Interpreting Abnormality of a Complex Static Scene using Generative Adversarial Network
Mahamat Moussa, Chern Hong Lim · 2019
Anomaly detection remains a difficult task in the computer vision and image processing field. Although several studies have been done to address this challenge, most of these studies focused on analyzing temporal features to determine abnormality. Examples of temporal features include behavioral changes and new object appearance in the target scene. In this paper, we are interpreting abnormality from a new perspective, which is static and complex image scene that focused on one object (airplane) using generative adversarial networks (GANs). Our interpretation of abnormality in such image intended to test two research hypotheses: 1) whether GANs can capture the cognitive features of abnormality from within a complex scene. 2) whether GANs can be used to generate more reliable datasets of abnormal scenes. In this work, we chose an airplane as the object of our experiment. We defined abnormal and normal scenes as follow: The scene is abnormal if the airplane involved in accidents (such as crash or fire), and normal otherwise (such as flying or landed airplane). A custom dataset is built for this experiment and it consists of two classes; normal and abnormal. We augmented each class to the double of its size using GANs, and then we created three different sets of datasets: (DS1, DS2, and DS3) to test our hypotheses. We applied four different supervised machine learning classifiers on each of these three sets, we repeated this step 3 times as follow: 1) pixel-based, 2) with applying Principal Component Analysis (PCA), and 3) with applying Local Binary Pattern (LBP). The overall results showed that GANs possess the capability of generating images that capture the abnormality features from the static complex scene.