Article
Environmental Sciences
Gabbo P. H. Ching, Ray K. W. Chang, Tess X. H. Luo, Wallace W. L. Lai
Summary: A guidance system was developed in this study to help GPR operators conduct three-dimensional imaging surveys more efficiently, reducing survey time and improving image resolution.
Article
Remote Sensing
Tess Luo, Song Zhu, Yiliminuer Yikeremu, Jiasong Zhu, John van Genderen
Summary: This study proposes a method for preliminary diagnosing large-scale culverts based on GPR wave attributes, which includes evaluating soil compactness, investigating soil moisture, and overlaying the results to pinpoint potential degradations. The method was validated through case studies on two long-distance culverts. The results indicate that this method can provide quick reference to improve GPR survey efficiency and reduce workload, facilitating large-scale GPR culvert surveys and safeguarding the water system.
GEO-SPATIAL INFORMATION SCIENCE
(2023)
Article
Chemistry, Multidisciplinary
Carmen Marin-Buzon, Antonio Miguel Perez-Romero, Manuel J. Leon-Bonillo, Ruben Martinez-Alvarez, Juan Carlos Mejias-Garcia, Francisco Manzano-Agugliaro
Summary: The study aimed to compare two geomatics techniques in archaeological excavations, focusing on accuracy and errors, especially in altimetry. It was found that Structure from Motion (SfM) photogrammetry was the most accurate and least limiting for use in semi-buried archaeological excavations, opening new perspectives for its application in such contexts.
APPLIED SCIENCES-BASEL
(2021)
Article
Computer Science, Information Systems
Maxwell M. Omwenga, Dalei Wu, Yu Liang, Li Yang, Dryver Huston, Tian Xia
Summary: This article introduces an autonomous cognitive GPR system enabled by deep reinforcement learning, which outperforms other systems in terms of detection accuracy and operating time in underground exploration.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Geosciences, Multidisciplinary
Muhammad Younis Khan, Ekrem Saralioglu, Syed Ali Turab, Sher Muhammad
Summary: The Mirpur Mw 5.8 earthquake in 2019 caused extensive liquefaction-induced surface deformation in surrounding villages. The PSInSAR technique was used to measure subsidence and uplift rates and mapped the spatial distribution of liquefaction features. GPR measurements were conducted to map near-surface cracks and other liquefaction features, assisting in the reconstruction of structural and hydrogeological features. Vulnerable zones were identified using remote sensing measurements and field observations. This study provides an effective approach for assessing liquefaction-induced deformation and aiding in hazard mitigation.
GEOMATICS NATURAL HAZARDS & RISK
(2023)
Article
Geochemistry & Geophysics
Qiqi Dai, Yee Hui Lee, Hai-Han Sun, Jiwei Qian, Genevieve Ow, Mohamed Lokman Mohd Yusof, Abdulkadir C. Yucel
Summary: This paper proposes a deep learning-based 2-D ground-penetrating radar (GPR) forward solver for predicting the B-scans of subsurface objects buried in heterogeneous soil. The solver utilizes a bimodal encoder-decoder neural network with adaptive feature fusion to extract informative features from subsurface permittivity and conductivity maps. The experimental results demonstrate that the proposed solver achieves high accuracy with a mean relative error of 1.28% and significantly reduces the computational time compared to traditional physics-based solvers.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Robotics
Chieh Chou, Haifeng Li, Dezhen Song
Summary: This article discusses system and algorithmic developments for a sensing suite designed for surface and subsurface infrastructure inspection. It addresses a novel GPR-camera calibration problem and a synchronization-challenged sensor fusion problem, resulting in successful 3-D reconstruction and reduction of end-to-end distance error.
