- All Categories
- Featured Events
- Alumni
- Application Deadline
- Arts
- Campus Discourse
- Careers
- BU Central
- Center for the Humanities
- Charity & Volunteering
- Kilachand Center
- Commencement
- Conferences & Workshops
- Diversity & Inclusion
- Examinations
- Food & Beverage
- Global
- Health & Wellbeing
- Keyword Initiative
- Lectures
- LAW Community
- Meetings
- Orientation
- Other Events
- Religious Services & Activities
- Special Interest to Women
- Sports & Recreation
- Social Events
- Study Abroad
- Weeks of Welcome
- In Wilderness Is the Preservation of the World: Photography by Dan Wells12:00 am
- CGS/CFA Voter Registration Drive10:00 am
- IS&T RCS Tutorial - Introduction to Python, Part One10:00 am
- Passport Pop-Up 11:00 am
- Spring Study Abroad Expo 11:00 am
- Research Presentation by Christine Mulhern: Beyond Teachers: Estimating Individual Guidance Counselors' Effects on Educational Attainment11:30 am
- Cross-Disability Club Meeting (ONLINE)12:30 pm
- IS&T RCS Tutorial - Data Wrangling in R1:00 pm
- ECE PHD Prospectus Defense: M. Ozan Tezcan1:30 pm
- IS&T RCS Tutorial - Programming in R2:00 pm
- CFA Student Listening Session2:00 pm
- Create Space3:00 pm
- IS&T RCS Tutorial - Version Control and Collaboration with Git and GitHub, Part One3:30 pm
- GCI Colloquium - Exceptional Investments: Analyzing the Relative Environmental Performance of China's Overseas Coal Plants3:30 pm
- Neural data science: from raw neuroscience recordings to scientific discoveries (Pengcheng Zhou - Columbia University)4:00 pm
- Time Management & Goal Setting Workshop4:00 pm
- Interviewing 1014:00 pm
- Global Dinner Club5:00 pm
- Grad School Info Session: Brown University5:00 pm
- A Writer’s Guide To Surviving Your First Book Deal5:30 pm
- Transfer Welcome (Back) Reception5:30 pm
ECE PHD Prospectus Defense: M. Ozan Tezcan
Title: Deep Learning Algorithms for Background Subtraction and People Detection
Presenter: M. Ozan Tezcan
Date: January 28, 2020
Time: 1:30PM- 3:30PM
Locations: PHO404/428
Advisor: Professor Janusz Konrad, ECE
Chair: Professor Prakash Ishwar, ECE
Committee: Professor Brian Kulis, ECE; Professor Pierre-Marc Jodoin, University of Sherbrooke
Abstract:Background subtraction is a basic task in computer vision and video processing often applied as a preprocessing step for object tracking, action recognition, etc. To date, many successful background subtraction algorithms have been proposed. Unsurprisingly, the top performing methods on “changedetection.net” today are supervised, deep-learning approaches. Their excellent performance, however, hinges on the availability of some annotated frames from a test video during training.
In this prospectus, I propose an alternative framework for background subtraction via supervised deep learning and its application to people detection. To date, I developed a novel algorithm, Background Subtraction for Unseen Videos (BSUV-Net), that is based on a fully convolutional neural network. Unlike in past approaches, the input to the network consists of the current frame and two background frames captured at different time scales along with their semantic segmentation maps. To reduce the chance of overfitting, I introduced a new data-augmentation technique that further mitigates illumination variations.In order to explore the potential of background subtraction as a pre-processing step for more complex visual analysis, I participated in a proof-of-concept study of people detection and counting from overhead fisheye cameras. Our most successful approach leverages people detection algorithms optimized for standard images (perspective-projection geometry) to detect people in fisheye images (radial geometry) via pre- and post-processing. Combining this approach with background subtraction affords a significant speed-up.
For the remainder of my PhD thesis research, I propose to further study background subtraction using video-agnostic neural networks that do not memorize video categories or specific challenges (e.g., snow, shadows), but instead focus exclusively on detecting changes. One approach I will consider is the GAN framework with a discriminator network that tries to classify the input video using BSUV-Net’s feature embedding, and an adversarial loss that tries to fool the discriminator. I expect this architecture to produce video-agnostic features. As for people detection, I will investigate the use of background subtraction in an attention mechanism that focuses a network on foreground pixels. Since people are typically part of the foreground, this is expected to improve the people-detection performance.
When | 1:30 pm to 3:30 pm on Tuesday, January 28, 2020 |
---|---|
Location | PHO404/428 |