Perspective Transformation Data Augmentation for Object Detection

One major reason for the success of convolutional neural networks (CNNs) is the availability of large-scale labeled data. Effective training of CNNs relies on large annotated data. Unfortunately, large amounts of data with corresponding annotations are too expensive to obtain in some real-world applications. One reasonable alternative is to use data augmentation techniques to automatically generate annotated samples. In this paper, a novel data augmentation framework based on perspective transformation is proposed. This method automatically generates new annotated data without extra manual labeling, thus effectively extends the inadequate dataset. Perspective transformation can produce new images captured from any cameras viewpoints. Therefore, our method can mimic images taken at the angle that the camera cannot reach. Extensive experimental results on several datasets have demonstrated that our perspective transformation data augmentation strategy is an effective tool when using deep CNNs on small or imbalance datasets.