Abstract
Feature detection, description, and matching are crucial steps for many computer vision algorithms. These steps rely on feature descriptors to match image features across sets of images. Previous work has shown that our SYnthetic BAsis (SYBA) feature descriptor can offer superior performance to other binary descriptors. This paper focused on various optimizations and hardware implementation of the newer and optimized version. The hardware implementation on a field-programmable gate array (FPGA) is a high-throughput low-latency solution which is critical for applications such as high-speed object detection and tracking, stereo vision, visual odometry, structure from motion, and optical flow. We compared our solution to other hardware designs of binary descriptors. We demonstrated that our implementation of SYBA as a feature descriptor in hardware offered superior image feature matching performance and used fewer resources than most binary feature descriptor implementations.
Highlights
Image processing for humans involves using sight and mentally breaking down what is seen to give it meaning
We show that SYnthetic BAsis (SYBA) can have significantly less resource usage in field-programmable gate array (FPGA) while maintaining its feature matching accuracy
(10,049 to 5944)implementations and FF usage is on decreased systems.solution, We compare ourisdesign to other feature descriptor
Summary
Image processing for humans involves using sight and mentally breaking down what is seen to give it meaning. SIFT is well-known and uses orientation and a magnitudes-of-intensity gradient-based feature descriptor It works very well on intensity images and provides feature descriptions that are invariant to both rotation and scaling. By only storing the similarity of the FRI to each SBI, the overall matching accuracy with simplicity, relatively low resource storage size computational is reduced dramatically It makes comparisons when searchingrequirements, for feature matchesand a hardware easier. Has previously been compared with two well-known binary shows a summarized of work previously performed in Reference [11], which compares SYBA descriptors, BRIEF-32 and rBRIEF, and has been shown to produce better feature matching results to various other[11]. Version of previous work from Reference [11]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
