CAJ | 학술논문

为了提高行人检测正确率，提出一种基于多特征融合和最小二乘支持向量机的行人检测模型。首先提取行人的相位一致性特征和梯度直方图特征，然后采用粒子群算法选择最优特征子集，最后将最优行人检测特征子集输入到最小二乘支持向量机对学习和分类，并采用对模型性能采用仿真实验进行测试。结果表明，相对于其它行人检测模型，本文模型不仅提高了行人检测率、降低了虚警率，而且加快行人检测效率，具有较强的鲁棒性。
위료제고행인검측정학솔，제출일충기우다특정융합화최소이승지지향량궤적행인검측모형。수선제취행인적상위일치성특정화제도직방도특정，연후채용입자군산법선택최우특정자집，최후장최우행인검측특정자집수입도최소이승지지향량궤대학습화분류，병채용대모형성능채용방진실험진행측시。결과표명，상대우기타행인검측모형，본문모형불부제고료행인검측솔、강저료허경솔，이차가쾌행인검측효솔，구유교강적로봉성。
In order to improve the pedestrian detection rate, a new pedestrian detection model based on multi-features and least squares support vector machine is proposed in this paper. Firstly, the Phase Congruency fea-ture and histograms of oriented gradients features are extracted, secondly, the optimal features are selected by parti-cle swarm optimization algorithm, finally, the features are input least squares support vector machine to train and classify, and the simulation experiments are carried out to test the performance of model. The results show that com-pared with other pedestrian detection model, the proposed model not only improve the pedestrian detection rate, but also can fasten the speed ,and it has good robust.