Vehicle Models Identification Based on the Double Updating Support Vector Machine Online Learning Algorithm

For the traditional online support vector machine classification algorithm based on the kernel function, the weight of the misclassified sample in the learning process of classification remains unchanged, which will inevitably affect the classification accuracy. This paper presents a Double Updating Online Support Vector Machine Learning Algorithm that can update the weight real-timely. According to the change of the training support vector set when the new sample is added, the algorithm can update the weights of misclassified sample and update the existing sample weights at the same time, making the algorithm achieve better classification performance in large-scale data situation. The online support vector machine double update algorithm is applied to the vehicle recognition, the added newly vehicle models classification and recognition can be done beautifully from the experiment, and the experiment proved the validity and feasibility of the algorithm robustness.