Accurate Scale Estimation for Robust Visual Tracking

Abstract

Robust scale estimation is a challenging problem in visual object tracking. Most existing methods fail to handle large scale variations in complex image sequences. This paper presents a novel approach for robust scale estimation in a tracking-by-detection framework. The proposed approach works by learning discriminative correlation filters based on a scale pyramid representation. We learn separate filters for translation and scale estimation, and show that this improves the performance compared to an exhaustive scale search while operating at real-time. Our scale estimation approach is generic as it can be incorporated into any tracking method with no inherent scale estimation.Discriminative Correlation Filters. Our tracking approach is based on the discriminative correlation filters employed in the MOSSE tracker [1]. Similarly to [2], these filters are extended to multi-dimensional features for visual tracking. We use HOG features for the translation filter and concatenate it with image intensity features. In general, we consider a d-dimensional feature map representation of an image. Let f be a rectangular patch of the target, extracted from this feature map. We denote feature dimension number l ∈ {1, . . . , d} of f by f l . The objective is to find an optimal correlation filter h, consisting of one filter h l per feature dimension. This is achieved by minimizing the cost function:Here, g is the desired correlation output associated with the training example f and λ ≥ 0 is a regularization parameter. The solution to (1) is:Capital letters denote the discrete Fourier transforms (DFTs) of the corresponding functions. We update the numerator A l t and denominator B t of the correlation filter H l t in (2) separately using a learning rate η:The correlation scores y at a patch z in the next frame are computed using (4). The new target state is found by maximizing the score y.Our Scale Estimation Approach. Ideally, an accurate scale estimation approach should be robust while computationally efficient. To achieve this, we propose a fast scale estimation approach by learning separate filters for translation and scale. This helps by restricting the search area

Tracking by Natural Language Specification

“…Henriques et al [12] introduce kernelized filters to further refine the trimming of features to the tracking situation at hand. Ma et al [25] enrich the model with long-term memory, while Danelljan et al [8] proposes a scale-invariant version and Liu et al [24] use structured correlation filters. They all aim to enhance the robustness of discriminative correlation filters against the diverse circumstances of tracking as well as to enhance the generality of discriminating the target from the background.…”

A Comprehensive Performance Evaluation of Deformable Face Tracking “In-the-Wild”

“…This periodic assumption enables efficient training and detection by utilizing the Fast Fourier Transform (FFT). Danelljan et al (2014) learn separate correlation filters for the translation and the scale estimation. In Danelljan et al (2015), the authors introduce a sparse spatial regularisation term to mitigate the artifacts at the boundaries of the circular correlation.…”

Coloring Channel Representations for Visual Tracking

“…Future work involves investigating how to incorporate our feature representation into efficient scale adaptive trackers, e.g. the Discriminative Scale Space Tracker [4]. Acknowledgments: This work has been supported by SSF through a grant for the project CUAS, by VR through a grant for the projects ETT and EMC 2 , …”