In this paper, we propose a novel effective non-rigid object tracking framework based on the spatial-temporal consistent saliency detection. In contrast to most existing trackers that utilize a bounding box to specify the tracked target, the proposed framework can extract accurate regions of the target as tracking outputs. It achieves a better description of the non-rigid objects and reduces the background pollution for the tracking model. Furthermore, our model has several unique features. First, a tailored fully convolutional neural network (TFCN) is developed to model the local saliency prior for a given image region, which not only provides the pixel-wise outputs but also integrates the semantic information. Second, a novel multi-scale multi-region mechanism is proposed to generate local saliency maps that effectively consider visual perceptions with different spatial layouts and scale variations. Subsequently, local saliency maps are fused via a weighted entropy method, resulting in a final discriminative saliency map. Finally, we present a non-rigid object tracking algorithm based on the predicted saliency maps. By utilizing a spatial-temporal consistent saliency map (STCSM), we conduct target-background classification and use a simple fine-tuning scheme for online updating. Extensive experiments demonstrate that the proposed algorithm achieves competitive performance in both saliency detection and visual tracking, especially outperforming other related trackers on the non-rigid object tracking datasets.
Cross-correlator plays a significant role in many visual perception tasks, such as object detection and tracking. Beyond the linear cross-correlator, this paper proposes a kernel cross-correlator (KCC) that breaks traditional limitations. First, by introducing the kernel trick, the KCC extends the linear cross-correlation to non-linear space, which is more robust to signal noises and distortions. Second, the connection to the existing works shows that KCC provides a unified solution for correlation filters. Third, KCC is applicable to any kernel function and is not limited to circulant structure on training data, thus it is able to predict affine transformations with customized properties. Last, by leveraging the fast Fourier transform (FFT), KCC eliminates direct calculation of kernel vectors, thus achieves better performance yet still with a reasonable computational cost. Comprehensive experiments on visual tracking and human activity recognition using wearable devices demonstrate its robustness, flexibility, and efficiency. The source codes of both experiments are released at https://github.com/wang-chen/KCC
Robust object tracking requires knowledge and understanding of the object being tracked: its appearance, its motion, and how it changes over time. A tracker must be able to modify its underlying model and adapt to new observations. We present Re3, a real-time deep object tracker capable of incorporating temporal information into its model. Rather than focusing on a limited set of objects or training a model at test-time to track a specific instance, we pretrain our generic tracker on a large variety of objects and efficiently update on the fly; Re3 simultaneously tracks and updates the appearance model with a single forward pass. This lightweight model is capable of tracking objects at 150 FPS, while attaining competitive results on challenging benchmarks. We also show that our method handles temporary occlusion better than other comparable trackers using experiments that directly measure performance on sequences with occlusion.
In this paper, we propose a novel structural correlation filter combined with a multi-task Gaussian particle filter (KCF-GPF) model for robust visual tracking. We first present an assemble structure where several KCF trackers as weak experts provide a preliminary decision for a Gaussian particle filter to make a final decision. The proposed method is designed to exploit and complement the strength of a KCF and a Gaussian particle filter. Compared with the existing tracking methods based on correlation filters or particle filters, the proposed tracker has several advantages. First, it can detect the tracked target in a large-scale search scope via weak KCF trackers and evaluate the reliability of weak trackers\rq decisions for a Gaussian particle filter to make a strong decision, and hence it can tackle fast motions, appearance variations, occlusions and re-detections. Second, it can effectively handle large-scale variations via a Gaussian particle filter. Third, it can be amenable to fully parallel implementation using importance sampling without resampling, thereby it is convenient for VLSI implementation and can lower the computational costs. Extensive experiments on the OTB-2013 dataset containing 50 challenging sequences demonstrate that the proposed algorithm performs favourably against 16 state-of-the-art trackers.
During the recent years, correlation filters have shown dominant and spectacular results for visual object tracking. The types of the features that are employed in these family of trackers significantly affect the performance of visual tracking. The ultimate goal is to utilize robust features invariant to any kind of appearance change of the object, while predicting the object location as properly as in the case of no appearance change. As the deep learning based methods have emerged, the study of learning features for specific tasks has accelerated. For instance, discriminative visual tracking methods based on deep architectures have been studied with promising performance. Nevertheless, correlation filter based (CFB) trackers confine themselves to use the pre-trained networks which are trained for object classification problem. To this end, in this manuscript the problem of learning deep fully convolutional features for the CFB visual tracking is formulated. In order to learn the proposed model, a novel and efficient backpropagation algorithm is presented based on the loss function of the network. The proposed learning framework enables the network model to be flexible for a custom design. Moreover, it alleviates the dependency on the network trained for classification. Extensive performance analysis shows the efficacy of the proposed custom design in the CFB tracking framework. By fine-tuning the convolutional parts of a state-of-the-art network and integrating this model to a CFB tracker, which is the top performing one of VOT2016, 18% increase is achieved in terms of expected average overlap, and tracking failures are decreased by 25%, while maintaining the superiority over the state-of-the-art methods in OTB-2013 and OTB-2015 tracking datasets.
