运动目标轨迹分类与识别

Trajectory Classification and Recognition of Moving Objects

运动目标轨迹识别是运动分析中的基本问题,其目的是解释所监视场景中发生的事件,对所监视场景中运动目标轨迹的行为模式进行分析与识别,智能地做出自动分类。对轨迹有效性判断后采用K均值聚类,引入改进的隐马尔可夫模型算法,针对轨迹的复杂程度对各个轨迹模式类建立相应的隐马尔可夫模型,利用训练样本训练模型得到可靠的模型参数,计算测试样本对于各个模型的最大似然概率,选取最大概率值对应的轨迹模式类作为轨迹识别的结果,对两种场景中聚类后的轨迹进行训练与识别,平均识别率较高,实验结果表明该方法是有效的。

Trajectory recognition of the moving objects is the basic problem of the movement analysis. The intentions are as follows： interpreting what has happened in surveillance scenes, analyzing and recognizing the trajectory activity patterns of the objects in real scenes, classifying them automatically and intelligently. After judging the validity of the trajectories, use the K-Means to cluster them. Using modified Hidden Markov Model, firstly, aiming at the complex degree of the trajectories, the models are built for every trajectory pattern, and the training samples are used to get the credible parameters of the model, finally, the maximum likelihood probability of the test samples are computed to all of the trained models, the maximum value is saved and the corresponding model is the recognition result. Then train and recognize the samples clustered, the average recognition rate is high, and the method is efficient.