Giovanni Fusco
Senior Computer Vision Engineer, Pixofarm
Degrees: Ph.D. in Computer Science, Universita' degli Studi di Genova
M.S. in Computer Science, Universita' degli Studi di Napoli Federico II
B.S. in Computer Science, Universita' degli Studi di Napoli Federico II
M.S. in Computer Science, Universita' degli Studi di Napoli Federico II
B.S. in Computer Science, Universita' degli Studi di Napoli Federico II
I combine my expertise in Computer Science, Computer Vision, Machine Learning and Assistive Technologies to create new technology for blind individuals to make travel, employment and education accessible. My main research focuses on developing tools to reduce accessibility barriers in the Science, Technology, Engineering and Mathematics (STEM) fields and in online media.
Tabs
Journal Articles
. (2021). Real-Time Sign Detection for Accessible Indoor Navigation. Journal On Technology And Persons With Disabilities, 9.
. (2016). Smooth pursuit eye movements in patients with macular degeneration. Journal Of Vision, 16, 1.
. (2014). Structured multi-class feature selection with an application to face recognition. Pattern Recognition Letters.
Conference Papers
. (2021). A Tangible Block Editor for the Scratch Programming Language. In CHI 2021. ACM: Yokohama, Japan.
. (2020). An Indoor Navigation App using Computer Vision and Sign Recognition. In 17th International Conference on Computers Helping People with Special Needs.
. (2020). Indoor Localization for Visually Impaired Travelers Using Computer Vision on a Smartphone. In 17th International Web for All Conference: Automation for Accessibility.
. (2019). Modeling echo-target acquisition in blind humans. In Conference on Cognitive Computational Neuroscience. Conference on Cognitive Computational Neuroscience: Berlin, Germany.
. (2018). Indoor Localization using Computer Vision and Visual-Inertial Odometry. In International Conference on Computers Helping People with Special Needs (ICCHP '18). Linz, Austria: Linz, Austria.
. (2016). Towards a Sign-Based Indoor Navigation System for People with Visual Impairments. In 18th International ACM SIGACCESS Conference on Computers and Accessibility. ACM: Reno, NV.
. (2015). Appliance Displays: Accessibility Challenges and Proposed Solutions. In 17th International ACM SIGACCESS Conference on Computers and Accessibility. ACM: Lisbon, Portugal. http://doi.org/http://dx.doi.org/10.1145/2700648.2811392
. (2014). Using Computer Vision to Access Appliance Displays. In ASSETS.
. (2014). Determining a Blind Pedestrian’s Location and Orientation at Traffic Intersections. In Computers Helping People with Special Needs (pp. 427–432). Springer International Publishing.
. (2014). Self-Localization at Street Intersections. In Computer and Robot Vision (CRV), 2014 Canadian Conference on (pp. 40–47). IEEE.
. (2013). Structured multi-class feature selection for effective face recognition. In Image Analysis and Processing–ICIAP 2013 (pp. 410–419). Springer Berlin Heidelberg.
. (2013). A system for the automatic measurement of the nuchal translucency thickness from ultrasound video stream of the foetus. In Computer-Based Medical Systems (CBMS), 2013 IEEE 26th International Symposium on (pp. 239–244). IEEE.
. (2012). Combining retrieval and classification for real-time face recognition. In Advanced Video and Signal-Based Surveillance (AVSS), 2012 IEEE Ninth International Conference on (pp. 276–281). IEEE.
. (2010). Low-cost face biometry for visually impaired users. In Biometric Measurements and Systems for Security and Medical Applications (BIOMS), 2010 IEEE Workshop on (pp. 45–52). IEEE.
. (2009). A semi-automated method for the measurement of the fetal nuchal translucency in ultrasound images. In Image Analysis and Processing–ICIAP 2009 (pp. 613–622). Springer.
Rehabilitation Engineering Research Center
The Center's research goal is to develop and apply new scientific knowledge and practical, cost-effective devices to better understand and address the real-world problems of blind, visually impaired, and deaf-blind consumers
Teng Lab
We aim to better understand how people perceive, interact with, and move through the world, especially when vision is unavailable. To this end, the lab studies perception and sensory processing in multiple sensory modalities, with particular interests in echolocation and braille reading in blind persons. We are also interested in mobility and navigation, including assistive technology using nonvisual cues. These are wide-ranging topics, which we approach using a combination of psychophysical, neurophysiological, engineering, and computational tools.
Active
Active
A11Y COVID-19
Accessible COVID-19 pandemic data are available at covid.ski.org
Active
t-Scratch: Tangible Programming Environment
tScratch: Tangible Programming Environment Targeted for Students who are Blind or Visually Impaired Introductory programming languages are overwhelmingly designed with sighted students in mind. Our goal is to expand and enhance scratch (https://scratch.mit.edu/), a block-based visual programming...
Active
Tactile Graphics Helper (TGH)
Tactile graphics use raised lines, textures, and elevations to provide individuals with visual impairments access to graphical materials through touch. Tactile graphics are particularly important for students in science, technology, engineering, and mathematics (STEM) fields, where educational...
Active
Human Echolocation
What is echolocation? Sometimes, the surrounding world is too dark and silent for typical vision and hearing. This is true in deep caves, for example, or in murky water where little light penetrates. Animals living in these environments often have the ability to echolocate: They make sounds and...
Active
ZoomBoard: an Affordable, Portable System to Improve Access to Presentations and Lecture Notes for Low Vision Viewers
The goal of the project is to develop a “ZoomBoard” system that students with low vision can use to better access visual material on a whiteboard or blackboard. The prototype version of the system that we plan to develop in this grant will consist of a dedicated camera...
Active
Sign Finder
This project seeks to develop a computer vision-based system that allows a visually impaired traveler to find and read informational signs, such as signs labeling office doors, streets, restrooms and Exit signs.
Link to...
Active
A Computer Vision-Based Indoor Wayfinding Tool
The ability to navigate safely and confidently is a fundamental requirement for independent travel and access to many settings such as work, school, shopping, transit and healthcare. Navigation is particularly challenging for people with visual impairments, who have limited ability to see signs, landmarks or maps posted in the environment.
Active
CamIO
CamIO (short for “Camera Input-Output”) is a system to make physical objects (such as documents, maps, devices and 3D models) accessible to blind and visually impaired persons, by providing real-time audio feedback in response to the location on an object that the user is touching. CamIO...
Completed
Completed
Display Reader
The goal of the Display Reader project is to develop a computer vision system that runs on smartphones and tablets to enable blind and visually impaired persons to read appliance displays. Such displays are found on an increasing array of appliances such as microwave ovens, thermostats and home...
Completed
Crosswatch
Crosswatch is a smartphone-based system developed for providing real-time guidance to blind and visually impaired travelers at traffic intersections. Using the smartphone's built-in camera and other sensors, Crosswatch is designed to tell blind and visually impaired travelers what kind of...
Contact Information
Email:
giofusco@ski.org
Links