Learning to Track at 100 FPS with Deep Regression Networks
This enables real-time generic object tracking for computer vision applications, addressing a bottleneck in speed for neural network trackers.
The authors tackled the problem of slow neural network-based object trackers by proposing an offline-trained deep regression network that achieves 100 fps, demonstrating state-of-the-art performance on a standard benchmark with performance improving as more training videos are added.
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.