IEEE TRANSACTIONS ON ROBOTICS
(2021)
Article
Geochemistry & Geophysics
Maryam Hajebi, Ahmad Hoorfar
Summary: An efficient multiresolution inverse scattering approach is proposed for profiling high-contrast buried targets in large investigation domains. The method is based on iterative multiscale approach (IMSA) combined with global evolutionary programming (EP) optimization algorithm to guarantee the success of inversion process. The results show superior performance of the proposed technique in handling nonlinearities and outperforming standard IMSA and other well-known global optimization techniques.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2021)
Article
Construction & Building Technology
Jiasong Zhu, Dingyi Zhao, Xianghuan Luo
Summary: Ground-penetrating radar (GPR) is an efficient method for diagnosing urban road defects, but its interpretation is complex. This study proposes an optimized YOLO-based framework for timely identification of road defects using GPR. Transfer learning and data augmentation are used to optimize the framework, and YOLOv5_s is found to perform the best. The framework is validated using real GPR data and provides comparable accuracy within seconds, benchmarking YOLOv5_s for timely road inspection.
ROAD MATERIALS AND PAVEMENT DESIGN
(2023)
Article
Environmental Sciences
Donghao Zhang, Zhengzheng Wang, Hui Qin, Tiesuo Geng, Shengshan Pan
Summary: In this work, a generative adversarial network (GAN)-based inversion framework was developed to automatically translate crosshole GPR images to their corresponding 2D defect reconstruction images. The proposed method extracts global features using fully connected layers and produces high-resolution defect reconstruction results using cascaded U-Net structures. The feasibility of this framework was demonstrated on synthetic and real-world crosshole GPR datasets, showing high recognition accuracy and structural similarity index measure (SSIM).
Article
Environmental Sciences
Maolin Chen, Xinyi Zhang, Cuicui Ji, Jianping Pan, Fengyun Mu
Summary: In this paper, a density-adaptive feature extraction method is proposed for point cloud classification. It addresses the issue of unknown angular resolution by introducing a method called neighborhood analysis of randomly picked points (NARP) for angular resolution estimation. The proposed method also includes the use of relative projection density, a grid feature, to mitigate the impact of density variation. Experimental results demonstrate the effectiveness and stability of the proposed method, especially for small-size objects. The relative projection density outperforms traditional projection density in classification performance.
Article
Environmental Sciences
Rami Al-Ruzouq, Saleh Abu Dabous, Abdelrahman Abueladas, Fatma Hosny, Fakhariya Ibrahim
Summary: This study proposes an integrated methodology combining various technologies to collect accurate data for preserving archaeological sites and provides a comprehensive model for maintaining and protecting these sites.
Article
Geochemistry & Geophysics
Nansha Li, Renbiao Wu, Haifeng Li, Huaichao Wang, Zhongcheng Gui, Dezhen Song
Summary: In this paper, a new multimodal fusion network called M(2)FNet is proposed to address the issue of trailing interference in underground radar data, which affects the accuracy of subsurface defect detection. The M(2)FNet utilizes a dual network structure to extract global and local features from the radar data, enhancing the representation learning capability. Additionally, a large-scale hybrid dataset called ASD-GPR is created for experimental evaluation, and transfer learning is applied to adapt the model to real-world scenarios for detecting rare defects.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Geochemistry & Geophysics
Zhilin Tian, Shihua Li
Summary: This study proposes a new graph-based leaf-wood separation method for individual trees using the xyz-information of the point cloud. The method shows high accuracy and robustness for trees of different species and sizes, and demonstrates good detection capability for small and leaf-surrounded branches.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Environmental Sciences
Klaudia Onyszko, Anna Fryskowska-Skibniewska
Summary: Reliable detection of underground infrastructure is crucial for infrastructure modernization, BIM technology, and 3D cadasters. The paper proposes a method of data filtration using wavelet analyses and Gabor filtration, as well as an object classification methodology based on the analytic hierarchy process method to improve the efficiency and accuracy of object detection and classification.
Article
Remote Sensing
Arunima Singh, S. K. P. Kushwaha, Subrata Nandy, Hitendra Padalia
Summary: The research utilized a terrestrial laser scanner (TLS) to retrieve tree parameters, calculate stem volume, and correlate it with the Forest Survey of India (FSI) equation, finding a high correlation between the volumes calculated by two algorithms, making them a viable alternative method for stem volume calculation.
