基于SV-DPI的图像坏元修正FPGA自动化验证

李艳龙; 杨琪; 王雪峰

基于SV-DPI的图像坏元修正FPGA自动化验证

西安微电子技术研究所，陕西西安 710065

详细信息

作者简介:
李艳龙（1988-），男，吉林白城人，工程师，硕士。研究方向为FPGA测试、测试自动化技术。E-mail：470968999@qq.com

中图分类号: TP306
计量
- 文章访问数: 225
- HTML全文浏览量: 97
- PDF下载量: 33
- 被引次数: 0
出版历程
- 收稿日期: 2020-04-20
- 修回日期: 2020-06-21
- 刊出日期: 2020-12-26

Automatic Verification of Field Programmable Gate Arrays for Dead Pixel Correction

Xi'an Microelectronic Technique Institute, Xi'an 710065, China

摘要

摘要: 为实现红外图像坏元修正FPGA（field programmable gate array）的快速验证，提高测试覆盖性，设计了基于SV-DPI（SystemVerilog-direct programming interface）的FPGA自动化验证平台。采用DPI（direct programming interface）编程接口技术，实现了SystemVerilog平台调用C++编程语言，构建了针对红外图像坏元数据的生成和检测修正模型，建立了两种语言在事务级（transaction level）模型的通信。结果表明相对于传统验证方法，该平台结构简单，可以快速实现激励产生、参考模型构建、测试结果自动比对等功能，实现了红外图像坏元检测与修正FPGA的自动化测试，功能覆盖率达到100%，有效缩短FPGA测试平台搭建和调试周期，提高了测试效率和测试质量。
- 自动化测试 /
- FPGA验证 /
- 红外图像坏元修正 /
- 验证平台
Abstract: To accelerate the simulation speed and improve the coverage of verification for a field programmable gate array (FPGA) implemented with dead pixel correction of an infrared image, an FPGA automatic verification platform based on SystemVerilog-Direct programming interface(SV-DPI) was designed. Using DPI programming interface technology, the C++ programming language was invoked by the SV platform. A generator and correction model for dead pixel data of infrared images was built. This established a communication between two languages on the transaction level. The results show that, compared with the traditional verification method, the proposed platform is simple in structure and can quickly generate a test vector, construct a reference model, and check results automatically. It realizes automated verification for an FPGA implemented with dead pixel detection and correction of an infrared image. The function coverage can reach 100%. It effectively shortens the period of construction and debugging for the FPGA verification platform and improves the efficiency and quality of verification.
- automated testing /
- FPGA verification /
- dead pixel correction of infrared image /
- verification platform

HTML全文

图 1 验证平台整体结构

Figure 1. Structure of the verification platform

下载: 全尺寸图片幻灯片

图 2 图像生成逻辑框图

Figure 2. Logical block diagram of image generation

下载: 全尺寸图片幻灯片

图 3 图像数据生成程序结构图

Figure 3. Structure chart of image data generation program

下载: 全尺寸图片幻灯片

图 4 参考模型逻辑流程图

Figure 4. Logic flow chart of reference model

下载: 全尺寸图片幻灯片

图 5 快速中值滤波

Figure 5. Median filtering

下载: 全尺寸图片幻灯片

表 1 测试用例及执行情况表

Table 1. Table of test case and execution

No.	Case type	Test case	Desired result	Execution result	Function coverage
1	Normal	The current pixel value is between the maximum and minimum values in the 3×3 neighborhood	The current pixel is not replaced and no correction is made	Effectively executed and passed	100%
2	Boundary	The current pixel value is greater than the maximum value in the 3×3 neighborhood, and the difference from the maximum value is less than or equal to the set threshold	The current pixel is not replaced and no correction is made	Effectively executed and passed
3	Normal	The current pixel value is greater than the maximum value in the 3×3 neighborhood, and the difference from the maximum value is greater than the set threshold	The current pixel value is replaced by the median value in the neighborhood. The correction is implemented.	Effectively executed and passed
4	Boundary	The current pixel value is less than the minimum value in the 3×3 neighborhood, and the difference from the minimum value is less than or equal to the set threshold	The current pixel is not replaced and no correction is made	Effectively executed and passed
5	Normal	The current pixel value is less than the minimum value in the 3×3 neighborhood, and the difference from the minimum value is greater than the set threshold	The current pixel value is replaced by the median value in the neighborhood. The correction is implemented.	Effectively executed and passed
6	Special location	The bad elements are on the four edges	The current pixel is not replaced and no correction is made	Effectively executed and passed
7	Special location	There are more than three bad elements in the image, and the positions of the bad elements are continuous	No correction	Effectively executed and passed
8	Performance	The number of bad elements accounts for 60% of an image, and the positions of bad elements are evenly dispersed	All bad elements are corrected	Effectively executed and passed
9	Normal	Input bad elements one by one, traverse the whole frame of image	Every bad element is corrected	Effectively executed and passed
10	Recovery	First input an image with bad elements, and then input an image without bad elements	The bad element of the first frame of image is corrected correctly, and the second frame of image is output correctly without error correction	Effectively executed and passed

