Hazy Particle Map 기반 실시간 처리 가능한 자동화 안개제거방법의 하드웨어 구현
Hardware implementation of automated haze removal method capable of real-time processing based on Hazy Particle Map
1
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
최근 자율주행 자동차를 구현하기 위해 카메라 영상을 통해 객체 및 차선을 인식하여 자율주행하는 영상처리 기술이 연구되고 있다. 안개는 카메라 촬영 영상의 가시성을 떨어뜨리기 때문에 자율주행 자동차 오작동의 원인이 된다. 이를 해결하기 위해 카메라에실시간 처리가 가능한 안개 제거 기능을 적용하는 것이 필요하다. 따라서 본 논문에서는 성능이 우수한 Sim의 안개 제거방법을 실시간 처리가 가능한 하드웨어로 구현한다. 제안하는 하드웨어는 Verilog HDL을 사용하여 설계하였고, Xilinx사의 xc7z045-2ffg900을 Target device로 설정하여 FPGA 구현하였다. Xilinx Vivado 프로그램을 이용한 논리합성 결과 4K(4096×2160) 고해상도 환경에서 최대 동작 주파수 276.932MHz, 최대 처리 속도 31.279fps를 가짐으로써 실시간 처리 기준을 만족한다.
Abstract
Recently, image processing technology for autonomous driving by recognizing objects and lanes through cameraimages to realize autonomous vehicles is being studied. Haze reduces the visibility of images captured by thecamera and causes malfunctions of autonomous vehicles. To solve this, it is necessary to apply the haze removalfunction that can be processed in real time to the camera. Therefore, in this paper, the fog removal method ofSim with excellent performance is implemented with hardware capable of real-time processing. The proposedhardware was designed using Verilog HDL, and FPGA was implemented by setting Xilinx’s xc7z045-2ffg900 as thetarget device. As a result of logic synthesis using Xilinx Vivado program, it has a maximum operating frequencyof 276.932MHz and a maximum processing speed of 31.279fps in a 4K (4096×2160) high-resolution environment,thus satisfying the real-time processing standard.
참고문헌 (16)
- Dat Ngo, "A 4K-Capable FPGA Implementation of Single Image Haze Removal Using Hazy Particle Maps", Applied Sciences, 9(17), pp.3443~3457 (2019), MDPI AG[DOI]
- D. Ngo, "Adapting a Dehazing System to Haze Conditions by Piece-Wisely Linearizing a Depth Estimator", Applied Sciences, 22(5), pp.1957~1981 (2022)[DOI]
- D. Ngo, "Single Image Haze Removal from Image Enhancement Perspective for Real-Time Vision-Based Systems", Sensors, 20(18), pp.5170~5190 (2020)[DOI]
- Kaiming He, "Single Image Haze Removal Using Dark Channel Prior", IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(12), pp.2341~2353 (2011), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- A. Levin, "A Closed-Form Solution to Natural Image Matting", IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(2), pp.228~242 (2008), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Geun-Jun KIM, "Single Image Haze Removal Using Hazy Particle Maps", IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, E101-A(11), pp.1999~2002 (2018), Institute of Electronics, Information and Communications Engineers (IEICE)[DOI]
- Dat Ngo, "Haziness Degree Evaluator: A Knowledge-Driven Approach for Haze Density Estimation", Sensors, 21(11), pp.3896~3927 (2021), MDPI AG[DOI]
- 심휘보, "Haziness Degree Evaluator를 적용한 Hazy Particle Map 기반 자동화 안개 제거 방법", 멀티미디어학회논문지, 25(9), pp.1266~1272 (2022), 한국멀티미디어학회
- Srinivasa G. Narasimhan, "Vision and the Atmosphere", International Journal of Computer Vision, 48(3), pp.233~254 (2002), Springer Science and Business Media LLC[DOI]
- Jean-Philippe Tarel, "Fast visibility restoration from a single color or gray level image", 2009 IEEE 12th International Conference on Computer Vision, pp.2201~2208 (2009), IEEE
- 조호상, "Color Image Enhancement Based on Adaptive Nonlinear Curves of Luminance Features", JOURNAL OF SEMICONDUCTOR TECHNOLOGY AND SCIENCE, 15(1), pp.60~67 (2015), 대한전자공학회
- Z. Wang, "Image Quality Assessment: From Error Visibility to Structural Similarity", IEEE Transactions on Image Processing, 13(4), pp.600~612 (2004), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Lin Zhang, "FSIM: A Feature Similarity Index for Image Quality Assessment", IEEE Transactions on Image Processing, 20(8), pp.2378~2386 (2011), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Hojatollah Yeganeh, "Objective Quality Assessment of Tone-Mapped Images", IEEE Transactions on Image Processing, 22(2), pp.657~667 (2013), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- C. Ancuti, "I-HAZE : A Dehazing Benchmark with Real Hazyand Haze-Free Indoor Images", Advanced Concepts for Intelligent Vision Systems, 620(631), pp.620~631 (2018)[DOI]
- C. Ancuti, "D-HAZY : A dataset to evaluate quantitatively dehazing algorithms", Proceedings of the IEEE International Conference on Image Processing (ICIP), pp.2226~2230 (2016)