基于Adaboost算法的行人检测方法

鉴于Adaboost算法简单可靠、学习精度高的特点，提出一种基于Adaboost算法的行人实时检测方法。选取了扩展的类Haar特征，采用Adaboost算法训练得到了一个识别准确率理想的行人分类器，通过VC编程将级联分类器应用到实际的行人检测系统中。试验结果表明，该方法可以快速、准确地实现行人的在线检测，具有较好的实时性。

Pedestrian Detection Method Based on Adaboost Algorithm

Adaboost algorithm is reliable and its precision is high. The article proposes a real-time pedestrian detection method based on the Adaboost algorithm. The expanded Haar-like characteristic is selected and calculated using integral map, the pedestrian detection cascaded classifiers with high accuracy are trained by Adaboost. Cascaded classifiers are loaded through VC to realize the real-time pedestrian detection. Experimental results indicate that the method is fast and reliable and meets the requirement of real-time system.