AI For Mankind Tech Talk: Deep Learning Based Wildfire Detection

Let's join forces to stop wildfires. Come and learn how deep learning/computer vision can be applied in wildfire detection and how you can help contributing to the solution.

California leads the nation in wildfire risk, with more than a quarter of the state’s properties considered at high-to-extreme peril, according to the Insurance Information Institute, a New York-based industry group.

Last year, California accounted for about a fifth of the 8.8 million acres burned nationally, according to the Fire Center. The U.S. spent more than $3.1 billion fighting fires last year.

Checkout this youtube video: Residents of Paradise, in Northern California, fled a fast-moving wildfire that continues to burn out of control. (Nov. 9, 2018) https://youtu.be/d4kmmTc--Vg

In this event, we will have

1) Dr. Kinshuk Govil from Team FUEGO (Fire Urgency Estimator in Geosynchronous Orbit) https://fuego.ssl.berkeley.edu/ to present about

"FUEGO Early Fire Detection"

Learn more about FUEGO: https://www.nbcnews.com/mach/science/astrophysicist-has-audacious-plan-stop-wildfires-ncna899341

Using modern digital technology, FUEGO will utilize platforms at various altitudes to detect wildland fires very early, measure wildland fires with high precision and specificity, and then feed such results into modern fire simulation programs.

Speaker Bio:
Dr. Kinshuk Govil received a BS in EECS from UC Berkeley, and a PhD in Computer Science from Stanford University.

Then he worked at VMware as Principal Engineer, and led the development of vSphere and vCenter products.

Dr. Govil developed a machine learning based image recognition system for Benetech [https://benetech.org/] to help digitize books for the blind.
Later, he worked as Principal Engineer at Google, where he worked on a novel SaaS application platform and led ML projects for emerging products.

Currently, Dr. Govil is leading the development of ML based early fire detection system with FUEGO group.

2) AI For Mankind will talk about our collective community efforts in developing wildfire smoke detection and curating an open dataset to promote research and collaboration. We will also share annotated wildfire smoke dataset and sample codes to get you started with deep learning based wildfire smoke classifier and detector.

Agenda:

4:30 pm: Door Open

4:30 pm to 5:00 pm: Networking

5:00 pm to 6:00 pm: Presentation 1

6:00 pm to 6:30 pm: Presentation 2

6:30 pm to 7:30 pm: Open discussion and planning on various tasks that volunteers can help and contribute to.

Note:
Adobe will check ID. Provide your full name when register for the event.
Please check in at Almaden Tower Lobby. Limited parking in Adobe. Use carpool or find offsite parking lots. Another options are Caltrain and Amtrak.

Adobe Inc
151 Almaden Blvd,
San Jose, CA 95113