Abstract
Registration of aerial images to enrich 3-D light detection and ranging (LiDAR) points with radiometric information can enhance the capability of object detection, scene classification, and semantic segmentation. However, airborne LiDAR data may not always come with on-board optical images collected during the same flight mission. Indirect georeferencing can be adopted, if ancillary imagery data are found available. Nevertheless, automatic recognition of control primitives in LiDAR and imagery datasets becomes challenging, especially when they are collected on different dates. This article proposes a generic registration mechanism based on using the phase congruency (PC) model and scene abstraction to overcome the stated challenges. The approach relies on the use of a PC measure to compute the image moments that determine the study scene's edges. Potential candidate points can be identified based on thresholding the image moments' values. A shape context descriptor is adopted to automatically pair symmetric candidate points to produce a final set of control points. Coordinate transformation parameters between the two datasets were estimated using a least squares adjustment for four registration models: first- (affine), second-, third-order polynomials, and direct linear transform models. Datasets covering different urban landscapes were used to examine the proposed workflow. The root-mean-square error of the registration is between one and two pixels. The proposed workflow is found to be computationally efficient especially with small-sized datasets, and generic enough to be applied in registering various imagery data and LiDAR point clouds.
Highlights
R ECENT studies indicate the fact that the world is undergoing the largest wave of urban growth in history [1].Manuscript received March 26, 2020; revised June 4, 2020, August 26, 2020, and September 23, 2020; accepted October 8, 2020
A semiautomatic 2D-3D point-based registration was applied using the phase congruency (PC) model as candidate control points (CCPs) identifier, in addition to the shape context descriptor (SCD) model to pair up CCPs as final control points (FCPs)
light detection and ranging (LiDAR) data were converted to 2-D images, the PC model was run on the resampled raster of aerial and LiDAR datasets
Summary
R ECENT studies indicate the fact that the world is undergoing the largest wave of urban growth in history [1].Manuscript received March 26, 2020; revised June 4, 2020, August 26, 2020, and September 23, 2020; accepted October 8, 2020. North America is one of the most urbanized regions with 82% of its population living in urban areas as reported in 2018 [2] This tangible urban sprawl consumes available resources and leads to a shortage of public services. It requires definitive administrative plans to precisely assess the quality of current urban areas and to develop new strategies to cope with the estimated urbanization in the future. This urban expansion highlights the necessity of resource-efficient and technology-driven cities known as smart cities [3]. Indirect georeferencing can be adopted if the optical images and the LiDAR point clouds are, respectively, collected on different dates or during different missions
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 callMore From: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Disclaimer: 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.
