Multi-level context-adaptive correlation tracking

One of the most important and challenging research topics in the area of computer vision is visual object tracking, which is relevant to many real-world applications. Recently, discriminative correlation filters (DCF) have been demonstrated to overcome the problems in visual object tracking efficiently. So far, only single-resolution feature maps have been utilized in DCF. Owing to this limitation, the potential of DCF has not been exploited. Moreover, convolutional features have demonstrated a better performance for visual tracking than histogram of oriented gradients (HOG) features and color features. Based on these facts, in this paper, we propose collaborative learning based on multi-resolution feature maps for DCF, employing convolutional features. Further, the confidence score, which represents the location of the target object, is selected from various candidates based on certain rules. In addition, the continuous filters are trained to handle the variations of appearance of the target. The extensive experimental results obtained using VOT2015 and OTB-100 benchmark datasets show that the proposed algorithm performs favorably against state-of-the-art tracking algorithms.

Rotation-aware correlation filters for robust visual tracking

Recently, Discriminative Correlation Filters (DCF) have shown excellent performance in visual object tracking. The correlation for a computing response map can be conducted efficiently in Fourier domain by Discrete Fourier Transform (DFT) of inputs, where the DFT of an image has symmetry on the Fourier domain. To enhance the robustness and discriminative ability of the filters, many efforts have been devoted to optimizing the learning process. Regularization methods, such as spatial regularization or temporal regularization, used in existing DCF trackers aim to enhance the capacity of the filters. Most existing methods still fail to deal with severe appearance variations—in particular, the large scale and aspect ratio changes. In this paper, we propose a novel framework that employs adaptive spatial regularization and temporal regularization to learn reliable filters in both spatial and temporal domains for tracking. To alleviate the influence of the background and distractors to the non-rigid target objects, two sub-models are combined, and multiple features are utilized for learning of robust correlation filters. In addition, most DCF trackers that applied 1-dimensional scale space search method suffered from appearance changes, such as non-rigid deformation. We proposed a 2-dimensional scale space search method to find appropriate scales to adapt to large scale and aspect ratio changes. We perform comprehensive experiments on four benchmarks: OTB-100, VOT-2016, VOT-2018, and LaSOT. The experimental results illustrate the effectiveness of our tracker, which achieved a competitive tracking performance. On OTB-100, our tracker achieved a gain of 0.8% in success, compared to the best existing DCF trackers. On VOT2018, our tracker outperformed the top DCF trackers with a gain of 1.1% in Expected Average Overlap (EAO). On LaSOT, we obtained a gain of 5.2% in success, compared to the best DCF trackers.

Discriminative Correlation Filters (DCFs) have demonstrated excellent performance in visual object tracking. These methods utilize a periodic assumption of the training samples to efficiently learn a classifier on image patches; unfortunately, this also introduces unwanted boundary effects. Recently, Spatially Regularized Discriminative Correlation Filters (SRDCFs) were proposed to resolve this issue by introducing penalization weights to the filter coefficients, thereby efficiently reducing boundary effects by assigning higher weights to the background. However, due to the variable target scale, defining the penalization ratio is non trivial; thus, it is possible to penalize the image content while also penalizing the background. In this paper, we investigate SRDCFs and present a novel and efficient part-based tracking framework by exploiting multiple SRDCFs. Compared with existing trackers, the proposed method has several advantages. (1) We define multiple correlation filters to extract features within the range of the object, thereby alleviating the boundary effect problem and avoiding penalization of the target content. (2) Through the combination of cyclic object shifts with penalized filters to build part-based object trackers, there is no need to divide training samples into parts. (3) Comprehensive comparisons demonstrate that our approach achieves a performance equivalent to that of the baseline SRDCF tracker on a set of benchmark datasets, namely, OTB2013, OTB2015 and VOT2017. In addition, compared with other state-of-the-art trackers, our approach demonstrates superior performance.

Discriminative correlation filters have recently achieved excellent performance for visual object tracking. The key to success is to make full use of dense sampling and specific properties of circulant matrices in the Fourier domain. However, previous studies don't take into consideration the importance and complementary information of different features, simply concatenating them. This paper investigates an effective method of feature integration for correlation filters, which jointly learns filters, as well as importance maps in each frame. These importance maps borrow the advantages of different features, aiming to achieve complementary traits and improve robustness. Moreover, for each feature, an importance map is shared by its all channels to avoid overfitting. In addition, we introduce a regularization term for the importance maps and use the penalty factor to control the significance of features. Based on handcrafted and CNN features, we implement two trackers, which achieve a competitive performance compared with several state-of-the-art trackers.

Discriminative correlation filter (DCF) has achieved promising performance in visual tracking for its high efficiency and high accuracy. However, DCF trackers usually suffer from some challenges, such as boundary effects and appearance changes. In this paper, we propose a novel correlation tracking method via spatial-temporal constraints and structured sparse regularization. Firstly, we introduce the background-aware selection strategy to extract real negative examples, and penalize the filter coefficients close to the boundary locations for spatial protection, both of which can alleviate the boundary effects. Secondly, we restrict the filters with structured sparse regularization to handle the local appearance changes, and exploit temporal consistent constraint on the filters to address the global appearance changes. Finally, we employ the alternative direction method of multipliers to optimize our correlation tracking model. In our optimization framework, we combine grayscale, color names, histogram of orientation gradient with deep features for appearance learning to improve the discrimination. Meanwhile, we penalize spatial constraint and structured sparse regularization alternatively based on occlusion detection to enhance processing efficiency. The qualitative and quantitative experiments are conducted on the OTB dataset. Experimental results demonstrate that the proposed tracker has better performance than other state-of-the-art trackers.

