Daniel Castro

Video Segmentation Project

The Video Segmentation Project was an effort to bring the video segmentation and annotation algorithm to the web. We leverage the tools under Google Cloud to provide users the ability to segment and annotate their videos online. To date, over 2000 videos have been processed in the online framework. Check it out at http://www.videosegmentation.com

Video Segmentation, Google Cloud
Discovering Picturesque Highlights from Egocentric Vacation Videos

We present an approach for identifying picturesque highlights from large amounts of egocentric video data. Given a set of egocentric videos captured over the course of a vacation, our method analyzes the videos and looks for images that have good picturesque and artistic properties. We introduce novel techniques to automatically determine aesthetic features such as composition, symmetry and color vibrancy in egocentric videos and rank the video frames based on their photographic qualities to generate highlights.

Egocentric Video, Segmentation
Predicting Daily Activities from Egocentric Images Using Deep Learning

In this project we are exploring the methods in which we can analyze egocentric images to recognize activities. Thus far we have conducted a few experiments, the main one of which analyzes 40,103 labeled images (by activity) taken over a period of 6 months and uses Convolutional Neural Networks (CNNs) to classify them. We achieve an overall accuracy of 83.07% for 19 unique activities.

Egocentric Images, Deep Learning, Computer Vision
Calibration-Free Rolling Shutter Removal

In this project, we focused on removing rolling shutter from user videos without calibrating to a specific camera. This project was eventually implemented into the video stabilization algorithm that runs on YouTube in a collaboration we did with Google.

Video Stabilization, Rolling Shutter

*Beards subject to availability, requests may be put in advance.
WHO AM I?

Hello there! My name is Daniel Castro, I am a PhD student under Dr. Irfan Essa at the Georgia Institute of Technology. I completed my undergraduate degree in Computer Science at GT in May 2013. I do research in the area of Computer Vision, and my interests outside of computing lie heavily in traveling the world to understand diverse cultures, fueling my adrenaline with skydiving and canyon jumping, writing poetry , and spending time becoming a better person :).

A few of the people I admire include Jason Silva, Devin Supertramp, and Lindsey Stirling.
PUBLICATIONS / WORK

Grundmann, M., Kwatra, V., Castro, D., & Essa, I. (2012, April). Calibration-free rolling shutter removal. In Computational Photography (ICCP), 2012 IEEE International Conference on (pp. 1-8). IEEE. Best Paper Award.

Google, Engineering Practicum Intern (Summer 2011), Software Engineering Intern (Summer 2012).

Teaching Assistant, CS 4475 (Computational Photography), CS 4474 (Computational Journalism), Barcelona Study Abroad, Summer 2013.

WHO AM I?

PUBLICATIONS / WORK