Various active learning methods have been proposed for image classification problems, while very little work addresses object detection. Measuring the informativeness of an image based on its object windows is a key problem in active learning for object detection. In this paper, an image selection method to select the most representative images is proposed based on measuring their object window distributions by Maximum Mean Discrepancy (MMD). Then an active learning method for object detection is introduced based on MMD-based image selection. Experimental results show that MMD-based image selection can improve object detection performance compared to random image selection. The proposed active learning method based on MMD image selection also outperforms a classical active learning method and passive learning method.