Rapid development of machine learning techniques opens new application fields for Unmanned Aerial Vehicles technology, which include detection and classification of objects. It is possible to detect buildings, vehicles or various objects present near pipelines and industrial buildings. In some cases, such as monitoring of the critical infrastructure, accuracy of the detection is crucial. 2D data classification enables detecting an object and determining its basic parameters. 3D data, that can be obtained from drones, supplement 2D data, and can significantly increase the accuracy of detection and classification of objects. It also bares additional information and can simplify determination of dimensions of already classified objects. Furthermore, some objects, difficult for classification using 2D images, can be easily classified with 3D data. Such objects are for example: excavations in the ground, objects partially overshadowed by trees or fully covered by dried leaves. 3D data collected by drones is typically obtained with SfM (Structure from Motion) and Lidar (Light Detection and Ranging) methods. SfM provides three-dimensional data from the photos that have been collected for 2D analysis. The advantage of this method is high quality texture. The main problem is that this method is not useful for night flights due to lack of feature points on images. Lidar is a laser measurement method using data on the time of flight of a laser beam reflected from an obstacle (object). It allows to obtain 3D data in all light conditions. However, collected data does not have color information. The combination of both methods will provide dense and accurate point clouds with texture, which can be consequently used for detection and classification of objects. In this paper a pipeline for acquisition, merging and processing of 3D data gathered by drones is presented. The first step is to obtain assembled point clouds from Lidar in one coordinate system using GPS data. Then Lidar point cloud is integrated with SfM point clouds. 3D data generated this way also includes coordinates of camera in the moments when SfM photos were collected. The full 3D model of monitored area containing GPS coordinates and positions of camera may be used to simplify configuration of a supplementary flight in order to measure places where no measurement data was obtained or the density of point cloud was too low. Having a point cloud of the reconstructed object prepared in such way, it is possible to compare point clouds, features extracted from point clouds and geometry of already classified objects over time.
In this paper, a fully automated 3D digitization system for documentation of paintings is presented. It consists of a specially designed frame system for secure fixing of painting, a custom designed, structured light-based, high-resolution measurement head with no IR and UV emission. This device is automatically positioned in two axes (parallel to the surface of digitized painting) with additional manual positioning in third, perpendicular axis. Manual change of observation angle is also possible around two axes to re-measure even partially shadowed areas. The whole system is built in a way which provides full protection of digitized object (moving elements cannot reach its vicinity) and is driven by computer-controlled, highly precise servomechanisms. It can be used for automatic (without any user attention) and fast measurement of the paintings with some limitation to their properties: maximum size of the picture is 2000mm x 2000mm (with deviation of flatness smaller than 20mm) Measurement head is automatically calibrated by the system and its possible working volume starts from 50mm x 50mm x 20mm (10000 points per square mm) and ends at 120mm x 80mm x 60mm (2500 points per square mm). The directional measurements obtained with this system are automatically initially aligned due to the measurement head’s position coordinates known from servomechanisms. After the whole painting is digitized, the measurements are fine-aligned with color-based ICP algorithm to remove any influence of possible inaccuracy of positioning devices.
We present exemplary digitization results along with the discussion about the opportunities of analysis which appear for such high-resolution, 3D computer models of paintings.
In this paper a fully automated 3D shape measurement and processing method is presented. It assumes that positioning of
measurement head in relation to measured object can be realized by specialized computer-controlled manipulator. On the
base of existing 3D scans, the proposed method calculates "next best view" position for measurement head. All 3D data
processing (filtering, ICP based fitting and final views integration) is performed automatically. Final 3D model is created
on the base of user specified parameters like accuracy of surface representation or density of surface sampling.
Exemplary system that implements all mentioned functionalities will be presented. The goal of this system is to
automatically (without any user attention) and rapidly (from days and weeks to hours) measure whole object with some
limitations to its properties: maximum measurement volume is described as a cylinder with 2,5m height and 1m radius,
maximum object's weight is 2 tons. Measurement head is automatically calibrated by the system and its possible working
volume starts from 120mm x 80mm x 60mm and ends up to 1,2m x 0,8m x 0,6m. Exemplary measurement result is presented.
In this paper a fully automated 3D shape measurement system is presented. It consists of rotary stage for cultural heritage
objects placement, vertical linear stage with mounted robot arm (with six degrees of freedom) and structured light
measurement set-up mounted to its head. All these manipulation devices are automatically controlled by collision
detection and next-best-view calculation modules. The goal of whole system is to automatically (without any user
attention) and rapidly (from days and weeks to hours) measure whole object. Measurement head is automatically
calibrated by the system and its possible working volume starts from centimeters and ends up to one meter. We present
some measurement results with different working scenarios along with discussion about its possible applications.
In this paper a distributed intelligent system for civil engineering structures on-line measurement, remote monitoring,
and data archiving is presented. The system consists of a set of optical, full-field displacement sensors connected to a
controlling server. The server conducts measurements according to a list of scheduled tasks and stores the primary data
or initial results in a remote centralized database. Simultaneously the server performs checks, ordered by the operator,
which may in turn result with an alert or a specific action.
The structure of whole system is analyzed along with the discussion on possible fields of application and the ways to
provide a relevant security during data transport. Finally, a working implementation consisting of a fringe projection,
geometrical moiré, digital image correlation and grating interferometry sensors and Oracle XE database is presented.
The results from database utilized for on-line monitoring of a threshold value of strain for an exemplary area of interest
at the engineering structure are presented and discussed.
In this paper a concept of a Internet Virtual Studio as a modern system for production of news, entertainment,
educational and training material is proposed. This system is based on virtual studio technology and integrated with
multimedia data base. Its was developed for web television content production. In successive subentries the general
system architecture, as well as the architecture of modules one by one is discussed. The authors describe each module by
presentation of a brief information about work principles and technical limitations. The presentation of modules is
strictly connected with a presentation of their capabilities. Results produced by each of them are shown in the form of
exemplary images. Finally, exemplary short production is presented and discussed.