Object detection using image alignment for autonomous machine applications

This invention describes a way for autonomous machines to spot objects on a road. It takes two camera images, aligns them perfectly, and then compares the pixels to find where things have moved or changed between the images. By grouping these differences and drawing boxes around them, the system can identify objects.

Why it matters: Filed in 2024, the continuous refinement of deep learning models (CNNs) and training methodologies for autonomous driving since then could offer more robust and efficient ways to implement this geometric object detection.

Status: Not in forceListed as no longer active. The specific reason is not in the record we hold.
How hard to build: SpecializedHeavy software system, computer vision algorithms

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