Student Projects 2014-2015

The article presents a list of projects developed for the course of 2D Vision Systems during the year 2014-2015.

The first project was developed by Simone Formichella, with the aim of developing a small vision system to detect objects on a rotating table using a NI1764 smart camera.

One of the problems the student faced was how to detect reflective objects with optical sensors and how to deal with the transparency of the rotating plate. Moreover, the smart camera was able to perform only lightweight elaborations, so the system had to be splitted between camera and the host PC, which was able to perform the more computational heavy processing required. The whole system was developed using LabView.

The second project was developed by Alessandro Nastro, with the aim of using a very low cost projector to project fringes for 3D reconstruction. 

The student created a triangulation system with two Basler Scout scA1390 cameras and a low cost projector (Philips PicoPix PPX22505). The student dealt with the camera 2D calibration performed by a custom made VI developed in LabView in order to correctly detect the fringes projected on the image and retrieve the period between them. In this way it is possibile to perform a 3D reconstruction of an object!

The third project was developed by Pietro Craighero with the aim of measuring the inner and the outer radius of a mechanical object using telecentric lenses.

Telecentric lenses allow users to obtain images with high contrast with almost no image distorsion, thus being a fundamental piece of any high accuracy vision system. The student created a small set-up with a red-light laser and a telecentric camera, used to acquire 2D images of the object to be measured. The software used for the project was developed in LabView.

Defect detection of mandrels using 3D Laser scanning

This project was committed to the Laboratory by Tenaris Dalmine, and was aimed at developing algorithms and measurement procedures for detecting defects in mandrels, for on-line inspection and quality control purposes.

The mandrels are scanned by using a laser slit: the profiles are acquired and the 3D map of the surface is obtained. Careful analysis of the 3D map allows the detection of surface defects.

The work is subjected to non disclosure agreements: the only available information is in the presentation below.

Optoranger: a 3D pattern matching method for bin picking applications

Optoranger is a new method, based on 3D vision, for the recognition of free-form objects in the presence of clutters and occlusions, ideal for robotic bin picking tasks. The method can be considered as a compromise between complexity and effectiveness.

A 3D point cloud representing the scene is generated by a triangulation-based scanning system, where a fast camera acquires a blade projected by a laser source. Image segmentation is based on 2D images, and on the estimation of the distances between point pairs, to search for empty areas. Object recognition is performed using commercial software libraries integrated with custom-developed segmentation algorithms, and a database of model clouds created by means of the same scanning system.

Experiments carried out to verify the performance of the method have been designed by randomly placing objects of different types in the Robot work area. The results demonstrate the excellent ability of the system to perform the bin picking procedure, and the reliability of the method proposed for automatic recognition of identity, position and orientation of the objects.

Related Publications

Sansoni, G.; Bellandi, P.; Leoni, F.; Docchio, F. “Optoranger: A 3D pattern matching method for bin picking applications“, Optics and Lasers in Engineering, Vol. 54, pp. 222-231. 2014

Combined use of Optical and Contact probes

This activity was carried out in the frame of a collaboration between our Laboratory and the DIMEG Metrological Laboratory of the University of Padova. It was aimed at integrating the measurement information from a 3D Vision sensor and a Coordinate Measuring Machine (CMM) for the reverse engineering of free-form surfaces. The objective was to reconstruct the CAD model of comples shapes with high accuracy and at the same time rapidly, and minimising the operator time.

Automotive applications: Reverse engineering of a Ferrari MM

This project was performed to demonstrate the feasibility of using an optical 3d range sensor based on fringe projection (OPL-3D) to acquire the shell of the Ferrari Mille Miglia shown in the figure. The point cloud were merged and the whole mash was obtained. A scaled copy of the shell was prototyped.

Related Publications

3D vision for the measurement of eccentricity of pipes

The aim of this project has been to design, to implement and to characterize a system for the 3D measurement of eccentricity of pipes.

