In this episode I’m joined by Lyne Tchapmi, PhD student in the Stanford Computational Vision and Geometry Lab, to discuss her paper, “SEGCloud: Semantic Segmentation of 3D Point Clouds.”
Subscribe: iTunes / Google Play / Spotify / RSS
SEGCloud is an end-to-end framework that performs 3D point-level segmentation combining the advantages of neural networks, trilinear interpolation and fully connected conditional random fields. In our conversation, Lyne and I cover the ins and outs of semantic segmentation, starting from the sensor data that we’re trying to segment, 2d vs 3d representations of that data, and how we go about automatically identifying classes. Along the way we dig into some of the details, including how she obtained a more fine grain labeling of points from sensor data and the transition from point clouds to voxels.
Join me at the AI Summit
Are you an IT, technology or business leader who needs to get smart on the broad spectrum of machine learning and AI opportunities in the enterprise? Or, perhaps someone in your organization could benefit from a level-up in this area? (Or, maybe you would benefit from them leveling up!) If this sounds like you, or someone you know, you’ll probably be interested in my upcoming AI Summit event.
Think of the event as a two-day, no-fluff, Technical MBA in machine learning & AI. You’ll leave with a clear understanding of:
How machine learning and deep learning work (no math required)
How to identify machine learning and deep learning opportunities in your organization
How to understand and take advantage of technologies like computer vision and natural language processing
How to manage and label data to take advantage of ML and AI
And how to build an AI-first culture, and operationalize AI in your business.
You’ll have an informed perspective on what’s going on across the ML and AI landscape, and will be able to engage confidently in discussions about machine learning and AI with your colleagues, customers and partners. I’m super excited about this event and the speakers you’ll get a chance to learn from. For more information visit twimlai.com/aisummit, and feel free to contact me with your questions.
Mentioned in the Interview
- Paper – SEGCloud: Semantic Segmentation of 3D Point Clouds
- MIT SuperUROP
- Sebastian Thrun
- Nearest Neighbors Algorithm
- 2D-3D-S Dataset
- Joan Bruna & Michael Bronstein – Geometric Deep Learning
- Register for the TWIML Executive AI Bootcamp/Summit
- Check out @ShirinGlander’s Great TWIML Sketches!
- TWIML Presents: Series page
- TWIML Events Page
- TWIML Meetup
- TWIML Newsletter
“More On That Later” by Lee Rosevere licensed under CC By 4.0