Feature Points
Feature point extraction and matching is compute and resource intensive. However, it is central to many computer vision tasks such as object tracking and SLAM. By providing onboard acceleration for these tasks, Bottlenose takes on the heavy lifting and lets the receiving hardware focus on the core applications. In this section, you will learn about:
- Feature Detection: describes the algorithms used by Bottlenose to extract feature points.
- Feature Descriptor: shows how Bottlenose generates a descriptor for each feature point.
- Feature Matching: presents how Bottlenose performs feature point matching.
Updated 10 months ago