This system was originally based on four laser slits, suitable oriented with respect to the pipe to acquire the external and the internal semi-profiles. In order to develop a compact version of the instrument, we studied a new optical layout, which halves the number of the cameras.

Related Publications

Sansoni, G.; Bellandi, P.; Docchio, F. “Design and development of a 3D system for the measurement of tube eccentricity“, Measurement Science and Technology, Vol. 22, no. 7. 2011

Sansoni, G.; Bellandi, P.; Docchio, F. “3D system for the measurement of tube eccentricity: an improved, rugged, easy to calibrate layout“, Measurement Science and Technology, Vol. 24, no. 3. 2013

The Robo3DScan Project

Recently, the integration of vision with robots has gained considerable attention from industry. Pick and place, sorting, assembling, cutting and welding processes are examples of applications which can have great advantage from the combination of information from 3D images with robot motion.

Our laboratory developed, in collaboration with DENSO EUROPE B. V., a system integrating 3D vision into robotic cells. The project led to the Roboscan system.

Roboscan is a Robot cell that combines 2D and 3D vision in a simple device, to aid a Robot manipulator in pick-and-place operations in a fast and accurate way. The optical head of Roboscan combines the two vision systems: the camera is used “stand-alone” in the 2D system, and combined to a laser slit projector in the 3D system, which operates in the triangulation mode. The 2D system, using suitable libraries, provides the preliminary 2D information to the 3D system to perform in a very fast, flexible and robust way the point cloud segmentation and fitting. The most innovative part of the system is represented by the use of robust 2D geometric template matching as a means to classify 3D objects. In this way, we avoid time-consuming 3D point cloud segmentation and 3D object classification, using 3D data only for estimating pose and orientation of the robot gripper. In addition, a novel approach to the template definition in the 2D geometric template matching is proposed, where the influence of surface reflectance and colour of the objects over the definition of the template geometry is minimized.

Related Publications

Bellandi, P.; Docchio, F.; Sansoni, G. “Roboscan: a combined 2D and 3D vision system for improved speed and flexibility in pick-and-place operation“, The International Journal of Advanced Manufacturing Technology, Vol. 69, no. 5–8, pp. 1873–1886. 2013

3D Acquisition and modeling for crime scene documentation

This project is aimed at testing the performance of 3D optical acquisition and reverse engineering to carry out the contact-less gauging of crime scenes for their documentation and analysis. In particular, the study focuses on two aspects. The former is the “in-field” measurement and modeling of crime scenes.

The activity carried out by the Laboratory staff deals with a number of significant cases. A comprehensive summary of the experiences is in the references below.

Related Publications

Cavagnini, G.; Scalvenzi, M.; Trebeschi, M.; Sansoni, G. “Reverse engineering from 3D optical acquisition: application to Crime Scene Investigation“, Proceedings of Virtual Modelling and Rapid Manufacturing, Advanced Research in Virtual and Rapid Prototyping, pp. 195-201. 2007

Sansoni, G.; Docchio, F.; Trebeschi, M.; Scalvenzi, M.; Cavagnini, G.; Cattaneo, C. “Application of three-dimensional optical acquisition to the documentation and the analysis of crime scenes and legal medicine inspection“, 2007 2nd International Workshop on Advances in Sensors and Interface, pp. 1-10. 2007

Sansoni, G.; Cattaneo, C.; Trebeschi, M.; Gibelli, D.; Porta, D.; Picozzi, M. “Feasibility of contactless 3D optical measurement for the analysis of bone and soft tissue lesions: new technologies and perspectives in forensic sciences“, Journal of Forensic Sciences, Vol. 54, no. 3, pp. 540-545. 2009

Sansoni, G.; Cattaneo, C.; Trebeschi, M.; Gibelli, D.; Poppa, P.; Porta, D.; Maldarella, M.; Picozzi, M. “Scene-of-Crime Analysis by a 3-Dimensional Optical Digitizer: A Useful Perspective for Forensic Science“, The American Journal of Forensic Medicine and Pathology, Vol. 32 no. 3, pp. 280-286. 2011

