Abstract: The paper presents a new algorithm for the detection of high-speed moving objects based on picture blocks and HVS color space of image differences techniques. The position of the object is roughly determined by examining the pictures which have been separated to blocks with the help of previous experiences. The moving object is detected in the determined local region by comparing the image differences in HVS color space. The experimental results show that this algorithm can overcome the weakness of traditional image difference method and suppress shadows effectively with advantages of self-adaptation and high speed. It can be used to detect the high-speed moving objects in the complex.

Key words: Moving object detection, Video monitor, HSV color space, Median filter, Morphological filter

摘要： 提出了一种新的基于图像块和HVS彩色图像差值技术的高速运动目标检测算法。对分块后的图像进行粗检，辅以经验知识确定出目标的大概区域。在锁定的局部区域内运用HVS彩色图像差值方法检测出运动目标。实验结果表明，该算法克服了传统的差图像法的缺点，能够有效地抑制阴影的影响，具有自适应性强、速度快等优点。在复杂的环境下，运用该算法提取运动目标可以获得满意的效果。

关键词: 运动目标检测, 视频监控, HSV彩色空间, 中值滤波, 形态学滤波