针对交通视频序列中的阴影检测问题，在分析目前常用的几种阴影检测算法的基础上，提出了一种基于交通视频流的灰度图阴影检测算法。该算法首先通过建立一个具有鲁棒性和自适应性的背景模型来获取背景，同时对阴影进行初步模糊滤除，然后再通过车体的重构来准确去除阴影。实践表明，该算法准确度高，具有广泛的应用前景。

Analyzing the characteristics of the shadows in traffic video sequence, we propose a small improvement to an existing background modal based on several current shadow detection algorithms, and incorporate a novel technique for shadow detection in grayscale video sequence. We gain the background establishes a robustness and auto adapted background modal. First we filtrate the shadow fuzzily, and then re establish the images of car to remove the shadow exactly. This algorithm works well for traffic video sequence, and has a widespread application prospect.