The Winged Victory of Brescia

The natural commitment of the Laboratory to applied research and to cooperation with institutions led to the establishment of an agreement between the Comune of Brescia and the University of Brescia for the study and the 3D digitization of one of the symbols of the City, the statue named ‘Vittoria Alata’. This 2m-high, bronze statue is located at the Museo of Santa Giulia at Brescia.
The original motivation of the archaeologists was to measure with high accuracy the distances between pairs of fiduciary points, in order to determine the archetype of the statue, and to solve the problem of its collocation in the right temporal and spatial framework. 

To obtain the statue proportions, the statue was completely acquired using OPL-3D; Multiview registration, meshing and modeling of the mesh resulted in the virtual copy of the statue. By means of rapid prototyping, different copyes varying in the reproduction scale have been developed.

The copy of the Winged Victory developed by the Laboratory staff represented the city of Brescia at the exhibition of the ANCI Conference, Brescia, 8-9 november 2007.

ANCI 002.jpg

Relevant Publications

Sansoni, G.; Patrioli, A.; Docchio, F.; Morandini, F. “Rilievo tridimensionale della Vittoria mediante tecniche di misura non a contatto“, Nuove ricerche sul Capitolium di Brescia: scavi, studi e restauri, pp. 159-163. 2002

Sansoni, G.; Docchio, F.; Patrioli, A. “Il rilievo 3D di forme complesse: stato dell’arte, applicazioni e prospettive“, Atti del 7° Convegno Nazionale di Strumentazione e metodi di misura elettroottici, pp. 263-270. 2002 

Sansoni, G.; Docchio, F. “A special case of 3-D optical measurements and reverse engineering for automotive applications: the Ferrari 250 Mille Miglia“, Proceedings of the 21st IEEE Instrumentation and Measurement Technology Conference, Vol. 2, pp. 1354-1359. 2004

Sansoni, G.; Docchio, F. “3-D optical measurements in the field of cultural heritage: the case of the Vittoria Alata of Brescia“, IEEE Transactions on Instrumentation and Measurement, Vol. 54, no. 1, pp. 359-368. 2005

3D prosthetic applications to maxillo-facial defects

In the last years, prosthetic techniques have gained increased interest in post oncological reconstruction and in congenital defect treatment. Both the fuctional and the aesthetic characteristics of the prosthesis are crucial, in view of allowing the patient to overcome the social, psychological and economic problems deriving from their handicap.

Traditional reconstruction techniques present a number of lacks: the patient’s discomfort and stress, the inaccuracy of the replicas, and the dependence on the artistic skills of an experienced prosthetist. In addition, the mould production process is cumbersome, and time consuming. Finally, the overall process is not adaptive, i.e., whenever the existing prothesis should be replaced, the overall process must be carried out from scratch.

The purpose of this research activity is to develop a novel approach that combines optical three-dimensional acquisition, reverse engineering (RE) and rapid prototyping (RP) for the prosthetic reconstruction of facial prostheses.

Relevant Publications

Sansoni, G.; Cavagnini, G.; Docchio, F.; Gastaldi, G. “Virtual and physical prototyping by means of a 3D optical digitizer: application to facial prosthetic reconstruction“, Virtual and Physical Prototyping, Vol. 4, pp. 217-226. 2009

Sansoni, G.; Trebeschi, M.; Cavagnini, G.; Gastaldi, G. “3D Imaging acquisition, modeling and prototyping for facial defects reconstruction“, Proceedings of SPIE Three-Dimensional Imaging Metrology, Vol. 7239, pp. 1-8. 2009

Cavagnini, G.; Sansoni, G.; Vertuan, A.; Docchio, F. “3D optical Scanning: application to forensic medicine and to maxillofacial reconstruction“, Proceedings of International Conference on 3D Body Scanning Technologies, pp. 167-178. 2010