Article
Computer Science, Information Systems
Jianwei Yu, Zhipeng Chen, Zhiming Xiong
Summary: In this paper, a fully automatic path voting method is proposed for crack detection in images. The method segments the image using path voting algorithm and generates a crack probability map, and then extracts cracks using spanning tree and tree pruning algorithms. Experimental results demonstrate the effectiveness of the proposed method.
Article
Mechanics
Kei Saito, Tei Hirashima, Ninshu Ma, Hidekazu Murakawa
Summary: A practical and reliable characteristic-tensor method (CTM) has been proposed for evaluating stress-intensity factors (SIFs) of various types of three-dimensional cracks. Using finite-element analysis, even with a relatively coarse mesh, accurate estimates of SIFs for mixed-mode crack problems can be obtained by the CTM. The results demonstrate that the CTM is a valuable approach for estimating SIFs of 3D cracks important for industrial applications.
ENGINEERING FRACTURE MECHANICS
(2021)
Article
Construction & Building Technology
Anh Thu Thi Phan, Thi Ngoc Huynh
Summary: This study achieves automatic detection of cracks in the road surface by using a laser scanner to observe and generate point clouds, extracting the road surface based on geometry and normal vectors, and extracting cracks and distress areas based on intensity gradient and inclination angle. Clear cracks and distress areas are obtained.
ADVANCES IN CIVIL ENGINEERING
(2022)
Article
Computer Science, Artificial Intelligence
Zixian Wei, Tao Sun, Yuhao Wu, Liqing Zhou, Xiaoli Ruan
Summary: An algorithm for pavement crack detection is proposed in this paper, which combines non-local block matching and local statistical mean to generate a crack probability map, utilizes an iterative seed points sampling method to find reliable crack seeds, and employs a minimum spanning tree for crack curve extraction to improve detection performance.
IET IMAGE PROCESSING
(2022)
Article
Engineering, Mechanical
Minmin Xiao, Chunyan Li, Xingyi Zhu, Liming Yang, Jinyong Dong
Summary: This paper investigates the influence of temperature and depth on complex crack instability and diffusion in asphalt pavements based on the fracture mechanics K-criterion. It analyzes the crack composite stress intensity factor and development pattern, and uses finite element modeling to analyze the change in stress intensity factor values at different temperatures and cracks depths. The study results show that the type I crack tip stress intensity factor (KI) is the most affected by temperature and crack depth, and is the main controlling factor of crack development.
THEORETICAL AND APPLIED FRACTURE MECHANICS
(2022)
Article
Computer Science, Artificial Intelligence
Qi Chen, Yuchun Huang, Hui Sun, Weihong Huang
Summary: This paper presents a method for detecting pavement cracks by modeling their directional features, which successfully addresses the challenge of accurate crack identification in existing methods. Experimental results demonstrate that the proposed approach performs well in detecting cracks in images of various crack types and under different conditions.
ADVANCED ENGINEERING INFORMATICS
(2021)
Article
Engineering, Civil
Huifang Feng, Wen Li, Zhipeng Luo, Yiping Chen, Sarah Narges Fatholahi, Ming Cheng, Cheng Wang, Jose Marcato Junior, Jonathan Li
Summary: This paper introduces a semi-supervised point-level approach to overcome the dependence on annotated data, constructing a reasonable graph structure and improving detection performance with commercial MLS point clouds. Experimental results demonstrate the method outperforms existing techniques in terms of performance and efficiency.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Automation & Control Systems
Kun Liu, Haowei Yan, Kai Meng, Haiyong Chen, Hasan Sajid
Summary: The proposed method presents a new iterative tensor voting algorithm to refine curvilinear structures through iterations, effectively addressing the challenges in defect detection on the surface of multicrystal solar cells caused by inhomogeneous texture and low contrast.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2021)
Article
Geochemistry & Geophysics
Shuang Liu, Haili Sun, Zhenxin Zhang, Yuqi Li, Ruofei Zhong, Jincheng Li, Siyun Chen
Summary: In this paper, a novel and efficient deep learning model is proposed for extracting multiscale and discriminative features of water leakages. By integrating a new residual network module (Res2Net) with a cascade structure, the proposed method expands the size of receptive field and improves the feature extraction performance. Experimental results demonstrate the advantages of the proposed method in extracting water leakage features.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Engineering, Manufacturing
Rui Wang, Nan Chen
Summary: This study proposes a novel method for the detection and recognition of mixed-type defect patterns in wafer bin maps. By separating mixed-type patterns into clusters using tensor voting and extracting region and curve patterns based on the structural saliency information of the voting process, our method is robust and flexible in dealing with complex defect patterns.
