Leveraging Video Analytics at United Airlines: Calculating Deplaning Times Using Deep Learning
For United Airlines, running a Safe and Efficient airline is core to our business. And with such a complex operation, we need to constantly track key events that keep the airline running smoothly. While tracking these events can be time-intensive and laborious, we believe developments in deep learning and edge computing are going to help us simplify that process. Over the past few months, United’s Data Science team has been exploring how to leverage advances in computer vision to solve some of these problems. Our presentation will focus on solving one of these tasks: timing how long it takes for passengers to exit an aircraft. We’ll provide an overview of key concepts of video analytics, share how we leveraged open source technology to build a solution and provide a demonstration of our work.
Outline/Structure of the Demonstration
- Importance of video recordings in the airline industry (2 mins)
- Video analytics as a substitute for simple, manual tasks (5 mins)
- Calculate Deplaning time: Problem Definition and need for a solution (3 mins)
- Deep learning concepts for Video analytics (12 mins)
- Image classification, localization and detection
- Understanding object detection vs. object tracking
- Combining both object detection and object tracking
- Finding the right DeepLearning framework, architecture and associated tradeoffs (3 Mins)
- Using OpenCV with DeepLearning models (5 mins)
- Demonstration of the solution and explanation of how interpretations are made through visualizations (5 mins)
- Q & A (10 mins)
- Need of video analytics in Airlines Industry and various applications
- Deep Learning & Computer Vision concepts and architectures for video analytics
ML enthusiasts, Data Scientists and everyone who believes that using AI can help us make our jobs a little bit easier.
Prerequisites for Attendees
We’ll be giving an overview of all the required concepts in the session but a basic understanding of below things will help:
- Video analysis related terms like FPS, resolution etc.
- Deep learning concepts like Convolution, Model training etc.
- Basic OpenCV concepts