Temporal Delta Layer: Training Towards Brain Inspired Temporal Sparsity for Energy Efficient Deep Neural Networks

In the recent past, real-time video processing using state-of-the-art deep neural networks (DNN) has achieved human-like accuracy but at the cost of high energy consumption, making them infeasible for edge device deployment. The energy consumed by running DNNs on hardware accelerators is dominated by the number of memory read/writes and...

Matting using a known background and a chroma-key minimization scheme

In this paper, we investigate the problem of segmenting the foreground objects from the known background. The target application is a setting where a large display serves as the backdrop for a scene. The method proposed in this paper solves this problem in two steps. We try to separate the foreground and the background with the modified...

Multi-frame deep learning models for action detection in surveillance videos

Visual surveillance technologies are increasingly being used to monitor public spaces. These technologies process the recordings of surveillance cameras. Such recordings contain depictions of human actions such as "running", "waving", and "aggression". In the field of computer vision, automated detection of human actions in videos is known as...

Processing Upper Airway Endoscopic Videos For Sleep Apnea Diagnostics.

Obstructive sleep apnea (OSA) is a common sleep disorder. Surgery is sometimes recommended, by specialists, for severe OSA. In that case, an endoscopic investigation with the patient under sedation would take place. By automating the detection of upper airway collapsing from the endoscopic video, we hope to assist doctors in their diagnostic of...