In this paper, we propose a robust visual tracking method which exploits the relationships of targets in adjacent frames using patchwise joint sparse representation. Two sets of overlapping patches with different sizes are extracted from target candidates to construct two dictionaries with consideration of joint sparse representation. By applying this representation into structural sparse appearance model, we can take two-fold advantages. First, the correlation of target patches over time is considered. Second, using this local appearance model with different patch sizes takes into account local features of target thoroughly. Furthermore, the position of candidate patches and their occlusion levels are utilized simultaneously to obtain the final likelihood of target candidates. Evaluations on recent challenging benchmark show that our tracking method outperforms the state-of-the-art trackers.
Template-matching methods for visual tracking have gained popularity recently due to their comparable performance and fast speed. However, they lack effective ways to adapt to changes in the target object's appearance, making their tracking accuracy still far from state-of-the-art. In this paper, we propose a dynamic memory network to adapt the template to the target's appearance variations during tracking. An LSTM is used as a memory controller, where the input is the search feature map and the outputs are the control signals for the reading and writing process of the memory block. As the location of the target is at first unknown in the search feature map, an attention mechanism is applied to concentrate the LSTM input on the potential target. To prevent aggressive model adaptivity, we apply gated residual template learning to control the amount of retrieved memory that is used to combine with the initial template. Unlike tracking-by-detection methods where the object's information is maintained by the weight parameters of neural networks, which requires expensive online fine-tuning to be adaptable, our tracker runs completely feed-forward and adapts to the target's appearance changes by updating the external memory. Moreover, unlike other tracking methods where the model capacity is fixed after offline training --- the capacity of our tracker can be easily enlarged as the memory requirements of a task increase, which is favorable for memorizing long-term object information. Extensive experiments on OTB and VOT demonstrates that our tracker MemTrack performs favorably against state-of-the-art tracking methods while retaining real-time speed of 50 fps.
We propose a new long video dataset (called Track Long and Prosper - TLP) and benchmark for single object tracking. The dataset consists of 50 HD videos from real world scenarios, encompassing a duration of over 400 minutes (676K frames), making it more than 20 folds larger in average duration per sequence and more than 8 folds larger in terms of total covered duration, as compared to existing generic datasets for visual tracking. The proposed dataset paves a way to suitably assess long term tracking performance and train better deep learning architectures (avoiding/reducing augmentation, which may not reflect real world behaviour). We benchmark the dataset on 17 state of the art trackers and rank them according to tracking accuracy and run time speeds. We further present thorough qualitative and quantitative evaluation highlighting the importance of long term aspect of tracking. Our most interesting observations are (a) existing short sequence benchmarks fail to bring out the inherent differences in tracking algorithms which widen up while tracking on long sequences and (b) the accuracy of trackers abruptly drops on challenging long sequences, suggesting the potential need of research efforts in the direction of long-term tracking.
Recently, correlation filters have demonstrated the excellent performance in visual tracking. However, the base training sample region is larger than the object region,including the Interference Region(IR). The IRs in training samples from cyclic shifts of the base training sample severely degrade the quality of a tracking model. In this paper, we propose the novel Region-filtering Correlation Tracking (RFCT) to address this problem. We immediately filter training samples by introducing a spatial map into the standard CF formulation. Compared with existing correlation filter trackers, our proposed tracker has the following advantages: (1) The correlation filter can be learned on a larger search region without the interference of the IR by a spatial map. (2) Due to processing training samples by a spatial map, it is more general way to control background information and target information in training samples. The values of the spatial map are not restricted, then a better spatial map can be explored. (3) The weight proportions of accurate filters are increased to alleviate model corruption. Experiments are performed on two benchmark datasets: OTB-2013 and OTB-2015. Quantitative evaluations on these benchmarks demonstrate that the proposed RFCT algorithm performs favorably against several state-of-the-art methods.
