CAJ | 학술논문

行人检测算法是利用行人的特征结合分类器对图片中是否有行人进行判断的方法。文中基于传统的HOG行人特征检测方法以及Adaboost分类器思想，改进了行人检测算法。使用多尺度的HOG特征对图片的检测区域进行特征提取，并采用级联的Adaboost分类器结合对应尺度的特征进行分类判断，将判断结果输入下一级分类器中继续进行分类判断，最终实现区域内有无人的检测。实验结果表明多尺度下的级联分类器能够更加有效地筛选出行人区域，在计算时间小幅增加的情况下，很大地提高了检测精度。
행인검측산법시이용행인적특정결합분류기대도편중시부유행인진행판단적방법。문중기우전통적HOG행인특정검측방법이급Adaboost분류기사상，개진료행인검측산법。사용다척도적HOG특정대도편적검측구역진행특정제취，병채용급련적Adaboost분류기결합대응척도적특정진행분류판단，장판단결과수입하일급분류기중계속진행분류판단，최종실현구역내유무인적검측。실험결과표명다척도하적급련분류기능구경가유효지사선출행인구역，재계산시간소폭증가적정황하，흔대지제고료검측정도。
Pedestrian detection algorithm is a method to decide whether there exists pedestrian or not in the picture by characters of pedes-trians combined with classifiers. In this paper,an improved pedestrian detection algorithm is advanced based on the traditional HOG meth-od and Adaboost classifying idea. In this algorithm,use the multi-scale HOG features to extract the features in the detection region,then the cascaded Adaboost classifiers with multi-scale features are used to judge,getting its result input into the next level of classifier,and fi-nally achieve the goal of pedestrian detection. The experimental result shows that the cascaded classifiers using multi-scale features per-forms better in pedestrian detection,which achieves higher detection precision at little cost of computing time.