About Me

I received my bachelor degree and my master degree in Computer Science (both summa cum laude) from the University of Catania in 2010 and 2013 respectively. In 2012 I joined the IPLAB. In 2013-2016 I have been a PhD student at the University of Catania under the supervision of Prof. Sebastiano Battiato and Dr. Giovanni Maria Farinella

My main research interests concern Computer Vision and Pattern Recognition, with a particular focus on First Person Vision.

Research

Recognizing Personal Locations from Egocentric Videos Project Web Page PaperBibTeX
Contextual awareness in wearable computing allows for construction of intelligent systems, which are able to interact with the user in a more natural way. We study how personal locations arising from the user’s daily activities can be recognized from egocentric videos. We assume that few training samples are available for learning purposes. Considering the diversity of the devices available on the market, we introduce a benchmark dataset containing egocentric videos of eight personal locations acquired by a user with four different wearable cameras. To make our analysis useful in real-world scenarios, we propose a method to reject negative locations, i.e., those not belonging to any of the categories of interest for the end-user. We assess the performances of the main state-of-the-art representations for scene and object classification on the considered task, as well as the influence of device-specific factors such as the field of view and the wearing modality. Concerning the different device-specific factors, experiments revealed that the best results are obtained using a head-mounted wide-angular device. Our analysis shows the effectiveness of using representations based on convolutional neural networks, employing basic transfer learning techniques and an entropy-based rejection algorithm.
Project Web PagePaper BibTeX Computer Vision Algorithms for Fisheye Camera Systems
Computer Vision Algorithms for Fisheye Camera Systems Perspective cameras are the most popular imaging sensors used in Computer Vision. However, many application fields including automotive, surveillance and robotics, require the use of wide angle cameras (e.g., fisheye), which allow to acquire a larger portion of the scene using a single device at the cost of the introduction of noticeable radial distortion in the images. Affine covariant feature detectors have proven successful in a variety of Computer Vision applications including object recognition, image registration and visual search. Moreover, their robustness to a series of variabilities related to both the scene and the image acquisition process has been thoroughly studied in the literature. In this paper, we investigate their effectiveness on fisheye images providing both theoretical and experimental analyses. As theoretical outcome, we show that the inherently non-linear radial distortion can be locally approximated by linear functions with a reasonably small error. The experimental analysis builds on Mikolajczyk’s benchmark to assess the robustness of three popular affine region detectors (i.e., Maximally Stable Extremal Regions (MSER), Harris and Hessian affine region detectors), with respect to different variabilities as well as to radial distortion. To support the evaluations, we rely on the Oxford dataset and introduce a novel benchmark dataset comprising 50 images depicting different scene categories. Experiments are carried out on rectilinear images to which radial distortion is artificially added, and on real-world images acquired using fisheye lenses. Our analysis points out that affine region detectors can be effectively employed directly on fisheye images and that the radial distortion is locally modelled as an additional affine variability.
Visual Tracking PaperBibTeX
Visual TrackingVisual Tracking is the process of estimating the location of one or more objects of interest over time. Visual tracking strategies are formulated by making some assumptions on the application domain and choosing a suitable object representation and a frame-by-frame localization method. The object representation is usually updated during the tracking, especially when the target object is subject to geometric and photometric transformations (object deformations, light changes, etc.).
Saliency Detection PaperBibTeX
Visual SaliencySaliency detection is a useful tool for real-time Computer Vision applications. It allows to select the most relevant locations of a scene and has been used in a number of applications. We perform an experimental analysis focusing on three levels where saliency is defined in different ways, namely visual attention modelling, salient object detection and salient object segmentation.

