17821627. STEREOVISION ANNOTATION TOOL simplified abstract (QUALCOMM Incorporated)

From WikiPatents
Jump to navigation Jump to search

STEREOVISION ANNOTATION TOOL

Organization Name

QUALCOMM Incorporated

Inventor(s)

Gary Franklin Gimenez of Bordeaux (FR)

Ophir Paz of Floirac (FR)

STEREOVISION ANNOTATION TOOL - A simplified explanation of the abstract

This abstract first appeared for US patent application 17821627 titled 'STEREOVISION ANNOTATION TOOL

Simplified Explanation

- Techniques for generating three-dimensionally coherent training data for image-detection machine learning models - Receiving images of an object from different perspectives - Receiving user input identifying a location on the object in one image - Displaying possible locations on the object in the other image based on user input - Generating training data for machine learning model based on user input

Potential Applications

- Improving accuracy of image-detection machine learning models - Enhancing object recognition in various industries such as autonomous vehicles, security systems, and medical imaging

Problems Solved

- Generating coherent training data for machine learning models - Improving object recognition in images with different perspectives

Benefits

- Increased accuracy of machine learning models - Enhanced object recognition capabilities - Improved performance in various industries utilizing image-detection technology


Original Abstract Submitted

Certain aspects of the present disclosure provide techniques for generating three-dimensionally coherent training data for image-detection machine learning models. Embodiments include receiving a first image of an object from a first perspective and a second image of the object from a second perspective. Embodiments include receiving user input identifying a location in the first image corresponding to a point on the object. Embodiments include displaying a range of possible locations in the second image corresponding to the point on the object based on the location in the first image. Embodiments include generating training data for a machine learning model based on updated user input associated with the range of possible locations.