为了提高匀速直线运动模糊图像的运动方向检测精度,提出一种基于频谱预处理的模糊运动方向鉴别改进算法。首先,通过对模糊图像的频谱图执行两次傅里叶对数变换,实现频谱图的亮条细化处理;然后,以亮条细化后的频谱图为研究对象,采用滑动邻域操作实施频谱图的二值化处理,剔除图像中的噪声和十字亮线,得到频谱图的预处理图像;最后,对预处理图像执行Radon变换,检测图像中的直线成分,并将检测结果映射为模糊图像的运动方向。实验数据显示,在不同模糊尺度和运动方向环境下,本文算法始终能够将运动方向的检测误差控制在0.5°的有效范围之内;实验结果表明,本文算法的运动方向检测精度优于其他同类的算法。

In order to improve the detection quality of direction of the objects moving in fixed direction from blurred image, In this paper, we propose a new algorithm for detection of moving direction, which is based on the pre-processing of spectrum image. First, the spectrum image of motion-blur image is transformed twice with Fourier logarithmic to meet refinment of bright lines. Second, with the previous spectrum as input, the image is bi-value processing with slipping neighbour operation, eliminating image noise and cross bright line. Finally, the pre-processed image is performed with Radon transform, detecting image linear characteristic, and mapping the detection results into direction of the blurred image. The experimental results show as below: 1) in different fuzzy scale and direction of the environment, the proposed algorithm can always limit the movement direction detection error under 0.5°;2) our algorithm can obtain better movement direction detection than other related algorithms.