Publications

International Journals
[1] A. Furnari, G. M. Farinella and S. Battiato, "Recognizing Personal Locations From Egocentric Videos", In IEEE Transactions on Human-Machine Systems, vol. 47, no. 1, pp. 6-18, 2017, DOI: 10.1109/THMS.2016.2612002. [bibtex] [pdf] [doi]
[2] A. Furnari, G. M. Farinella, A. R. Bruna and S. Battiato, "Affine Covariant Features for Fisheye Distortion Local Modeling", In IEEE Transactions on Image Processing, vol. 26, no. 2, pp. 696-710, 2017, DOI: 10.1109/TIP.2016.2627816. [bibtex] [pdf] [doi]
[3] S. Battiato, G. M. Farinella, A. Furnari, G. Puglisi, A. Snijders and J. Spiekstra, "An integrated system for vehicle tracking and classification", In Expert Systems with Applications, vol. 42, no. 21, pp. 7263–7275, 2015, DOI: 10.1016/j.eswa.2015.05.055. [bibtex] [pdf] [doi]
International Conferences/Workshops
[4] F. Ragusa, V. Tomaselli, A. Furnari, S. Battiato and G. M. Farinella, "Food Vs Non-Food Classification", In International Workshop on Multimedia Assisted Dietary Management (MADiMA) in conjunction with ACM, Amsterdam, The Netherlands, October 15-19, pp. 77–81, 2016, DOI: 10.1145/2986035.2986041. [bibtex] [pdf] [doi]
[5] Furnari, Antonino, Farinella, Giovanni Maria and Battiato, Sebastiano, "Temporal Segmentation of Egocentric Videos to Highlight Personal Locations of Interest", In International Workshop on Egocentric Perception, Interaction and Computing (EPIC) in conjunction with ECCV, The Netherlands, Amsterdam, October 9, Springer Lecture Notes in Computer Science, vol. 9913 of Lecture Notes in Computer Science, pp. 474–489, 2016. [bibtex] [pdf]
[6] A. Furnari, G. M. Farinella and S. Battiato, "Recognizing Personal Contexts from Egocentric Images", In Workshop on Assistive Computer Vision and Robotics (ACVR) in conjunction with ICCV, Santiago, Chile, December 12, 2015. [bibtex] [pdf]
[7] A .Furnari, G. M. Farinella, A. Bruna and S. Battiato, "Generalized Sobel Filters for Gradient Estimation of Distorted Images", In IEEE International Conference on Image Processing (ICIP), Quebec, Canada, September 27-30, pp. 3250-3254, 2015. [bibtex] [pdf]
[8] A. Furnari, G. M. Farinella, A. Bruna and S. Battiato, "Distortion Adaptive Descriptors: Extending Gradient-Based Descriptors to Wide Angle Images", In International Conference on Image Analysis and Processing (ICIAP), Genova, Italy, September 7-11, Springer Lecture Notes in Computer Science, vol. 9280 of Lecture Notes in Computer Science, pp. 205–215, 2015, DOI: 10.1007/978-3-319-23234-8_20. [bibtex] [pdf] [doi]
[9] A. Furnari, G. M. Farinella and S. Battiato, "An Experimental Analysis of Saliency Detection with respect to Three Saliency Levels", In Workshop on Assistive Computer Vision and Robotics (ACVR) in conjunction with ECCV, Zurich, Switzerland, September 12, Springer Lecture Notes in Computer Science, vol. 8927 of Lecture Notes in Computer Science, pp. 806-821, 2014, DOI: 10.1007/978-3-319-16199-0_56. [bibtex] [pdf] [doi]
[10] A. Furnari, G. M. Farinella, G. Puglisi, A. R. Bruna and S. Battiato, "Affine Region Detectors on the Fisheye Domain (ICIP)", In IEEE International Conference on Image Processing, Paris, France, October 27-30, pp. 5681–5685, 2014, DOI: 10.1109/ICIP.2014.7026149. [bibtex] [pdf] [doi]
[11] S. Battiato, G. M. Farinella, A. Furnari, G. Puglisi, A. Snijders and J. Spiekstra, "Vehicle tracking based on customized template matching", In VISAPP International Conference on Computer Vision Theory and Applications, Lisbon, Portugal, January 5-8, vol. 2, pp. 755-760, 2014. [bibtex] [pdf]
Abstracts
[12] D. Scandura, S. Battiato, V. Bruno, F. Cannavò, G. M. Farinella, A. Furnari, M. Mattia, G. Pappalardo, G. Puglisi and U. Weigmuller, "Image Processing Techniques to Estimate the Propagation of Ground Deformation at Mt. Etna (Italy) from ALOS PALSAR InSAR Data", American Geophysical Union (AGU) Fall Meeting, San Francisco, 2014. [bibtex]
[13] A. Furnari, G. M. Farinella, S. Battiato, "Segmenting Egocentric Videos to Highlight Personal Locations of Interest", Fourth Workshop on Egocentric (First-Person) Vision in conjunction with CVPR, Las Vegas, Nevada, July 1st, 2014. [bibtex] [pdf]
[14] S. Battiato, G. M. Farinella, A. Furnari, G. Puglisi, "A Customized System for Vehicle Tracking and Classification", European Conference on Mathematics for Industry (ECMI), Taormina, Italy, June 9-13, 2014. [bibtex] [pdf]