군사용 적외선 영상의 안정화 성능 개선 및 Zynq SoC 구현
Improve Stability of Military Infrared Image and Implement Zynq SoC
1
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
Military camera equipment has a problem that observability is inferior due to various shaking factors. In this paper, we propose an image stabilization algorithm considering performance and execution time to solve this problem and implemented it in Zynq SoC. We stabilized both the simple shaking in the fixed observation position and the sudden shaking in the moving observation position. The feature of the input image is extracted by the Sobel edge algorithm, the subblock with the large edge data is selected, and the motion vector, which is the compensation reference, is calculated through template matching using the 3-step search algorithm of the region of interest. In addition, the proposed algorithm can distinguish the shaking caused by the simple shaking and the movement by using the Kalman filter, and the stabilized image can be obtained by minimizing the loss of image information. To demonstrate the effectiveness of the proposed algorithm, experiments on various images were performed. In comparison, PSNR is improved in the range of 2.6725~3.1629 (dB) and image loss is reduced from 41% to 15%. On the other hand, we implemented the hardware- software integrated design using HLS of Xilinx SDSoC tool and confirmed that it operates at 32 fps on the Zynq board, and realized SoC that operates with real-time processing.
Abstract
Military camera equipment has a problem that observability is inferior due to various shaking factors. In this paper, we propose an image stabilization algorithm considering performance and execution time to solve this problem and implemented it in Zynq SoC. We stabilized both the simple shaking in the fixed observation position and the sudden shaking in the moving observation position. The feature of the input image is extracted by the Sobel edge algorithm, the subblock with the large edge data is selected, and the motion vector, which is the compensation reference, is calculated through template matching using the 3-step search algorithm of the region of interest. In addition, the proposed algorithm can distinguish the shaking caused by the simple shaking and the movement by using the Kalman filter, and the stabilized image can be obtained by minimizing the loss of image information. To demonstrate the effectiveness of the proposed algorithm, experiments on various images were performed. In comparison, PSNR is improved in the range of 2.6725~3.1629 (dB) and image loss is reduced from 41% to 15%. On the other hand, we implemented the hardware- software integrated design using HLS of Xilinx SDSoC tool and confirmed that it operates at 32 fps on the Zynq board, and realized SoC that operates with real-time processing.
참고문헌 (6)
- 유신, "차량용 비전 시스템을 위한 영상 안정화에 관한 연구", 한국정보통신학회논문지, 15(4), pp.957~964 (2011), 한국정보통신학회
- W. Yang, "A Real-time Gray Projection Algorithm for Electronic Image Stabilization", Proceedings of SPIE International Symposium on Photoelectronic Detection and Imaging, 8193, pp.81932G~ (2011)
- 김종호, "휴대용 열 영상 관측 장비를 위한 전자적 영상 안정화", 한국군사과학기술학회지, 19(3), pp.288~293 (2016), 한국군사과학기술학회[DOI]
- C.H. Park, "Using Motion Estimation Video Stabilization for Thermal Imaginary Video" (2015)
- J.N. Kim, "A Fast Three-step Search Algorithm With Minimum Checking Points Using Unimodal Error Surface Assumption", IEEE Transactions on consumer Electronics, 44(3), pp.638~648 (1998)[DOI]
- P. Coussy, "High-level Synthesis" (2010), Springer