Discriminative Correlation Filters (DCF) are efficient in visual tracking but suffer from unwanted boundary effects. Spatially Regularized DCF (SRDCF) has been suggested to resolve this issue by enforcing spatial penalty on DCF coefficients, which, inevitably, improves the tracking performance at the price of increasing complexity. To tackle online updating, SRDCF formulates its model on multiple training images, further adding difficulties in improving efficiency. In this work, by introducing temporal regularization to SRDCF with single sample, we present our spatial-temporal regularized correlation filters (STRCF). Motivated by online Passive-Agressive (PA) algorithm, we introduce the temporal regularization to SRDCF with single sample, thus resulting in our spatial-temporal regularized correlation filters (STRCF). The STRCF formulation can not only serve as a reasonable approximation to SRDCF with multiple training samples, but also provide a more robust appearance model than SRDCF in the case of large appearance variations. Besides, it can be efficiently solved via the alternating direction method of multipliers (ADMM). By incorporating both temporal and spatial regularization, our STRCF can handle boundary effects without much loss in efficiency and achieve superior performance over SRDCF in terms of accuracy and speed. Experiments are conducted on three benchmark datasets: OTB-2015, Temple-Color, and VOT-2016. Compared with SRDCF, STRCF with hand-crafted features provides a 5 times speedup and achieves a gain of 5.4% and 3.6% AUC score on OTB-2015 and Temple-Color, respectively. Moreover, STRCF combined with CNN features also performs favorably against state-of-the-art CNN-based trackers and achieves an AUC score of 68.3% on OTB-2015.
With the advantage of high mobility, Unmanned Aerial Vehicles (UAVs) are used to fuel numerous important applications in computer vision, delivering more efficiency and convenience than surveillance cameras with fixed camera angle, scale and view. However, very limited UAV datasets are proposed, and they focus only on a specific task such as visual tracking or object detection in relatively constrained scenarios. Consequently, it is of great importance to develop an unconstrained UAV benchmark to boost related researches. In this paper, we construct a new UAV benchmark focusing on complex scenarios with new level challenges. Selected from 10 hours raw videos, about 80,000 representative frames are fully annotated with bounding boxes as well as up to 14 kinds of attributes (e.g., weather condition, flying altitude, camera view, vehicle category, and occlusion) for three fundamental computer vision tasks: object detection, single object tracking, and multiple object tracking. Then, a detailed quantitative study is performed using most recent state-of-the-art algorithms for each task. Experimental results show that the current state-of-the-art methods perform relative worse on our dataset, due to the new challenges appeared in UAV based real scenes, e.g., high density, small object, and camera motion. To our knowledge, our work is the first time to explore such issues in unconstrained scenes comprehensively.
Object proposal generation methods have been widely applied to many computer vision tasks. However, existing object proposal generation methods often suffer from the problems of motion blur, low contrast, deformation, etc., when they are applied to video related tasks. In this paper, we propose an effective and highly accurate target-specific object proposal generation (TOPG) method, which takes full advantage of the context information of a video to alleviate these problems. Specifically, we propose to generate target-specific object proposals by integrating the information of two important objectness cues: colors and edges, which are complementary to each other for different challenging environments in the process of generating object proposals. As a result, the recall of the proposed TOPG method is significantly increased. Furthermore, we propose an object proposal ranking strategy to increase the rank accuracy of the generated object proposals. The proposed TOPG method has yielded significant recall gain (about 20%-60% higher) compared with several state-of-the-art object proposal methods on several challenging visual tracking datasets. Then, we apply the proposed TOPG method to the task of visual tracking and propose a TOPG-based tracker (called as TOPGT), where TOPG is used as a sample selection strategy to select a small number of high-quality target candidates from the generated object proposals. Since the object proposals generated by the proposed TOPG cover many hard negative samples and positive samples, these object proposals can not only be used for training an effective classifier, but also be used as target candidates for visual tracking. Experimental results show the superior performance of TOPGT for visual tracking compared with several other state-of-the-art visual trackers (about 3%-11% higher than the winner of the VOT2015 challenge in term of distance precision).
We propose a new context-aware correlation filter based tracking framework to achieve both high computational speed and state-of-the-art performance among real-time trackers. The major contribution to the high computational speed lies in the proposed deep feature compression that is achieved by a context-aware scheme utilizing multiple expert auto-encoders; a context in our framework refers to the coarse category of the tracking target according to appearance patterns. In the pre-training phase, one expert auto-encoder is trained per category. In the tracking phase, the best expert auto-encoder is selected for a given target, and only this auto-encoder is used. To achieve high tracking performance with the compressed feature map, we introduce extrinsic denoising processes and a new orthogonality loss term for pre-training and fine-tuning of the expert auto-encoders. We validate the proposed context-aware framework through a number of experiments, where our method achieves a comparable performance to state-of-the-art trackers which cannot run in real-time, while running at a significantly fast speed of over 100 fps.
