PHOTOMETRIC STEREO FOR VEHICLE NAVIGATION

Organization Name

ford global technologies, llc

Inventor(s)

David Michael Herman of West Bloomfield MI (US)

Larry Sanders of Monroe MI (US)

Binduhasini Sairamesh of Milpitas CA (US)

Akshay Vaidya of Canton MI (US)

PHOTOMETRIC STEREO FOR VEHICLE NAVIGATION - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240239367 titled 'PHOTOMETRIC STEREO FOR VEHICLE NAVIGATION

The abstract of the patent application describes a computer system that controls a vehicle-mounted lamp system to capture image data of a scene, generate a map of surface normals using photometric stereo algorithms, and navigate the vehicle based on the map when the vehicle's speed is below a certain threshold.

Simplified Explanation:

- A computer system controls vehicle-mounted lamps to capture image data and generate a map of surface normals for navigation.

Key Features and Innovation:

- Sequential activation of lamps for scene illumination. - Image data processing using photometric stereo algorithms. - Navigation based on surface normals map.

Potential Applications:

- Autonomous driving systems. - Robotics for navigation in various environments. - Surveillance and security systems.

Problems Solved:

- Efficient scene capture and navigation in low-speed scenarios. - Accurate surface mapping for obstacle avoidance.

Benefits:

- Improved safety in low-speed driving conditions. - Enhanced navigation accuracy in complex environments.

Commercial Applications:

- Title: "Advanced Navigation System for Vehicles" - Potential use in autonomous vehicles, drones, and security robots. - Market implications in transportation, surveillance, and robotics industries.

Prior Art:

- Prior research on photometric stereo algorithms for surface reconstruction. - Existing navigation systems for autonomous vehicles.

Frequently Updated Research:

- Ongoing advancements in photometric stereo algorithms for improved surface mapping accuracy.

Questions about the technology: 1. How does the computer system determine when to activate the lamps for scene capture? 2. What are the limitations of using photometric stereo algorithms for surface normal generation in real-time applications?

Original Abstract Submitted

a computer includes a processor and a memory, and the memory stores instructions executable by the processor to sequentially activate a plurality of lamps aimed at a scene, the lamps mounted to a vehicle; receive image data of the scene generated while sequentially activating the lamps; generate a map of surface normals of the scene by executing a photometric stereo algorithm on the image data; and in response to a speed of the vehicle being below a speed threshold, navigate the vehicle based on the map of the surface normals.