhang, Hao Ma
Summary: This study established a prediction model for SPAD values of summer maize leaves at different spatial scales based on UAV multispectral images. The sparrow search optimized kernel limit learning machine (SSA-KELM) method was used to establish the prediction models for canopy leaf (CL) SPAD and ear leaf (EL) SPAD. The results showed that the SSA-KELM method had more precise prediction results compared to the partial least squares method (PLSR) and can provide technical support for remote sensing monitoring of the chlorophyll content of summer maize.
Article
Engineering, Geological
Yuchao Li, Jianping Chen, Fujun Zhou, Xin Zhou, Zhihai Li, Qing Wang
Summary: Due to the limited availability of discontinuity data in engineering geology, a stochastic kinematic method based on Monte Carlo simulation, Latin hypercube, and Bayesian estimation was proposed to estimate the slope failure angle in a discontinuity-controlled rock slope. After statistical optimization, the slope failure angles were determined to be 65.69 degrees (plane failure) and 58.65 degrees (wedge failure). This method provides a more objective approach for slope stability analysis and can be used as a basis for engineering construction and disaster prevention.
GEORISK-ASSESSMENT AND MANAGEMENT OF RISK FOR ENGINEERED SYSTEMS AND GEOHAZARDS
(2023)
Article
Chemistry, Applied
Weifang Han, Xinwei Zhang, Mengyuan Chen, Xiaohan Chu, Wei Li, Peng Fu, Zhengfeng Jia, Yuchao Li
Summary: We synthesized multilayered boron nitride nanosheets/rhodamine B (MBNNSs/RhB) composite fluorophores with intense red-light emission through adsorption process and annealing treatment. The luminescence of MBNNSs/RhB composite fluorophores can be adjusted by rational optimization of the RhB concentration and the heat-treatment temperature. Moreover, the composite fluorophore exhibits excellent thermal stability and luminous stability.
Article
Chemistry, Multidisciplinary
Yaya Tian, Ming-Sheng Zheng, Yuchao Li, Chuqi Xu, Yiyi Zhang, Wei Liu, Zhi-Min Dang, Jun-Wei Zha
Summary: A novel polyimide material with excellent dielectric properties and high thermostability has been successfully synthesized in this study. One of the materials showed outstanding breakdown strength and high energy density at 250 degrees Celsius.
MATERIALS HORIZONS
(2023)