Object detection using skewed polygons suitable for parking space detection

This invention describes a computer program that uses sensor data, like camera images, to precisely identify and outline specific areas, such as parking spaces. It works by training a machine learning model to find the exact corner points of a tilted or distorted shape that defines the area, and can also indicate where the entrance to that area might be.

Why it matters: The rapid advancements in object detection models, particularly those focusing on precise keypoint or polygon regression rather than just bounding boxes, have continued since 2024. This could offer more robust and accurate solutions for delineating complex shapes like skewed parking spaces with less custom development.

Status: Not in forceListed as no longer active. The specific reason is not in the record we hold.
How hard to build: SpecializedMachine learning software development

3 AI reinvention directions for this patent

See all three

AI gives you a few directions you could take this. Pick one, and we check whether your version is different enough to patent, then write the filing.

Reinvent this with AI

Where this one came from

Every morning we go through millions of abandoned patents and pick out 15 worth your time. This was one of today’s.

This one

+10