Dipartimento d'Ingegneria

Engineering design and metallurgy - Progettazione industriale, costruzioni meccaniche e metallurgia

The research interests of the group include all tools and methods related to any stage of product design and manufacturing.
At present the activity is mainly focussed on the following areas: machine design; system dynamics; structural mechanics; computer-aided engineering (including finite elements analysis, computational fluid dynamics and multi-body simulation); fatigue mechanics; random loads fatigue; comfort evaluation; motion sickness analysis; product design; design tools and method in Engineering; engineering drawing; computer-aided design; design for life-cycle; tolerance analysis; machine vision and machine learning for industrial applications.

Texture databases for benchmarking

In Research ,
Written by Friday, 02 May 2014 17:30
Texture analysis is an area of intense research activity. Like in other fields, the availability of public data for benchmarking is vital to the development of the discipline. In ‘‘Texture databases – A comprehensive survey’’, Hossain and Serikawa recently provided a precious review of a good number of texture datasets. We have recently proposed an appendix to complement the cited work by providing reference to additional image databases of bio-medical textures, textures of materials and natural textures that have been recently employed in experiments with texture analysis.

F Bianconi and A. Fernández, An appendix to ‘‘Texture databases – A comprehensive survey’’, Pattern Recognition Letters, 45(1):33-38,2014
Stereo pair images from very high-resolution optical satellites GeoEye-1 (GE1) and WorldView-2 (WV2) can be succesfully used for land cover classification agricultural areas through object-based image analysis. The overall accuracy attained by applying nearest neighbor and support vector machine classifiers to the four multispectral bands of GE1 were very similar to those computed from WV2, for either four or eight multispectral bands. Height data, in the form of nDSM, proved to be the most important feature for greenhouse classification. We obtained overall accuracy close to 90%.

M.Á. Aguilar, F. Bianconi, F.J. Aguilar and I. Fernández, "Object-Based Greenhouse Classification from GeoEye-1 and WorldView-2 Stereo Imagery", Remote Sensing, 6(5):3554-3582, 2014

Colour descriptors for parquet sorting

In Research ,
Written by Wednesday, 05 March 2014 10:43
We have experimentally investigated and compared the performance of various colour descriptors (i.e.: soft descriptors, percentiles, marginal histograms and 3D histogram), and colour spaces (i.e.: RGB, HSV and CIE Lab) for parquet sorting. The results show that simple and compact colour descriptors, such as the mean of each colour channel, are as accurate as more complicated features. Likewise, we found no statistically significant difference in the accuracy attainable through the colour spaces considered in the paper. Our experiments also show that most methods are fast enough for real-time processing. The results suggest the use of simple statistical descriptors along with RGB data as the best practice to approach the problem.

OAK 04 
OAK 08

F. Bianconi, A. Fernández, E. González and S.A. Saetta, "Performance analysis of colour descriptors for parquet sorting", Expert Systems With Applications, 40(5):1636-1644, 2013

GEOEYE1-WV2 project just finished

In Projects ,
Written by Tuesday, 04 March 2014 16:15
'GEOEYE1-WV2: generation of high resolution geo-referenced data from GeoEye-1 and WorldView-2 satellite images' (ref. CTM2010-16573) has finalised. The project, in which Dr. Francesco Bianconi participated as a member of the research group, was coordinated by the University of Almería, Spain. Find out more.

Page 5 of 6


This site uses cookies, including third parties, for statistics and to help you navigate web pages. Further information available at the privacy policy page. Learn more

I understand