Learning to Track at 100 FPS with Deep Regression Networks

TL;DR

This paper introduces a fast, offline-trained neural network tracker capable of tracking novel objects at 100 fps, significantly advancing real-time object tracking with state-of-the-art accuracy.

Contribution

The authors present the first neural network tracker that operates at 100 fps and learns to track generic objects without online training, leveraging offline training on large video datasets.

Findings

Achieves 100 fps tracking speed.

Outperforms previous neural network trackers on standard benchmarks.

Performance improves with more offline training data.

Abstract

Machine learning techniques are often used in computer vision due to their ability to leverage large amounts of training data to improve performance. Unfortunately, most generic object trackers are still trained from scratch online and do not benefit from the large number of videos that are readily available for offline training. We propose a method for offline training of neural networks that can track novel objects at test-time at 100 fps. Our tracker is significantly faster than previous methods that use neural networks for tracking, which are typically very slow to run and not practical for real-time applications. Our tracker uses a simple feed-forward network with no online training required. The tracker learns a generic relationship between object motion and appearance and can be used to track novel objects that do not appear in the training set. We test our network on a standard tracking benchmark to demonstrate our tracker's state-of-the-art performance. Further, our performance improves as we add more videos to our offline training set. To the best of our knowledge, our tracker is the first neural-network tracker that learns to track generic objects at 100 fps.