Abstract
Mining slopes, electrical power generation dams and several big construction enterprises demands continuous inspections. The size and diversity of these structures demands high precision and portable approach. In such environments, 3D reconstruction methodologies are able to capture and analyze the real world in detail. However, the accuracy and precision can affect the ability to process and interpret the acquired data. For instance, laser scanning is a very accurate method and can deliver a higher quality result. Meanwhile, 3D photogrammetry using a single camera and Structure From Motion (SFM) have their performance correlated with the image quality. In a typical application, 3D data from reconstruction is pre-processed by a specialist. Then, it is stored for comparison and analyzed over time. The posterior analysis has several challenges associated with the reconstruction process characteristics. Several techniques have been developed to allow the comparison of point cloud captured at different epochs. Therefore, this research work presents a new methodology to perform alignment and comparison of point clouds, namely 3D-CP2, an acronym for 3D Correspondence and Point Projection. This method intends to analyze the point cloud motion to be applied in terrestrial 3D SFM reconstructions. Besides, the technique can also be used in many other related applications. The methodology developed in this work is applied in controlled experiments and real use cases to show its potential for point cloud displacements analysis. The results showed that the proposed method is efficient and can produce results more accurately than the referenced literature.
Highlights
Massive constructions are typically associated with high contingency risks demanding the highest security and inspection standards [1]
Due to the lack of regular structures and smooth objects, the deformation analysis of natural scenes is demanding for point cloud since two points cannot be readily identified in different epochs [9]
In the works of Qin et al [20] and Lindenbergh and Pietrzyk [27], the authors presented a theoretical background of 3D point cloud change detection
Summary
Massive constructions are typically associated with high contingency risks demanding the highest security and inspection standards [1]. As stated by the authors of Qin et al [20], the two major approaches in 3D change detection are the methods that rely on statistical analysis to find correlations among data, and the methods that use surface reconstruction to collapse the point cloud to an average position. These solutions have limitations and may not produce accurate results.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
