Unsupervised Anomaly Approach to Pedestrian Age Classification from Surveillance Cameras Using an Adversarial Model with Skip-Connections

Anomaly detection is an active research area within the machine learning and scene understanding fields. Despite the ambiguous definition, anomaly detection is considered an outlier detection in a given data based on normality constraints. The biggest problem in real-world anomaly detection applications is the high bias of the available data due to the class imbalance, meaning a limited amount of all possible anomalous and normal samples, thus making supervised learning model use difficult. This paper introduces an unsupervised and adversarially trained anomaly model with a unique encoder-decoder structure to address this issue. The proposed model distinguishes different age groups of people-namely child, adult, and elderly-from surveillance camera data in Busan, Republic of Korea. The proposed model has three major parts: a parallel-pipeline encoder with a conventional convolutional neural network and a dilated-convolutional neural network. The latent space vectors created at the end of both networks are concatenated. While the convolutional pipeline extracts local features, the dilated convolutional pipeline extracts the global features from the same input image. Concatenation of these features is sent as the input into the decoder, which has partial skip-connection elements from both pipelines. This, along with the concatenated feature vector, improves feature diversity. The input image is reconstructed from the feature vector through the stacked transpose convolution layers. Afterward, both the original input image and the corresponding reconstructed image are sent into the discriminator and are distinguished as real or fake. The image reconstruction loss and its corresponding latent space loss are considered for the training of the model and the adversarial Wasserstein loss. Only normal-designated class images are used during the training. The hypothesis is that if the model is trained with normal class images, then during the inference, the construction loss will be minimal. On the other hand, if the untrained anomalous class images are input through the model, the reconstruction loss value will be very high. This method is applied to distinguish different age clusters of people using unsupervised training. The proposed model outperforms the benchmark models in both the qualitative and the quantitative measurements.