IEEE TRANSACTIONS ON SEMICONDUCTOR MANUFACTURING
(2022)
Article
Geochemistry & Geophysics
Zhengchuan Sha, Yiping Chen, Yangbin Lin, Cheng Wang, Jose Marcato, Jonathan Li
Summary: This paper proposes a novel supervoxel segmentation algorithm framework for enhancing road boundaries from 3-D point clouds. The method achieves good performance in road scenes by segmenting the point clouds using seed points and adjusting the centroids of supervoxels.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Geochemistry & Geophysics
Kunping Yan, Qingyong Hu, Hanyun Wang, Xiaohong Huang, Li Li, Song Ji
Summary: The paper introduces MappingConvSeg, a continuous convolution network for semantic segmentation of large-scale point clouds, which utilizes continuous convolution operation to learn spatial correlation of unstructured 3D point clouds and constructs a hierarchical network. Experimental results demonstrate the superiority of the proposed method on two public benchmarks.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Geochemistry & Geophysics
Zilong Zhong, Ying Li, Lingfei Ma, Jonathan Li, Wei-Shi Zheng
Summary: This study introduces a novel spectral-spatial transformer network (SSTN) to overcome the limitations of convolution kernels and proposes a factorized architecture search (FAS) framework that focuses on finding optimal architecture settings without the need for bilevel optimization. Experimental results demonstrate the excellent performance of SSTNs on multiple HSI benchmark datasets.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Shaobo Xia, Sheng Xu, Ruisheng Wang, Jonathan Li, Guanghui Wang
Summary: This study presents a method to extract individual buildings from ALS point clouds using widely accessible polygonal footprints. The method can achieve high instance-level building mapping accuracy around 90% and future work will focus on improving classification errors in preprocessing, shape inconsistencies between point clouds and polygons, as well as building footprint delineation and updating in postprocessing.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Ming Cheng, Guoyan Li, Yiping Chen, Jun Chen, Cheng Wang, Jonathan Li
Summary: This article introduces a novel dense point cloud completion architecture based on generative adversarial networks, utilizing two generator and discriminator modules to achieve complete reconstruction of incomplete point clouds. Experimental results demonstrate that DPCG-Net outperforms other models in cases with a large proportion of missing point clouds, showing effectiveness in both synthetic and real-world scenarios.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Wen Li, Zhipeng Luo, Zhenlong Xiao, Yiping Chen, Cheng Wang, Jonathan Li
Summary: In this article, a graph convolutional network (GCN)-based method is proposed to automatically and accurately extract power lines and pylons from airborne LiDAR point clouds. By developing data augmentation and near-ground filtering methods, designing neighborhood dimension information (NDI) and neighborhood geometry information aggregation (NGIA) modules, as well as an attention fusion module, a line structure constraint algorithm is introduced to identify individual power lines, achieving high identification rates and superior performance compared to existing algorithms in mountainous areas.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Zhipeng Luo, Ziyue Zhang, Wen Li, Yiping Chen, Cheng Wang, Abdul Awal Md Nurunnabi, Jonathan Li
Summary: This study proposes a deep learning framework for individual tree detection in complex forests using UAV laser scanning point clouds. The framework consists of two stages: ground filtering and tree detection. The ground filtering stage utilizes a modified graph convolution network with a local topological information layer, while the tree detection stage employs a top-down slice module and a special multichannel representation. Experimental results show that the framework achieves excellent performance.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Engineering, Civil
Kun Zhao, Lingfei Ma, Yu Meng, Li Liu, Junbo Wang, Jose Marcato, Wesley Nunes Goncalves, Jonathan Li
