一种基于FPGA非均匀光照图像分割方法  

An Image Segmentation Method Based on FPGA in the Condition of Non-uniform Illumination

作　　者：杨勇[1,2] 范胜利[2] 张芸蕾 王一刚[2] 

机构地区：[1]太原科技大学电子信息工程学院,太原030024 [2]浙江大学宁波理工学院信息科学与工程学院,浙江宁波315100

出　　处：《太原科技大学学报》2014年第6期419-423,共5页Journal of Taiyuan University of Science and Technology

摘　　要：针对非均匀光照条件下图像的分割问题,提出一种基于FPGA的实时图像分割方法。得到了一种非均匀光照下分割效果较好的方法。首先,使用图像传感器采集原始的图像数据,然后进行sobel边缘检测,最后对其进行Bernsen局部二值化得到分割图像。本方法使用FPGA来对图像进行高速采集和并行处理,实时完成图像边缘检测及局部二值化。经现场调试证明本方法可以有效分割图像,使其目标更加突出,从而改善了非均匀光照对图像分割质量带来的影响,并具有良好的实时性。Aiming at the problem of image segmentation in the condition of non-uniform illumination, a real-time image capture and segmentation method based on FPGA is proposed, which achieved a much better result in the condition. Firstly, the image sensor captures original image data. Secondly, the edge of the image is detected by so- bel algorithm and the outstanding subject image is achieved. Thirdly, the Bemsen local binarization is applied to process the subject image, and then the segmented image is obtained. This method adopts FPGA to capture image quickly and process image data parallel. Besides, image edge detection and local binarization are completed in real time. The result shows that the method can make the subject image more outstanding and improve the quality of im- age segmentation greatly under the condition of non-uniform illumination. In addition, the real-timing of the method is good.

关 键 词：非均匀光照 边缘检测 局部二值化 FPGA 图像分割 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]