To improve the adaptability of vehicle detection algorithms in complex traffic circumstances, a robust detection algorithm based on LBP features of Haar-like Characteristics was proposed. The image texture feature reflects some characteristics of the degree of gray distribution, contrast and spatial distribution, Haar-like was inducted into LBP, then this method calculate the local texture features of image in accordance with local binary pattern (LBP); then a small number of critical features from a large set of new haar local binary pattern was selected while training AdaBoost, finally two classes classification was performed using AdaBoost classifier and the selected features. Experimental results show that the robustness of the classifier has been greatly improved so that the classifiers can detect the vehicles accurately.