Abstract: A new codebook model was proposed based on HSV color space to eliminate the effect of complex dynamic background in the moving object detection. The merits of this new model lie in three aspects: 1) HSV color space was introduced to effectively distinguish foreground and background for false targets removal; 2) a 4-tuple codeword was proposed for fast codebook training and small storage in comparison with the traditional 9-tuple codeword; 3) a new codebook learning and updating scheme was designed for easy and fast codebook training and detection. A global quantitative evaluation method named recall-precision curve was also proposed for the video sequence. Qualitative and quantitative experiments demonstrate that the proposed codebook model can effectively detect moving object under complex dynamic background.

Key words: complex dynamic background, moving object detection, codebook model, HSV color space

摘要： 为了有效消除复杂动态背景对运动物体检测的影响，提出一种新的基于HSV颜色空间的码书模型。该模型的特点是：1)引入具有较强前后景区分能力的HSV颜色空间，有效减少伪目标的检测；2)采用四元素码字，实现较前人九元素码字更快的训练和更低的存储；3)设计新的码字学习和更新策略，实现简单和快速的码字学习和运动目标检测。同时提出新的算法评价方法：覆盖率—准确率曲线，以反映运动物体检测算法对连续视频序列的检测性能。使用覆盖率—准确率曲线评价的实验结果证明,所提出的码书模型可以有效检测复杂背景下的运动物体。

关键词: 复杂动态背景, 运动物体检测, 码书模型, HSV颜色空间