Generative Adversarial Models for People Attribute Recognition in Surveillance
This work addresses attribute recognition in surveillance, which is incremental as it applies existing DCGAN methods to enhance images for a specific domain.
The paper tackles the problem of recognizing people attributes in surveillance footage by addressing poor resolution and occlusion issues, achieving effective attribute extraction even with up to 80% occlusion.
In this paper we propose a deep architecture for detecting people attributes (e.g. gender, race, clothing ...) in surveillance contexts. Our proposal explicitly deal with poor resolution and occlusion issues that often occur in surveillance footages by enhancing the images by means of Deep Convolutional Generative Adversarial Networks (DCGAN). Experiments show that by combining both our Generative Reconstruction and Deep Attribute Classification Network we can effectively extract attributes even when resolution is poor and in presence of strong occlusions up to 80\% of the whole person figure.