3D building model generation from MLS point cloud and 3D mesh using multi-source data fusion

Liu, Weiquan; Zang, Yu; Xiong, Zhangyue; Bian, Xuesheng; Wen, Chenglu; Lu, Xiaolei; Wang, Cheng; Marcato, José; Gonçalves, Wesley Nunes; Li, Jonathan

doi:10.1016/j.jag.2022.103171

Cited by 17 publications

(7 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Shallower buried structures or objects were identified and interpreted on the GPR image by analyzing the relative amplitude variation of electromagnetic waves. Considering the data acquisition and formats of TLS and GPR, it is obvious that the TLS-based point clouds are unable to be combined with GPR profile [ 46 , 47 , 48 ].…”

Section: The Principle Of Integrated Tls and Gpr Methodsmentioning

confidence: 99%

Multisensor and Multiscale Data Integration Method of TLS and GPR for Three-Dimensional Detailed Virtual Reconstruction

Zhang,

Jia,

Ren

et al. 2023

Sensors

View full text Add to dashboard Cite

Integrated TLS and GPR data can provide multisensor and multiscale spatial data for the comprehensive identification and analysis of surficial and subsurface information, but a reliable systematic methodology associated with data integration of TLS and GPR is still scarce. The aim of this research is to develop a methodology for the data integration of TLS and GPR for detailed, three-dimensional (3D) virtual reconstruction. GPR data and high-precision geographical coordinates at the centimeter level were simultaneously gathered using the GPR system and the Global Navigation Satellite System (GNSS) signal receiver. A time synchronization algorithm was proposed to combine each trace of the GPR data with its position information. In view of the improved propagation model of electromagnetic waves, the GPR data were transformed into dense point clouds in the geodetic coordinate system. Finally, the TLS-based and GPR-derived point clouds were merged into a single point cloud dataset using coordinate transformation. In addition, TLS and GPR (250 MHz and 500 MHz antenna) surveys were conducted in the Litang fault to assess the feasibility and overall accuracy of the proposed methodology. The 3D realistic surface and subsurface geometry of the fault scarp were displayed using the integration data of TLS and GPR. A total of 40 common points between the TLS-based and GPR-derived point clouds were implemented to assess the data fusion accuracy. The difference values in the x and y directions were relatively stable within 2 cm, while the difference values in the z direction had an abrupt fluctuation and the maximum values could be up to 5 cm. The standard deviations (STD) of the common points between the TLS-based and GPR-derived point clouds were 0.9 cm, 0.8 cm, and 2.9 cm. Based on the difference values and the STD in the x, y, and z directions, the field experimental results demonstrate that the GPR-derived point clouds exhibit good consistency with the TLS-based point clouds. Furthermore, this study offers a good future prospect for the integration method of TLS and GPR for comprehensive interpretation and analysis of the surficial and subsurface information in many fields, such as archaeology, urban infrastructure detection, geological investigation, and other fields.

show abstract

Section: The Principle Of Integrated Tls and Gpr Methodsmentioning

confidence: 99%

Multisensor and Multiscale Data Integration Method of TLS and GPR for Three-Dimensional Detailed Virtual Reconstruction

Zhang,

Jia,

Ren

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…The increasing reliance on lightweight neural network architectures and edge computing serves to address these requirements [11]. In parallel, advancements in 3D modeling and photogrammetry have significantly contributed to enhancing spatial analysis from aerial imagery, thereby improving object detection and mapping accuracy [12]. The role of transfer learning in aerial image analysis has been pivotal in reducing dependency on large, domain-specific annotated datasets.…”

Section: Related Workmentioning

confidence: 99%

Enhancing UAV Aerial Image Analysis: Integrating Advanced SAHI Techniques With Real-Time Detection Models on the VisDrone Dataset

