摘要
针对镁熔液复杂表面背景下可视弱目标的检测,提出了一种基于形态学和隔帧差分的算法。该方法首先利用形态学白Top-Hat变换进行低频背景抑制,增强图像的对比度;然后进行隔帧差分,去除背景杂波和大量噪声,得到含有目标点及少量的噪声点图像;最后结合数学形态学开运算去除噪声点获得真正的目标。同时比较了不同结构元素在背景抑制和运行速度方面的性能差异。仿真结果表明本方法能有效地检测出弱目标,且菱形结构元素综合性能最好。
A new detection method based on morphology and discontinuous frame difference was presented for the visible small target on the complicated surface in magnesium melt.First,the contrast of image was enhanced and its background was suppressed by white Top-Hat transformation;then discontinuous frame difference was used to remove the background clutter and the large of noises,thus,the image was obtained including weak target and a few noises,Finally,the true target was detected combining with the open algorithm of mathematical morphology to remove noise,and the properties of different structural elements were compared with background suppression and running time.Simulation results show that this method can effectively detect the weak target,and the synthesized properties of diamond element are the best.
出处
《轻金属》
CSCD
北大核心
2013年第1期60-62,共3页
Light Metals
基金
国家自然科学基金专项基金项目(51044001)
安徽省自然科学基金项目(11040606M104)
关键词
镁熔液
弱目标
白Top-Hat变换
隔帧差分
结构元素
magnesium melt
weak target
white Top-Hat transformation
discontinuous frame difference
structural elements