The Generative Adversarial Network For Data Augmentation In Pedestrian Detection

State-of-the-art pedestrian detection models have achieved great success in many benchmarks.However,these models require a lot of annotation information and the labeling process usually takes lots of time and efforts.In this paper,we propose a method to generate labeled pedestrian data and adopt them to support the training of pedestrian detectors.Inspired by the recent success of Generative Adversarial Network(GAN),we propose to build a GAN-based model to generate realistic pedestrian images in real scene and utilize them as the augmented data to train the CNN-based(Convolutional Neural Network)pedestrian detector.Compared with adopting the regular GAN as a powerful tool for generating images,the goal of our model is different and more challenging due to: 1)generating pedestrians to fit the background scene well;2)providing the corresponding locations of those synthetic pedestrians as the ground truths for the CNN-based detectors.We denominate it as Pedestrian-Synthesis-GAN(PS-GAN).The proposed framework is built on the GAN model with multiple discriminators,trying to synthesize realistic pedestrian and learn the background context simultaneously.One discriminator aims to force PS-GAN to learn the background information like the road,light condition.It leads to smooth connection between the background and the synthetic pedestrian.The other makes PS-GAN to generate real pedestrians with more realistic shape and details.Moreover,to deal with the pedestrians of different sizes,we adopt the Spatial Pyramid Pooling(SPP)layer in the discriminator.To the best of our knowledge,PS-GAN is the first work that utilizes GAN to generate data for pedestrian/object detection task.We execute experiments on two benchmarks.The results show that our framework can smoothly synthesize pedestrians on background images of variations and different levels of details.To quantitatively evaluate our approach,we add the generated samples into training data of the baseline pedestrian detectors and show that the synthetic images are able to help improve the detector's performance.