SURF Algorithm in FPGA: a Novel Architecture for High Demanding Industrial Applications

Provided by: edaa
Topic: Hardware
Format: PDF
Object recognition and tracking are getting more and more appealing for many embedded applications, from motion-based recognition and automated surveillance, up to vehicle and even spacecraft navigation. To detect an object and track it, interesting features must be identified, such as colors, edges, textures etc. Among all, interest points, characterized by high local variations of the image intensity and high repeatability, are growing in use because they are characterized by an intrinsic robustness to image transformations, like scale, rotation, illumination and viewpoint changes.

Find By Topic