18166118. SENSOR CALIBRATION FOR AUTONOMOUS SYSTEMS AND APPLICATIONS simplified abstract (NVIDIA Corporation)
Contents
SENSOR CALIBRATION FOR AUTONOMOUS SYSTEMS AND APPLICATIONS
Organization Name
Inventor(s)
Ayon Sen of Santa Clara CA (US)
Cheng-Chieh Yang of Seattle WA (US)
Yue Wu of Mountain View CA (US)
SENSOR CALIBRATION FOR AUTONOMOUS SYSTEMS AND APPLICATIONS - A simplified explanation of the abstract
This abstract first appeared for US patent application 18166118 titled 'SENSOR CALIBRATION FOR AUTONOMOUS SYSTEMS AND APPLICATIONS
Simplified Explanation
The abstract describes a patent application related to sensor configuration for autonomous or semi-autonomous systems using image feature correspondences between camera images to calibrate image sensors with LiDAR sensors.
- Explanation of the patent:
* The patent describes systems and methods that use image feature correspondences between camera images to calibrate image sensors with LiDAR sensors and/or another image sensor. * An optimization problem is constructed to minimize a geometric loss function that encodes the notion that corresponding image features are views of the same point on a locally planar surface constructed from LiDAR data. * The calibration process removes structure estimation from the optimization problem.
- Potential Applications
This technology can be applied in autonomous vehicles, robotics, surveillance systems, and augmented reality devices.
- Problems Solved
1. Accurate calibration of image sensors with LiDAR sensors. 2. Removal of structure estimation from the optimization problem.
- Benefits
1. Improved accuracy in sensor calibration. 2. Enhanced performance of autonomous or semi-autonomous systems. 3. Simplified calibration process.
- Potential Commercial Applications
- Optimizing Sensor Calibration for Autonomous Systems
- Potential Commercial Applications
- Possible Prior Art
There may be prior art related to sensor calibration techniques using image feature correspondences, but the specific method described in this patent application may be novel.
- Unanswered Questions
- How does this technology handle variations in environmental conditions that may affect sensor calibration?
This article does not provide details on how the system adapts to changing environmental conditions that could impact sensor calibration.
- Are there any limitations to the size or complexity of the locally planar surface that can be constructed from LiDAR data?
The article does not address any potential limitations regarding the size or complexity of the locally planar surface constructed from LiDAR data.
Original Abstract Submitted
In various examples, sensor configuration for autonomous or semi-autonomous systems and applications is described. Systems and methods are disclosed that may use image feature correspondences between camera images along with an assumption that image features are locally planar to determine parameters for calibrating an image sensor with a LiDAR sensor and/or another image sensor. In some examples, an optimization problem is constructed that attempts to minimize a geometric loss function, where the geometric loss function encodes the notion that corresponding image features are views of a same point on a locally planar surface (e.g., a surfel or mesh) that is constructed from LiDAR data generated using a LiDAR sensor. In some examples, performing such processes to determine the calibration parameters may remove structure estimation from the optimization problem.