Abstract
Abstract. Panoramic images captured using laser scanning technologies, which principally produce point clouds, are readily applicable in colorization of point cloud, detailed visual inspection, road defect detection, spatial entities extraction, diverse map creation, etc. This paper underlines the importance of images in modern surveying technologies and different GIS projects at the same time having regard to their anonymization in accordance with law. The General Data Protection Regulation (GDPR) is a legal framework that sets guidelines for the collection and processing of personal information from individuals who live in the European Union (EU). Namely, it is a legislative requirement that faces of persons and license plates of vehicles in the collected data are blurred. The objective of this paper is to present a novel architecture of the solution for a particular object blurring. The architecture is designed as a pipeline of object detection algorithms that progressively narrows the search space until it detects the objects to be blurred. The methodology was tested on four data sets counting 5000, 10 000, 15 000 and 20 000 panoramic images. The percentage of accuracy, i.e., successfully detected and blurred objects of interest, was higher than 97 % for each data set. Additionally, our aim was to achieve efficiency and broad use.
Highlights
The rapid advancement of the technologies used in geodesy and geomatics has opened up many possibilities in various scientific spheres
This study focuses on automatic object detection from panoramic images, obtained by mobile mapping technology, which is followed by the blurring of those objects
Colorization of the point cloud is performed with the help of collected images, and this has helped a more efficient extraction and element recognition
Summary
The rapid advancement of the technologies used in geodesy and geomatics has opened up many possibilities in various scientific spheres. The implementation of laser scanning technology combined with a high-precision navigation system enables 3D scanning of road infrastructure (mobile laser scanning – MLS) By using this method, time consumption is reduced (Sztubecki et al, 2020), and it is possible to obtain a significantly larger amount of information. Reliable feature extraction from 3D point cloud data is an important phase in numerous application domains, such as traffic managing, object recognition, autonomous navigation, civil engineering and architectural projects. Each photo is associated with the appropriate position from the trajectory, and in this way the photo is matched with the point cloud (Batilovicet al., 2019) These images are gaining in importance due to the processes of visualization and different map creation.
Sign-in/Register to view highlights & summary 
Published Version (
Free)
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 call