下载: 导出CSV

表 2 搭建平台时间对比

Table 2. Comparison of platform building time

Types of platforms	Time consuming to build a platform/d
Pure SystemVerilog verification platform	3
UVM verification platform	3.7
The automated verification platform designed in this article	1.6

下载: 导出CSV

参考文献(9)

[1]	白俊奇, 蒋怡亮, 赵春光, 等.红外焦平面阵列探测器盲元检测算法研究[J]. 红外技术, 2011, 33(4): 233-235, 240. doi: 10.3969/j.issn.1001-8891.2011.04.011 BAI Junqi, JIANG Yiliang, ZHAO Chunguang, et al. Blind-pixel detection algorithm for infrared focal plane array detector[J]. Infrared Technology, 2011, 33(4): 233-235, 240. doi: 10.3969/j.issn.1001-8891.2011.04.011
[2]	李炎冰, 梁少峰, 陈洪亮, 等.红外焦平面阵列坏元检测算法[J]. 电光与控制, 2015, 22(3): 69-71. doi: 10.3969/j.issn.1671-637X.2015.03.015 LI Yanbing, LIANG Shaofeng, CHEN Hongliang, et al. A bad-pixel detection algorithm for infrared focal plane array[J]. Electronics Optics & Control, 2015, 22(3): 69-71. doi: 10.3969/j.issn.1671-637X.2015.03.015
[3]	胡云生, 胡越黎, 燕明, 等.一种图像坏点检测及修正算法[J]. 上海大学学报:自然科学版, 2018, 24(5): 755-762. http://www.cnki.com.cn/Article/CJFDTotal-SDXZ201805009.htm HU Yunsheng, HU Yueli, YAN Ming, et al. Detection and correction of dead pixels in an image[J]. Journal of Shanghai University: Natrual Science, 2018, 24(5): 755-762. http://www.cnki.com.cn/Article/CJFDTotal-SDXZ201805009.htm
[4]	李雷鸣, 张焕春, 张波.一种基于FPGA的图像中值滤波器的硬件实现[J]. 电子工程师, 2004(2): 48-50. doi: 10.3969/j.issn.1674-4888.2004.02.015 LI Leiming, ZHANG Huanchun, ZHANG Bo. The realization of image median filter based on FPGA[J]. Electronic Engineer, 2004(2): 48-50. doi: 10.3969/j.issn.1674-4888.2004.02.015
[5]	周珊, 杨雅雯, 王金波.航天高可靠FPGA测试技术研究[J]. 计算机技术与发展, 2017, 27(3): 1-5. http://d.wanfangdata.com.cn/Periodical/wjfz201703001 ZHOU Shan, YANG Yawen, WANG Jinbo. Research on high reliable FPGA test technology on space flight[J]. Computer Technology and Development, 2017, 27(3): 1-5. http://d.wanfangdata.com.cn/Periodical/wjfz201703001
[6]	朱伟杰, 阳徽, 费亚男, 等. FPGA功能验证自动化技术研究与实践[J]. 航天控制, 2017, 35(2): 72-77, 98. http://www.cqvip.com/QK/90122X/20172/72847590504849554850484951.html ZHU Weijie, YANG Hui, FEI Yanan, et al. Research and practice of automation technology on FPGA function verification[J]. Aerospace Control, 2017, 35(2): 72-77, 98. http://www.cqvip.com/QK/90122X/20172/72847590504849554850484951.html
[7]	习建博, 朱鹏, 崔留争.基于UVM方法的FPGA验证技术[J]. 电子科学技术, 2016, 3(3): 204-207. http://d.wanfangdata.com.cn/Periodical/dzkxjs201603003 XI Jianbo, ZHU Peng, CUI Liuzheng. FPGA verification technology based on UVM[J]. Electronic Science & Technology, 2016, 3(3): 204-207. http://d.wanfangdata.com.cn/Periodical/dzkxjs201603003
[8]	克里斯·斯皮尔. SystemVerilog系统验证[M]. 2版: 张春等译.北京: 科学出版社, 2009. Chris Spear. SystemVerilog for Verification[M]. 2nd Edition: Translated by ZHANG Chun, et al. Beijing: Science Press, 2009.
[9]	韩团军.快速中值滤波算法研究及其FPGA硬件实现[J]. 电子器件, 2017, 40(3): 697-701. doi: 10.3969/j.issn.1005-9490.2017.03.036 HAN Tuanjun. Research of fast median filtering algorithm and hardware implementation based on FPGA[J]. Chinese Journal of Electron Devices, 2017, 40(3): 697-701. doi: 10.3969/j.issn.1005-9490.2017.03.036