Abstract: The target detection of digital image is one of the main content in computer vision research, which is used widely. This paper presents an algorithm for the foggy small targets detection. Firstly, all the pixel values are looked as a set of elements with the corresponding address, and the small target is selected according to the needs, so the pixels are divided into two sets, one is object set and the other is complementary set; then the addresses of the target pixels are located; the next step is calculating the thresholds of target set and its complementary set. Finally, the binarization operation is applied to the small target set and its complement set by the threshold. The test results show that this algorithm for small target detection is very effective.

Key words: digital image, target detection, complementary set, subset, binarization

摘要： 数字图像目标检测是计算机视觉研究中的主要内容之一，具有较广泛的用途。提出一种针对数字图像中模糊小目标进行检测的算法。将所有像素值看作具有对应地址的元素集合，根据需要确定小目标像素范围，把图像分为目标集合及其补集；通过定位查找确定存储小目标像素的地址；计算出小目标像素子集合及其补集的阈值；利用计算出的阈值分别对小目标集合及其补集进行二值化运算，得到检测后的结果。实验结果证明，该算法对小目标检测具有较好的效果。

关键词: 数字图像, 目标检测, 补集, 子集, 二值化