DCCO: Towards Deformable Continuous Convolution Operators
This work addresses the issue of tracking non-rigid objects in computer vision, offering an incremental improvement over existing DCF methods.
The paper tackled the problem of rigid appearance models in DCF-based trackers being insufficient for non-rigid target transformations by proposing a deformable continuous convolution operator, which improved baseline performance to be comparable to state-of-the-art on benchmarks like OTB-2015, TempleColor, and VOT2016.
Discriminative Correlation Filter (DCF) based methods have shown competitive performance on tracking benchmarks in recent years. Generally, DCF based trackers learn a rigid appearance model of the target. However, this reliance on a single rigid appearance model is insufficient in situations where the target undergoes non-rigid transformations. In this paper, we propose a unified formulation for learning a deformable convolution filter. In our framework, the deformable filter is represented as a linear combination of sub-filters. Both the sub-filter coefficients and their relative locations are inferred jointly in our formulation. Experiments are performed on three challenging tracking benchmarks: OTB- 2015, TempleColor and VOT2016. Our approach improves the baseline method, leading to performance comparable to state-of-the-art.