Real Time Visual Tracking using Spatial-Aware Temporal Aggregation Network
This addresses the challenge of adapting to appearance changes and resisting drift in real-time visual tracking for applications like surveillance or robotics, representing a strong specific gain rather than a foundational advancement.
The paper tackles the problem of visual tracking by proposing a method that aggregates historical features using spatial-aligned and scale-aware temporal information, achieving leading performance on multiple benchmarks like OTB2013, OTB2015, VOT2015, VOT2016, and LaSOT with a real-time speed of 26 FPS.
More powerful feature representations derived from deep neural networks benefit visual tracking algorithms widely. However, the lack of exploitation on temporal information prevents tracking algorithms from adapting to appearances changing or resisting to drift. This paper proposes a correlation filter based tracking method which aggregates historical features in a spatial-aligned and scale-aware paradigm. The features of historical frames are sampled and aggregated to search frame according to a pixel-level alignment module based on deformable convolutions. In addition, we also use a feature pyramid structure to handle motion estimation at different scales, and address the different demands on feature granularity between tracking losses and deformation offset learning. By this design, the tracker, named as Spatial-Aware Temporal Aggregation network (SATA), is able to assemble appearances and motion contexts of various scales in a time period, resulting in better performance compared to a single static image. Our tracker achieves leading performance in OTB2013, OTB2015, VOT2015, VOT2016 and LaSOT, and operates at a real-time speed of 26 FPS, which indicates our method is effective and practical. Our code will be made publicly available at \href{https://github.com/ecart18/SATA}{https://github.com/ecart18/SATA}.