Article
Environmental Sciences
Arunima Singh, Sunni Kanta Prasad Kushwaha, Subrata Nandy, Hitendra Padalia, Surajit Ghosh, Ankur Srivastava, Nikul Kumari
Summary: This study aimed to assess aboveground biomass (AGB) in the Barkot Forest Range, Uttarakhand, India by integrating Terrestrial Laser Scanner (TLS) and ALOS PALSAR L-band Synthetic Aperture Radar (SAR) data. Various parameters were derived from the ALOS SAR data, and TLS was used to obtain diameter at breast height (dbh) and tree height. The integration of SAR and TLS data using Random Forest (RF) and Artificial Neural Network (ANN) showed that RF performed better in estimating the biomass with an R-2 value of 0.94 and an RMSE of 59.72 ton ha(-1).
Proceedings Paper
Geography, Physical
A. Singh, S. K. P. Kushwaha, S. Nandy, H. Padalia
Summary: Forest biomass quantification is crucial for global carbon cycle maintenance. This research aimed to formulate a volumetric equation based on the tree structure, not species, for accurate estimation of tree parameters. By utilizing the Random Sample Consensus algorithm and line primitive vector, the radius of the stem and tree height were successfully estimated. Multiple linear regression analysis was conducted to establish the correlation between TLS derived tree parameters and field estimated tree parameters. The results showed that the volumetric equation achieved high accuracy in volume estimation and demonstrated good correlation in biomass estimation.
17TH 3D GEOINFO CONFERENCE
(2022)
Proceedings Paper
Geography, Physical
H. Harshit, S. K. P. Kushwaha, K. Jain
Summary: This paper discusses the use of point clouds as a common source of 3D information, and how to extract geometric features and evaluate the quality of point clouds. By analyzing multiple scales of point clouds and calculating local geometric properties, the information level and scene structure of the point cloud can be understood.
17TH 3D GEOINFO CONFERENCE
(2022)
Proceedings Paper
Geography, Physical
S. K. P. Kushwaha, M. Mokros, K. Jain
Summary: Unmanned aerial vehicle (UAV) photogrammetry is a cost-effective and efficient method for surveying and mapping. However, creating accurate 3D models in dense urban areas is challenging. This research investigates an experimental approach to enhance the quality of the digital surface model (DSM), and the results show significant improvements in specific areas and conditions.
17TH 3D GEOINFO CONFERENCE
(2022)
Proceedings Paper
Geography, Physical
S. K. P. Kushwaha, Arunima Singh, Kamal Jain, Martin Mokros
Summary: In remote sensing of forest landscape, Terrestrial Laser Scanner (TLS) can provide more accurate information about ground and under canopy structure compared to aerial remote sensing techniques. This research determines the optimal number of TLS scans and positions needed to generate a Digital Terrain Model (DTM) at the forest plot level.
XXIV ISPRS CONGRESS: IMAGING TODAY, FORESEEING TOMORROW, COMMISSION III
(2022)
Article
Environmental Sciences
Arunima Singh, Sunni Kanta Prasad Kushwaha
Summary: The integration of UAV optical photogrammetry and SAR data can offer appreciated results in monitoring and managing inaccessible forest areas. Calculated vegetation indices and texture images can quantify the degradation of the forest, providing valuable insights for monitoring purposes.
JOURNAL OF THE INDIAN SOCIETY OF REMOTE SENSING
(2021)
Proceedings Paper
Engineering, Civil
Yogender, S. Raghavendra, S. K. P. Kushwaha
APPLICATIONS OF GEOMATICS IN CIVIL ENGINEERING
(2020)
Proceedings Paper
Engineering, Civil
S. K. P. Kushwaha, Karun Reuel Dayal, Sachchidanand, S. Raghavendra, Hina Pande, Poonam S. Tiwari, S. Agrawal, S. K. Srivastava
APPLICATIONS OF GEOMATICS IN CIVIL ENGINEERING
(2020)
Proceedings Paper
Environmental Sciences
S. K. P. Kushwaha, Yogender, S. Raghavendra
SEVENTH INTERNATIONAL CONFERENCE ON REMOTE SENSING AND GEOINFORMATION OF THE ENVIRONMENT (RSCY2019)
(2019)
Proceedings Paper
Geography, Physical
S. K. P. Kushwaha, Hina Pande, S. Raghavendra
ISPRS TC V MID-TERM SYMPOSIUM GEOSPATIAL TECHNOLOGY - PIXEL TO PEOPLE
(2018)