摘要： 针对多云天气条件下的车辆检测问题，提出了一种快速有效的车辆检测方法。采用基于区间分布的背景更新模型，提高了算法对背景跟踪速度；采用基于彩色图像的HSI模型对云层造成的运动噪声进行抑制，有效地提高了目标检测的准确性。实验表明，该方法能够适应多云天气条件，综合使用背景更新和噪声抑制两种手段，能够使得多云条件下的车辆检测率达到80％以上。

关键词: 车辆检测, 多云条件, 背景更新, 噪声抑制

Abstract: This paper proposes a fast and effective method for moving vehicle detection under cloudy conditions. A zone distribution based background estimate model is used to update background and accelerate the background track. It introduces a color image based HSI model to suppress the noise caused by cloud movements, and to improve object detection accuracy. The experiment results show that the algorithm can be adaptive to cloudy conditions and vehicle detection correction rate is up to 80%.

Key words: Vehicle detection, Cloudy conditions, Background update, Noise suppression