实时动态坏点检测校正算法的实现  

Realization of real-time bad spot detection and correction algorithm

作　　者：赵冬青[1] 王达 上官鹏 储成群[1] ZHAO Dongqing;WANG Da;SHANGGUAN Peng;CHU Chengqun(Key Laboratory of Instrumentation Science&Dynamic Measurement,Ministry of Education,North University of China,Taiyuan 030051,China;Beijing Institute of Control and Electronic Technology,Bejing 100032,China)

机构地区：[1]中北大学电子测试技术国家重点实验室,太原030051 [2]北京控制与电子技术研究所,北京100032

出　　处：《激光杂志》2022年第6期59-64,共6页Laser Journal

摘　　要：针对在工业相机的制造以及使用的过程中,因各种因素造成图像出现坏点的现象,提出了一种快速的动态坏点检测校正算法。算法首先通过缩小检测半径并设定动态阈值的方法来提高坏点的检测准确率,减少误检测数量;然后采用坏点周围多子均值替代坏点值的办法来有效实现对图像边缘的保护;最后利用FPGA并行性的优势实现坏点检测校正算法的实时性设计。实验结果表明,与传统算法相比,该算法能够实时有效消除坏点,较好地保护图像边缘的完整性且坏点误检数目相对较少。In the process of manufacturing and industrial camera using, a fast bad point detection correction algorithm is proposed to improve its detection accuracy by narrowing the detection radius and setting dynamic judgment threshold, reducing the number of error detection firstly. Then, using the method of replacing bad point values with multi-sub mean around bad points to effectively realize the protection of image edge effect. The experimental results show that compared with existing algorithm, the algorithm can effectively eliminate the bad points in real time, protect the integrity of the image edge, and the number of bad point errors is relatively small.

关 键 词：图像坏点 坏点检测 坏点校正 FPGA 工业相机 

分 类 号：TP394.1[自动化与计算机技术—计算机应用技术] TH691.9[自动化与计算机技术—计算机科学与技术]