Augmenting cascaded correlation filters with spatial–temporal saliency for visual tracking

In recent years, discriminative correlation filter (DCF) based algorithms have significantly advanced the state of the art in visual object tracking. The key to the success of DCF is an efficient discriminative regression model trained with powerful multi-cue features, including both hand-crafted and deep neural network features. However, the tracking performance is hindered by their inability to respond adequately to abrupt target appearance variations. This issue is posed by the limited representation capability of fixed image features. In this work, we set out to rectify this shortcoming by proposing a complementary representation of a visual content. Specifically, we propose the use of a collaborative representation between successive frames to extract the dynamic appearance information from a target with rapid appearance changes, which results in suppressing the undesirable impact of the background. The resulting collaborative representation coefficients are combined with the original feature maps using a spatially regularised DCF framework for performance boosting. The experimental results on several benchmarking datasets demonstrate the effectiveness and robustness of the proposed method, as compared with a number of state-of-the-art tracking algorithms.

Discriminative correlation filters (DCF)-based trackers have been increasingly applied to visual tracking due to their high precision while running at high frame rates. However, most recent DCF-based methods solely concentrate on learning the correlation filter with spatial information and thus do not have sufficient descriptive power to discriminate the target from the background in the complex circumstances, such as full occlusion (OCC) and rapid target variation. In this article, we introduce a novel tracking framework that exploits the relationship between the target and its spatiotemporal context to improve tracking accuracy and robustness. Especially, we present our spatiotemporal context model in a hierarchical way, where each layer of the context pyramid is a spatial correlation filter learned from different temporal instances. For gaining an accurate spatiotemporal model, we propose an optimization fusion approach that can adaptively and efficiently learn the effect of each hierarchical layer and exploit these multiple temporal levels of correlation filters for visual tracking. Moreover, an adaptive model update strategy for correlation filters is introduced into the framework to dynamically select proper hierarchical layers, which boosts the temporal diversity of the target appearance, while radically reduces the number of model parameters and guarantees the real-time performance of the tracking method. The experimental results show that, with conventional handcrafted features, our tracker achieves the best success rates among available state-of-the-art trackers with handcrafted features, and provides state-of-the-art performance comparable to those of deep-learning-based trackers on OTB-2013, OTB-2015, VOT-2016, and UAV-20L benchmarks but runs significantly faster than deep trackers.

Learning dynamic spatial-temporal regularized correlation filter tracking with response deviation suppression via multi-feature fusion

At present, Discriminative Correlation Filter(DCF) based trackers and Deep Learning based trackers are the main methods to achieve visual tracking. Although they have achieved promising performance in many cases, there are still some inherent flaws that they can't overcome. Neither of the two main tracking algorithms can achieve satisfactory tracking performance, and considering that they can complement each other to some extent. In this paper, we focus on combining them together for a better tracking. To this end, we select several Correlation Filter and Deep Learning based tracking methods, then modify them appropriately and take different combinations to get a comprehensive result. To meet the real-time requirements, in the DCF branch, we mainly use hand-crafted features rather than deep features. Finally, we propose a new adaptive fusion approach to improve the tracking robustness and accuracy. Comprehensive experiments are performed on several benchmark datasets, using the evaluation criteria which have been proposed by the corresponding benchmarks. In order to fully understand the role of each branch and the effect of fusion strategy, our approach is compared with corresponding individual branches meanwhile the combination of our branches is compared with different fusion strategies. Finally, our approach is compared with state-of-the-art trackers, and the results show that our method has good accuracy and robustness when compared with other methods.

Tracking-by-detection approaches show good performance in visual tracking, which often train discriminative classifiers to separate tracking target from their surrounding background. As we know, an effective and efficient image feature plays an important role for realizing an outstanding tracker. The excellent image feature can separate the tracking object and the background more easily. Besides, the feature should effectively adapt to many boring factors such as illumination changes, appearance changes, shape variations, and partial or full occlusions, etc. To this end, in this paper, we present a novel multi-channel compressive feature, which combine rich information from multiple channels, and then project it into a low-dimension compressive feature space. After that, we designed a new visual tracker based on the multi-channel compressive features. At last, extensive comparative experiments conducted on a series of challenging sequences demonstrate that our tracker outperforms most of state-of-the-art tracking approaches, which also proves that our multi-channel compressive feature is effective and efficient.

The discriminative correlation filter (DCF) method is widely used in target tracking due to its real-time performance. However, the computational efficiency of DCF results in boundary effect, which reduces the tracking accuracy in fast motion scene. Besides, background noise is always required to be carefully handled for they will cause trouble in scenes such as background clutter, occlusion, deformation etc. To address the two issues, this study proposes masked discriminative correlation filter, which uses mask to process DCF filter as well as target samples so as to suppress boundary effect and background noise. Experimental results on benchmark datasets show that the proposed tracker performs better than a series of benchmark trackers, and is superior to them in almost various scenes.

Discriminative Correlation Filter (DCF) based trackers have tremendously improved the tracking performance. They adopt the first frame of video sequence to initialize the tracker and provide a fast solution due to its formulation in the Fourier domain. Previous work that applies a DCF layer on the top of pretrianed CNN, however, has not taken full advantage of CNN feature maps. In this paper, we propose a tracking architecture to fuse the local and global response map for visual tracking in an accuracy and robust way. The feature map extracted from pretrained CNN is applied to a fully-convolutional DCF layer and a non-local layer for capturing local and global response map. Experiments show that our method achieves state-of-the-art performance on three popular benchmarks: OTB-2013, OTB-2015 and VOT2016.

An accelerated correlation filter tracker