Dual-regression model for visual tracking

Enhanced robust spatial feature selection and correlation filter learning for UAV tracking

Spatial boundary effect can significantly reduce the performance of a learned discriminative correlation filter (DCF) model. A commonly used method to relieve this effect is to extract appearance features from a wider region of a target. However, this way would introduce unexpected features from background pixels and noises, which will lead to a decrease of the filter's discrimination power. To address this shortcoming, this paper proposes an innovative method called enhanced robust spatial feature selection and correlation filter Learning (EFSCF), which performs jointly sparse feature learning to handle boundary effects effectively while suppressing the influence of background pixels and noises. Unlike the ℓ₂-norm-based tracking approaches that are prone to non-Gaussian noises, the proposed method imposes the ℓ_2,1-norm on the loss term to enhance the robustness against the training outliers. To enhance the discrimination further, a jointly sparse feature selection scheme based on the ℓ_2,1 -norm is designed to regularize the filter in rows and columns simultaneously. To the best of the authors' knowledge, this has been the first work exploring the structural sparsity in rows and columns of a learned filter simultaneously. The proposed model can be efficiently solved by an alternating direction multiplier method. The proposed EFSCF is verified by experiments on four challenging unmanned aerial vehicle datasets under severe noise and appearance changes, and the results show that the proposed method can achieve better tracking performance than the state-of-the-art trackers.

Efficient joint model learning, segmentation and model updating for visual tracking

The Tracking-by-segmentation framework is widely used in visual tracking to handle severe appearance change such as deformation and occlusion. Tracking-by-segmentation methods first segment the target object from the background, then use the segmentation result to estimate the target state. In existing methods, target segmentation is formulated as a superpixel labeling problem constrained by a target likelihood constraint, a spatial smoothness constraint and a temporal consistency constraint. The target likelihood is calculated by a discriminative part model trained independently from the superpixel labeling framework and updated online using historical tracking results as pseudo-labels. Due to the lack of spatial and temporal constraints and inaccurate pseudo-labels, the discriminative model is unreliable and may lead to tracking failure. This paper addresses the aforementioned problems by integrating the objective function of model training into the target segmentation optimization framework. Thus, during the optimization process, the discriminative model can be constrained by spatial and temporal constraints and provides more accurate target likelihoods for part labeling, and the results produce more reliable pseudo-labels for model learning. Moreover, we also propose a supervision switch mechanism to detect erroneous pseudo-labels caused by a severe change in data distribution and switch the classifier to a semi-supervised setting in such a case. Evaluation results on OTB2013, OTB2015 and TC-128 benchmarks demonstrate the effectiveness of the proposed tracking algorithm.

Adaptive ensemble perception tracking

Recently, tracking models based on bounding box regression (such as region proposal networks), built on the Siamese network, have attracted much attention. Despite their promising performance, these trackers are less effective in perceiving the target information in the following two aspects. First, existing regression models cannot take a global view of a large-scale target since the effective receptive field of a neuron is too small to cover the target with a large scale. Second, the neurons with a fixed receptive field (RF) size in these models cannot adapt to the scale and aspect ratio changes of the target. In this paper, we propose an adaptive ensemble perception tracking framework to address these issues. Specifically, we first construct a per-pixel prediction model, which predicts the target state at each pixel of the correlated feature. On top of the per-pixel prediction model, we then develop a confidence-guided ensemble prediction mechanism. The ensemble mechanism adaptively fuses the predictions of multiple pixels with the guidance of confidence maps, which enlarges the perception range and enhances the adaptive perception ability at the object-level. In addition, we introduce a receptive field adaption model to enhance the adaptive perception ability at the neuron-level, which adjusts the RF by adaptively integrating the features with different RFs. Extensive experimental results on the VOT2018, VOT2016, UAV123, LaSOT, and TC128 datasets demonstrate that the proposed algorithm performs favorably against the state-of-the-art methods in terms of accuracy and speed.