Attentive Deep Regression Networks for Real-Time Visual Face Tracking in Video Surveillance

TL;DR

This paper introduces an attentive deep learning tracker built on GOTURN for real-time face tracking in video surveillance, outperforming existing methods and providing new annotated datasets for further research.

Contribution

It presents a novel end-to-end attentive deep learning tracker based on GOTURN, significantly improving tracking accuracy and speed, and offers new annotated datasets for face tracking research.

Findings

Outperforms state-of-the-art GOTURN and IVT trackers

Achieves real-time tracking speeds

Provides new annotated datasets for face tracking

Abstract

Visual face tracking is one of the most important tasks in video surveillance systems. However, due to the variations in pose, scale, expression, and illumination it is considered to be a difficult task. Recent studies show that deep learning methods have a significant potential in object tracking tasks and adaptive feature selection methods can boost their performance. Motivated by these, we propose an end-to-end attentive deep learning based tracker, that is build on top of the state-of-the-art GOTURN tracker, for the task of real-time visual face tracking in video surveillance. Our method outperforms the state-of-the-art GOTURN and IVT trackers by very large margins and it achieves speeds that are very far beyond the requirements of real-time tracking. Additionally, to overcome the scarce data problem in visual face tracking, we also provide bounding box annotations for the G1 and G2 sets of ChokePoint dataset and make it suitable for further studies in face tracking under surveillance conditions.