摘要
介绍了一种基于TMS320DM642内河船舶目标检测系统的设计与实现。首先讨论了船舶检测系统的硬件设计,该系统采用新一代数字多媒体处理器TMS320DM642。它具有极强的处理能力,可以保证图像信息处理的实时性和准确性。然后在硬件平台的基础上给出了其软件实现,提出了基于形态学重构的内河船舶目标检测算法。该算法先对原图像进行中值滤波,然后取滤波后的图像中亮度值最大的像素作为标记图像;原图像经顶帽变换,并进行迭代阈值分割后的图像作为掩模图像来进行形态学重构,从而实现船舶目标检测。最后将该系统应用于长江三峡的船舶检测,实验结果表明,该系统能实时的满足算法的需要,该算法在复杂背景下,能准确地检测出目标。
The design and realization of a freshwater ship target detection system based on TMS320DM642 was introduced in this paper. At the beginning, we discussed the hardware design of the system in which the TMS320DM642 from TI company was used. Then on the hardware platform, the software realization was listed. The target detection method for freshwater ship which based on morphological reconstruction was presented, firstly, it operates the source picture with mid-filter, and then gets the max pixel as the marker image. Secondly, the algorithm operates the source picture with top-hat wansform, and then segment the picture using global threshold, the result is mask image. Finally, the algorithm used the marker image and the mask image to reconstruct the target ship. Experiments on the ChangJiang River based on this method showed a good target detection results and a successful design system.
出处
《自动化与仪器仪表》
2007年第4期8-10,共3页
Automation & Instrumentation
基金
重庆市科委自然科学基金(项目编号:CSTC
2006BA6016)
