论文部分内容阅读
从目标相对于邻域背景区的信噪比出发,分析了其低信噪比运动小目标特性对自动目标识别所带来的困难.基于部分Hausdorff距离在模板匹配相似性度量中可以有效抑制背景与噪声干扰的优点,提出了用自适应模板实现自动目标识别的方法.然后,综合目标区像素灰度自适应二值化处理和形心算法,实现了图像序列中目标自动定位的功能.实验结果证明:该基于自适应模板的低信噪比运动目标的自动定位算法具有快速,稳定和实用等优点.
Based on the signal-to-noise ratio of the target relative to the neighborhood background, the difficulties of automatic target recognition due to its low signal-to-noise ratio (SNR) moving target characteristics are analyzed. Based on the partial Hausdorff distance, the template matching similarity measure can effectively suppress the background And noise interference, a method of automatic target recognition based on adaptive template is proposed.After that, based on adaptive pixel binarization and centroid algorithm in target area, the automatic target location in image sequence is realized.Experiment The result proves that the automatic positioning algorithm based on adaptive template with low signal-to-noise ratio is fast, stable and practical.