Automated person re-identification is a challenging research problem that has many real-world applications, especially in video surveillance. While many recent studies have been focusing on solving the person re-identification problem using full-scale images or video footages, little work has been done to solve the person re-identification problem in a top-down context. In this work, we propose a solution to the top-down reidentification problem that uses the Siamese architecture in conjunction with Convolutional Neural Networks. In our approach, a pair of top-down images is distinguished by a single Siamese network, which is trained to predict the similarity, or a distance between two input images. Experiments have shown that once the model is properly trained, it is able to achieve one-shot, top-down re-identification by learning unseen classes of person in real-time.