Summary: This paper presents a multi-level fusion network for 3D vehicle detection from point clouds and images. Extensive experiments show that the proposed network has better detection performance on occluded and distant vehicles, and reduces the false detection of similarly shaped objects.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Engineering, Civil
Chengming Ye, He Zhao, Lingfei Ma, Han Jiang, Hongfu Li, Ruisheng Wang, Michael A. Chapman, Jose Marcato Junior, Jonathan Li
Summary: This article presents a method to extract lane features from mobile laser scanning data, which shows strong feasibility and robustness, and achieves higher accuracy and robustness compared to most state-of-the-art methods.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Engineering, Civil
Jianlan Gao, Yiping Chen, Jose Marcato, Cheng Wang, Jonathan Li
Summary: This paper proposes a novel method for rapidly extracting urban road guardrails from MLS point clouds, combining multi-level filtering and a modified DBSCAN clustering. The method is applicable to most types of guardrails and rough slope roads. Experimental results demonstrate that the proposed method outperforms the state-of-the-art method in extracting 3D guardrails from point clouds.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Remote Sensing
Linwei Chen, Bowen Fang, Lei Zhao, Yu Zang, Weiquan Liu, Yiping Chen, Cheng Wang, Jonathan Li
Summary: In this paper, a physics informed neural network (PINN) framework called DeepUrbanDownscale (DUD) is proposed for accurate high-resolution urban surface temperature estimation. The network uses high-precision 3D point clouds and atmospheric physics guidance to achieve accurate temperature estimation at an ultra-high spatial resolution. Experimental results show that the proposed DUD network outperforms traditional methods in predicting urban surface temperatures.
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION
(2022)
Article
Engineering, Civil
Hao Liu, Yanni Ma, Hanyun Wang, Chaobo Zhang, Yulan Guo
Summary: This paper introduces a novel object detection method based on anchor points, where foreground points are used as anchor points and encoded as object queries. Each object query has an explicit physical meaning and only focuses on nearby objects. The proposed AnchorPoint detector achieves promising accuracy and efficiency on several large-scale 3D object detection datasets.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Geochemistry & Geophysics
Junhui Wan, Zhiheng Fu, Minglin Chen, Peng Zhang, Hanyun Wang, Yulan Guo
Summary: Semantic instance reconstruction is a hot topic in various fields, and the existing methods struggle with occlusions and noise. To tackle these issues, this paper proposes a novel semantic instance reconstruction network PMNet, which incorporates point cloud completion. The proposed network consists of an object detection module, a point cloud completion module, and a mesh generation module. Extensive experiments validate that PMNet achieves the best reconstruction performance on real-world point clouds.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2023)
Article
Geochemistry & Geophysics
Huan Luo, Lingkai Li, Lina Fang, Hanyun Wang, Cheng Wang, Wenzhong Guo, Jonathan Li
Summary: This letter proposes a new neural network for domain adaptation in 3-D object classification. It uses an Asymmetrical Siamese module to reduce data discrepancy of intraclass objects in different domains and a Conditional Adversarial module to preserve discriminative information for interclass objects.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Engineering, Electrical & Electronic
Yinxuan Li, Li Li, Jian Yao, Menghan Xia, Hanyun Wang
Summary: We propose a contrast-aware color consistency correction approach that simultaneously eliminates drastic color differences and enhances image contrast. By integrating the problems of color consistency correction and image contrast enhancement into the same optimization framework and utilizing the original color information, our approach can generate corrected images with consistent tones and visually appealing contrast even when the input images have low contrast.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2022)