Re3: Real-Time Recurrent Regression Networks for Visual Tracking of Generic Objects скачать в хорошем качестве

Re3: Real-Time Recurrent Regression Networks for Visual Tracking of Generic Objects

Paper: https://arxiv.org/abs/1705.06368 Code available at: https://gitlab.com/danielgordon10/re3... Robust object tracking requires knowledge and understanding of the object being tracked: its appearance, its motion, and how it changes over time. A tracker must be able to modify its underlying model and adapt to new observations. We present Re3, a real-time deep object tracker capable of incorporating temporal information into its model. Rather than focusing on a limited set of objects or training a model at test-time to track a specific instance, we use a recurrent neural network to represent the appearance and motion of the object. We train the network offline to learn how an object's appearance and motion may change, letting it track with a single forward pass at test time. This lightweight model is capable of tracking objects at 150 FPS, while attaining competitive results on challenging benchmarks. We also show that our method handles temporary occlusion better than other comparable trackers using experiments that directly measure performance on sequences with occlusion.