FPGA-Based Image Processing System for Target Locating

In this paper, we proposed the design of an FPGA-based image processing system for target locating. The locating mechanism is based on the feature line segments of target’s image. The system processes the target’s image sequence, finds and matches feature points on each image, and uses the feature points to calculate the length of feature line segments for target locating. We implemented the Speeded Up Robust Features (SURF) algorithm on FPGA hardware to extract feature points. The system has a core CPU for control and part of the mathematical computation. Custom-designed logic circuit modules are used to accelerate the feature point extraction. The system’s software is designed to work with parallel and pipeline operation. The performance test shows that the system is capable of real-time processing.

[1]  Libor Preucil,et al.  FPGA based Speeded Up Robust Features , 2009, 2009 IEEE International Conference on Technologies for Practical Robot Applications.

[2]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..

[3]  王荻 Wang Di,et al.  A Passive Ranging System Based on Image Sequence From Single Lens and the Respective Imaging Direction along with Its Performance , 2011 .

[4]  Christopher Hunt,et al.  Notes on the OpenSURF Library , 2009 .

[5]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[6]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[7]  Shang-qian Liu,et al.  A real time image sequence processing algorithm for target ranging , 2007, International Congress on High-Speed Imaging and Photonics.

[8]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[9]  Gundolf Kiefer,et al.  Flex-SURF: A Flexible Architecture for FPGA-Based Robust Feature Extraction for Optical Tracking Systems , 2010, 2010 International Conference on Reconfigurable Computing and FPGAs.