Image classification is a very easy task for humans. Even a three years old child can classify an image instantly and without any doubt. However, teaching computers classifying images has been a working area for researchers for a long time because of the intrinsic difficulties of the task for computers. With the rise of deep learning, it has been possible to get better classification performance than before. In this work, we evaluated the performance of convolutional neural network combined with support vector machine for classifying aerial images based on presence of a vehicle.