基于计算机视觉的座舱仪表识别检测方法

来源期刊:中南大学学报(自然科学版)2014年第5期

论文作者:何林远 毕笃彦 熊磊 周理

文章页码:1469 - 1476

关键词:计算机视觉;中值滤波;类间方差法;交叉视觉皮质模型;最大梯度下降法

Key words:computer vision; median-value filter; Otsu; ICM; max gradient search method

摘    要:在简要介绍座舱仪表及其常用识别检测方法的基础上,提出一种基于计算机视觉的座舱仪表识别检测的方法。阐述过程中的几个关键环节及所用到的图像处理算法。采用同态滤波和自适应中值滤波相结合的方法来改善图像效果,然后用改进的类间方差法(Otsu)获取仪表的二值图像。利用改进后交叉皮质视觉模型对仪表的边缘进行提取,并结合骨架来提取指针,最终通过最大梯度下降法得到指针的准确读数。实验结果表明:该方法可快速获取仪表指针读数,且能并行处理多个仪表。与传统的Hough变换、最小二乘法等相比,该算法在保证精度准度的基础上,大幅提高了处理运算的速率。

Abstract: Based on the theory of cockpit meters and standard recognize technique, a new recognizing technique that is based on computer vision was proposed. Some key points and the image processing methods were discussed. The homomorphic filter and self-adaption median-value filter were used to perfect the result of image, and the improved Otsu was used to obtain binary image. The improved intersect cortical model (ICM) was used to receive edge of meters, and the pointer was picked up with combining skeleton. Finally, by the max gradient search method, the exact value was obtained. The result shows that this method can quickly get the number of meters, and process the parallel data. Compared with the traditional Hough transform and the least squares fit methods, this method can quicken the recognition process of the pointer and ensure the accuracy and standard of method.

相关论文

  • 暂无!

相关知识点

  • 暂无!

有色金属在线官网  |   会议  |   在线投稿  |   购买纸书  |   科技图书馆

中南大学出版社 技术支持 版权声明   电话:0731-88830515 88830516   传真:0731-88710482   Email:administrator@cnnmol.com

互联网出版许可证:(署)网出证(京)字第342号   京ICP备17050991号-6      京公网安备11010802042557号