Name
Title | ||
|---|---|---|
The Nature-Inspired BASIS Feature Descriptor for UAV Imagery and Its Hardware Implementation |
Abstract | ||
|---|---|---|
This paper presents a feature descriptor well suited for limited-resource applications such as an unmanned aerial vehicle embedded systems, small microprocessors, and small low-power field programmable gate array (FPGA) fabric. The basis sparse-coding inspired similarity (BASIS) descriptor utilizes sparse coding to create dictionary images that model the regions in the human visual cortex. Due to the reduced amount of computation required for computing BASIS descriptors, reduced descriptor size, and the ability to create the descriptors without the use of a floating point, this approach is an excellent candidate for FPGA hardware implementation. The bit-level-accurate BASIS descriptor was tested on a dataset of real aerial images with the task of calculating a frame-to-frame homography and compared to software versions of scale-invariant feature transform (SIFT) and speeded-up robust features (SURF). Experimental results show that the BASIS descriptor outperforms SIFT and performs comparably to SURF on frame-to-frame aerial feature point matching. BASIS descriptors require less memory storage than other descriptors and can be computed entirely in hardware, allowing the descriptor to operate at real-time frame rates on a low-power embedded platform such as an FPGA. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/TCSVT.2012.2223631 | Circuits and Systems for Video Technology, IEEE Transactions |
Keywords | Field | DocType |
autonomous aerial vehicles,embedded systems,feature extraction,field programmable gate arrays,image coding,image matching,low-power electronics,robot vision,FPGA fabric,FPGA hardware implementation,UAV imagery hardware implementation,basis sparse coding inspired similarity descriptor,bit-level-accurate BASIS descriptor testing,frame-to-frame aerial feature point matching,frame-to-frame homography,human visual cortex,limited-resource applications,low-power embedded platform,memory storage,microprocessors,nature-inspired BASIS feature descriptor,real aerial images,small low-power field programmable gate array fabric,unmanned aerial vehicle embedded systems,Computer vision,feature description,feature descriptor,feature detection,feature detector,sparse coding | Scale-invariant feature transform,Computer science,Floating point,Homography,Artificial intelligence,Computer hardware,Computer vision,Pattern recognition,GLOH,Neural coding,Feature (computer vision),Field-programmable gate array,Frame rate | Journal |
Volume | Issue | ISSN |
23 | 5 | 1051-8215 |
Citations | PageRank | References |
8 | 0.50 | 25 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Spencer G. Fowers | 1 | 38 | 4.74 |
| Dah-Jye Lee | 2 | 422 | 42.05 |
| Dan Ventura | 3 | 31 | 4.39 |
| James K. Archibald | 4 | 632 | 161.01 |