Deformable Parts Correlation Filters for Robust Visual Tracking
This work improves visual tracking for applications like surveillance and robotics by introducing a novel method that combines deformable parts with correlation filters, though it is incremental as it builds on existing tracking approaches.
The authors tackled the problem of robust visual tracking by addressing non-rigid object deformations and self-occlusions with a deformable parts model, achieving state-of-the-art performance on OTB, VOT2014, and VOT2015 benchmarks while running in real-time.
Deformable parts models show a great potential in tracking by principally addressing non-rigid object deformations and self occlusions, but according to recent benchmarks, they often lag behind the holistic approaches. The reason is that potentially large number of degrees of freedom have to be estimated for object localization and simplifications of the constellation topology are often assumed to make the inference tractable. We present a new formulation of the constellation model with correlation filters that treats the geometric and visual constraints within a single convex cost function and derive a highly efficient optimization for MAP inference of a fully-connected constellation. We propose a tracker that models the object at two levels of detail. The coarse level corresponds a root correlation filter and a novel color model for approximate object localization, while the mid-level representation is composed of the new deformable constellation of correlation filters that refine the object location. The resulting tracker is rigorously analyzed on a highly challenging OTB, VOT2014 and VOT2015 benchmarks, exhibits a state-of-the-art performance and runs in real-time.