A talk by Ryan Alimo. Artificial Intelligence (AI) is set to revolutionize the way we live, work, and communicate with each other.

With the wide adoption of AI in our daily lives we will soon find it part of our daily routine that would extend our capabilities.

A critical element of AI systems is its brain and vision system. The marriage between AI and affordable consumer based depth sensors (e.g., LiDAR scanner) is giving birth to new industries including spatial mapping and augmented reality (AR) that would change many jobs including first responders would be performed in the near future.

In this talk, we will review some of the applications of 3D computer vision for space and proptech applications that could be beneficial for first responders. We first demonstrate how our advanced AI algorithms based on neural rendering are capable of converting a video to a 3D scene view with high resolution particularly for virtual tour applications. Then we demonstrate the state of the art photogrammetry and AI app named, ScanTo3D, that could enable the first responders to reconstruct a floorplan of the building in real time by simply walking around and taking video of the property.

Also, we show the applications of 3D segmentations in scene understanding and enabling the first responders to make faster decision making capability leveraging smart glasses and their smartphones.

In the end, we draw some conclusions and summarize our experiences with working with 3D machine vision and how first responders could take advantage of the 5th industrial revolution to reduce cost and increase performance.