17931238. PRIOR INFORMED POSE AND SCALE ESTIMATION simplified abstract (MICROSOFT TECHNOLOGY LICENSING, LLC)
Contents
PRIOR INFORMED POSE AND SCALE ESTIMATION
Organization Name
MICROSOFT TECHNOLOGY LICENSING, LLC
Inventor(s)
Victor M. Fragoso Rojas of Bellevue WA (US)
Gabriel Takacs of Issaquah WA (US)
PRIOR INFORMED POSE AND SCALE ESTIMATION - A simplified explanation of the abstract
This abstract first appeared for US patent application 17931238 titled 'PRIOR INFORMED POSE AND SCALE ESTIMATION
Simplified Explanation
The patent application describes a method for estimating the scale and pose of a camera system based on camera data and a scale prior parameter. The method involves calculating a cost function for a similarity transformation, where the cost is influenced by the scale prior parameter. If the cost function is below a threshold, the estimated scale and pose of the camera system are output.
- Camera system scale and pose estimation method:
- Receives camera data for a scene - Receives a scale prior parameter - Calculates cost of a cost function for a similarity transformation - Influences cost function based on scale prior parameter - Outputs estimated scale and pose if cost function is below threshold
- Potential Applications:**
- Augmented reality - Robotics - Autonomous vehicles
- Problems Solved:**
- Accurate scale and pose estimation for camera systems - Improved scene understanding - Enhanced object recognition
- Benefits:**
- Increased accuracy in camera system calibration - Improved performance in various applications - Enhanced user experience in augmented reality
- Potential Commercial Applications:**
- Camera calibration software - Robotics navigation systems - Augmented reality applications
- Possible Prior Art:**
- Existing camera calibration methods - Pose estimation algorithms
- Unanswered Questions:**
- 1. How does the method handle varying lighting conditions in the scene?**
- The patent application does not specify how the method accounts for changes in lighting that may affect the accuracy of scale and pose estimation.
- 2. What is the computational complexity of the cost function calculation?**
- The patent application does not provide information on the computational resources required to calculate the cost function for the similarity transformation.
Original Abstract Submitted
A scale and pose estimation method for a camera system is disclosed. Camera data for a scene acquired by the camera system is received. A scale prior parameter characterizing scale of the camera system is received. A cost of a cost function is calculated for a similarity transformation. The cost of the cost function is influenced at least by the scale prior parameter. Based at least on the cost function being less than a threshold cost, an estimated scale and pose of the camera system is output based on the similarity transformation.