Event Stream-based Visual Object Tracking: HDETrack V2 and A High-Definition Benchmark
This work addresses the problem of visual object tracking in event streams for applications such as surveillance, robotics, and autonomous vehicles, providing an incremental improvement over existing methods.
The authors tackled the problem of visual object tracking in event streams, achieving high performance and flexibility in target tracking with their proposed method, HDETrack V2, which was validated on both low-resolution and high-resolution datasets, including their newly proposed EventVOT dataset with 1141 videos. The method demonstrated effectiveness on diverse categories such as pedestrians, vehicles, and UAVs.
We then introduce a novel hierarchical knowledge distillation strategy that incorporates the similarity matrix, feature representation, and response map-based distillation to guide the learning of the student Transformer network. We also enhance the model's ability to capture temporal dependencies by applying the temporal Fourier transform to establish temporal relationships between video frames. We adapt the network model to specific target objects during testing via a newly proposed test-time tuning strategy to achieve high performance and flexibility in target tracking. Recognizing the limitations of existing event-based tracking datasets, which are predominantly low-resolution, we propose EventVOT, the first large-scale high-resolution event-based tracking dataset. It comprises 1141 videos spanning diverse categories such as pedestrians, vehicles, UAVs, ping pong, etc. Extensive experiments on both low-resolution (FE240hz, VisEvent, FELT), and our newly proposed high-resolution EventVOT dataset fully validated the effectiveness of our proposed method. Both the benchmark dataset and source code have been released on https://github.com/Event-AHU/EventVOT_Benchmark