I completed my PhD study in computer science on June 2015 from the CUNY Graduate Center in the City College Visual Computing Laboratory (CcvcL) under the advisement of Prof. Zhigang Zhu. Most of my doctoral work was in the area of multimodal sensor registration and 3D stereo visualization of Large-Scale scenes persistently captured over long periods of time. I also continue to study and design accessible/assistive technologies for disabled communities, with a focus on the blind and visually impaired communities.
Previously, I was CEO/Co-Founder of Vista Wearable Inc. (now closed), an assistive technology spinoff company from the CcvcL.
Currently, I am the Head Instructor for the CUNY Tech Prep program, which is a NYC Tech Talent Pipeline initiative.
I am also available for consulting. I have experience in Computer Vision development, Digital Hardware Development, in Mobile Development (iOS, Android), and in Full Stack Web Development (Ruby on Rails, DevOps, and API development).
- Computer Vision
- Human-Computer Interaction (HCI) and Situational Awareness
- Visualization (3D Stereo and Data)
- Multimodal Sensing and Machine Learning
- Accessible/Assistive Technologies for Visually Impaired People
- Edgardo Molina and Zhigang Zhu. Persistent aerial video registration and fast multiview mosaicing. Image Processing, IEEE Transactions on, 23(5):2184–2192, May 2014
- Edgardo Molina, Alpha Diallo, and Zhigang Zhu. Visual noun navigation framework for the blind. Journal of Assistive Technologies, 7(2):118–130, 2013
- Zhigang Zhu and Edgardo Molina. Panostereo: Panoramic stereoscopic imaging. In Phil Laplante, editor, Encyclopedia of Image Processing. Taylor and Francis Group (invited and under review), 2014
- Zhu, Z., Li, W., Molina, E., and Wolberg, G., LDV sensing and processing for remote hearing in a multimodal surveillance system. In Z. Zhu and T. Huang, editors, Multimodal Surveillance: Sensors, Algorithms and Systems. Artech House Publisher, 2007
- Edgardo Molina, Zhigang Zhu, and Yingli Tian. Visual nouns for indoor/outdoor navigation. In Proceedings of the 13th International Conference on Computers Helping People with Special Needs - Volume Part II, ICCHP’12, pages 33–40, Berlin, Heidelberg, 2012. Springer-Verlag
- E. Molina, Zhigang Zhu, and C.N. Taylor. A layered approach for fast multi-view stereo panorama generation. In Multimedia (ISM), 2011 IEEE International Symposium on, pages 589–594, Dec 2011
- Yufu Qu, W.L. Khoo, E. Molina, and Zhigang Zhu. Multimodal 3d panoramic imaging using a precise rotating platform. In Advanced Intelligent Mechatronics (AIM), 2010 IEEE/ASME International Conference on, pages 260–265, July 2010
- Edgardo Molina, Zhigang Zhu, and Olga Mendoza-Schrock. Mosaic-based 3d scene representation and rendering of circular aerial video. In SPIE Defense, Security, and Sensing, pages 77040K–77040K. International Society for Optics and Photonics, 2010
- E. Molina, Hao Tang, Zhigang Zhu, and O. Mendoza. Mosaic-based modeling and rendering of large-scale dynamic scenes for internet applications. In Aerospace and Electronics Conference, 2008. NAECON 2008. IEEE National, pages 322–329, July 2008
- Zhigang Zhu, Weihong Li, E. Molina, and G. Wolberg. Ldv sensing and pro- cessing for remote hearing in a multimodal surveillance system. In Computer Vision and Pattern Recognition, 2007. CVPR ’07. IEEE Conference on, pages 1–2, June 2007
- Zhu, Z., Ro, T., Ai, L., Khoo, W., Molina, E., and Palmer, F. Wearable navigation assistance for the vision-impaired, December 27, 2013. US Patent App. 14/141,742 (pending)