Muzammul,

Algarni,

Ghadi

et al. 2024

IEEE Access

View full text Add to dashboard Cite

This research presents a groundbreaking approach in aerial image analysis by integrating the Real-Time Detection and Recognition (RT-DETR-X) model with the Slicing Aided Hyper Inference (SAHI) methodology, utilizing the VisDrone-DET dataset. Aimed at enhancing the efficiency of drone technology across a spectrum of applications, including water conservancy, geological exploration, and military operations, this study focuses on harnessing the real-time, end-to-end object detection capabilities of RT-DETR-X. Characterized by its high-speed and high-accuracy performance, particularly in UAV aerial photography, RT-DETR-X demonstrates a remarkable 54.8% Average Precision (AP) and 74 frames per second (FPS), surpassing similar models in both speed and accuracy. The research thoroughly examines the VisDrone-DET dataset, which encompasses a diverse range of small targets in UAV aerial photography scenes. Covering 10 distinct categories, the dataset provides a robust platform for rigorous model testing. The study emphasizes the utilization of the original image dataset for comprehensive training and evaluation, alongside the practical implementation of the SAHI method for enhanced detection of small-scale objects. Through an in-depth exploration of the model's performance in various scenarios and a detailed analysis of the environmental setup, this paper underscores the impact of integrating RT-DETR with the SAHI approach. The findings reveal significant progress in drone detection technologies, offering a holistic framework for effective and efficient aerial surveillance. The integration not only boosts the model's detection accuracy but also opens new avenues for advanced image analysis in UAV applications.

show abstract

“…The distributed shallow underground explosive source localization system developed by the Key Laboratory of Shanxi Province of Information Detection and Processing, North University of China, was used to obtain the localization parameters. The monitoring area of 120m*120m*60m (l*w*h) was divided into small cube grids with the same size [21], [48], and the grid width was set as 1 m [19], [20]. The range of x-axis, yaxis, and z-axis were [-60,60], [-60,60], and [-60,0], respectively.…”

Section: Experiments Verification and Data Analysismentioning

confidence: 99%

Securing Fast and High-Precision Localization for Shallow Underground Explosive Source: A Curiosity-Driven Deep Reinforcement Learning Approach

Wu,

Wang,

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Shallow underground explosive source localization technology is a key technology in the field of underground space localization. The existing approaches mainly aim to improve the localization accuracy, but need to deploy enormous sensors in the monitoring area, and rely on a large number of back-end workstations to solve. These methods have the defects of considerable calculation and high time cost, and are hard to satisfy the precise and real-time requirements of onsite testing, ultimately resulting in slow localization speed and accurate localization failure. Fortunately, emerging deep reinforcement learning (DRL) can effectively solve the problem of slow search policy by modeling the source localication as a Markov decision process (MDP). Therefore, a Curiosity-Driven Deep Dueling Double Q-learning Network (C-D3QN) is subsequently proposed to solve the above MDP. The overestimation problem is solved by decoupling selection and evaluation of the bootstrap action, and the action difference is effectively increased by introducing the dueling network that separately represents state values and action advantages. Meanwhile, the exploration is jointly reinforced by an intrinsic reward outputted from the curiosity module and an extrinsic reward supplied by the environment, guaranteeing the convergence to global optimal. Finally, extensive simulation results based on the outfield experiment data show that compared with other algorithms, the proposed scheme can significantly improve exploration ability and learning speed as well as generalization and robustness. Additionally, compared to the baseline algorithm DQN, the C-D3QN algorithm can offer an improved localization accuracy as high as 99.62% and an increased localization speed of 66.23%.

show abstract

3D building model generation from MLS point cloud and 3D mesh using multi-source data fusion

Cited by 17 publications

References 37 publications

Multisensor and Multiscale Data Integration Method of TLS and GPR for Three-Dimensional Detailed Virtual Reconstruction

Multisensor and Multiscale Data Integration Method of TLS and GPR for Three-Dimensional Detailed Virtual Reconstruction

Enhancing UAV Aerial Image Analysis: Integrating Advanced SAHI Techniques With Real-Time Detection Models on the VisDrone Dataset

Securing Fast and High-Precision Localization for Shallow Underground Explosive Source: A Curiosity-Driven Deep Reinforcement Learning Approach

Contact Info

Product

Resources

About