Implementation of Generalized Hough transform for autonomous inspection systems
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Generalized Hough transform (GHT) is well-known algorithm for image registration and it is applicable for various applications. This paper presents a hardware design of autonomous inspection system based on GHT algorithm. We implement our modified GHT with Zynq7020 FPGA, and both hardware and software are co-designed with Vivado toolkit. In addition, our system is also designed in ASIC. In the experimental results, we achieve 65 fps with FPGA and 130 fps with ASIC design when the input is VGA images. Our chip design requires 317.4K gates while consuming 135.9mW.
Abstract
Generalized Hough transform (GHT) is well-known algorithm for image registration and it is applicable for various applications. This paper presents a hardware design of autonomous inspection system based on GHT algorithm. We implement our modified GHT with Zynq7020 FPGA, and both hardware and software are co-designed with Vivado toolkit. In addition, our system is also designed in ASIC. In the experimental results, we achieve 65 fps with FPGA and 130 fps with ASIC design when the input is VGA images. Our chip design requires 317.4K gates while consuming 135.9mW.
참고문헌 (12)
- D. H. Ballard, "Generalizing the Hough transform to detect arbitrary shapes", Pattern Recognition, 13(2), pp.111~122 (1981)
- Z. Wang, "Super-Resolving IC Images with an Edge-Preserving Bayesian Framework", IEEE Trans. Semicond. Manuf, 27(1), pp.118~130 (2015)
- J. Xu, "Automatic detection of inshore ships in high-resolution remote sensing images using robust invariant generalized Hough transform", IEEE Geosci. Remote Sens. Lett., 11(12), pp.2070~2074 (2014)
- N. S. Vu, "Enhanced patterns of oriented edge magnitudes for face recognition and image matching", IEEE Trans. Image Process., 21(3), pp.1352~1365 (2012)
- D. G. Lowe, "Distinctive image features from scale-invariant keypoints", Int. J. Comput. Vision, 60(2), pp.91~110 (2004)
- A. J. Crispin, "Automated inspection of PCB components using a genetic algorithm template-matching approach", Int. J. Adv. Manuf. Technol., 35(3), pp.293~300 (2007)
- J. Canny, "A computational approach to edge detection", IEEE Trans. Pattern Anal. Mach. Intell., 8(6), pp.679~698 (1986)
- S. R. Geninatti, "FPGA implementation of the generalized Hough transform", Proc. Int. Conf. Reconfigurable Computing and FPGAs, pp.172~177 (2009)
- R. Strzodka, "A graphics hardware implementation of the generalized hough transform for fast object recognition, scale, and 3D pose detection", Proc. 12th Int. Conf. Image Anal. Process, pp.188~193 (2003)
- Guil N., "Bidimensional shape detection using an invariant approach", Pattern Recognition, 32, pp.1025~1038 (1999)
- R. K. K. Yip, "Modification of hough transform for circles and ellipses detection using a 2-dimensional array", Pattern Recognition, 25(9), pp.1007~1022 (1992)
- Mun, J., "2D template matching for automated inspection using generalized hough transform", Research and Development (SCOReD), 2017 IEEE 15th Student Conference, pp.461~466 (2017), IEEE