Tracking humans that are interacting with the other subjects or environment remains unsolved in visual tracking, because the visibility of the human of interests in videos is unknown and might vary over time. In particular, it is still difficult for state-of-the-art human trackers to recover complete human trajectories in crowded scenes with frequent human interactions. In this work, we consider the visibility status of a subject as a fluent variable, whose change is mostly attributed to the subject's interaction with the surrounding, e.g., crossing behind another object, entering a building, or getting into a vehicle, etc. We introduce a Causal And-Or Graph (C-AOG) to represent the causal-effect relations between an object's visibility fluent and its activities, and develop a probabilistic graph model to jointly reason the visibility fluent change (e.g., from visible to invisible) and track humans in videos. We formulate this joint task as an iterative search of a feasible causal graph structure that enables fast search algorithm, e.g., dynamic programming method. We apply the proposed method on challenging video sequences to evaluate its capabilities of estimating visibility fluent changes of subjects and tracking subjects of interests over time. Results with comparisons demonstrate that our method outperforms the alternative trackers and can recover complete trajectories of humans in complicated scenarios with frequent human interactions.
An efficient iterative Earth Mover's Distance (iEMD) algorithm for visual tracking is proposed in this paper. The Earth Mover's Distance (EMD) is used as the similarity measure to search for the optimal template candidates in feature-spatial space in a video sequence. The computation of the EMD is formulated as the transportation problem from linear programming. The efficiency of the EMD optimization problem limits its use for visual tracking. To alleviate this problem, a transportation-simplex method is used for EMD optimization and a monotonically convergent iterative optimization algorithm is developed. The local sparse representation is used as the appearance models for the iEMD tracker. The maximum-alignment-pooling method is used for constructing a sparse coding histogram which reduces the computational complexity of the EMD optimization. The template update algorithm based on the EMD is also presented. The iEMD tracking algorithm assumes small inter-frame movement in order to guarantee convergence. When the camera is mounted on a moving robot, e.g., a flying quadcopter, the camera could experience a sudden and rapid motion leading to large inter-frame movements. To ensure that the tracking algorithm converges, a gyro-aided extension of the iEMD tracker is presented, where synchronized gyroscope information is utilized to compensate for the rotation of the camera. The iEMD algorithm's performance is evaluated using eight publicly available datasets. The performance of the iEMD algorithm is compared with seven state-of-the-art tracking algorithms based on relative percentage overlap. The robustness of this algorithm for large inter-frame displacements is also illustrated.
The tracking-by-detection framework consists of two stages, i.e., drawing samples around the target object in the first stage and classifying each sample as the target object or as background in the second stage. The performance of existing trackers using deep classification networks is limited by two aspects. First, the positive samples in each frame are highly spatially overlapped, and they fail to capture rich appearance variations. Second, there exists extreme class imbalance between positive and negative samples. This paper presents the VITAL algorithm to address these two problems via adversarial learning. To augment positive samples, we use a generative network to randomly generate masks, which are applied to adaptively dropout input features to capture a variety of appearance changes. With the use of adversarial learning, our network identifies the mask that maintains the most robust features of the target objects over a long temporal span. In addition, to handle the issue of class imbalance, we propose a high-order cost sensitive loss to decrease the effect of easy negative samples to facilitate training the classification network. Extensive experiments on benchmark datasets demonstrate that the proposed tracker performs favorably against state-of-the-art approaches.
Tracking a target of interest in both sparse and crowded environments is a challenging problem, not yet successfully addressed in the literature. In this paper, we propose a new long-term visual tracking algorithm, learning discriminative correlation filters and using an online classifier, to track a target of interest in both sparse and crowded video sequences. First, we learn a translation correlation filter using a multi-layer hybrid of convolutional neural networks (CNN) and traditional hand-crafted features. We combine advantages of both the lower convolutional layer which retains more spatial details for precise localization and the higher convolutional layer which encodes semantic information for handling appearance variations, and then integrate these with histogram of oriented gradients (HOG) and color-naming traditional features. Second, we include a re-detection module for overcoming tracking failures due to long-term occlusions by training an incremental (online) SVM on the most confident frames using hand-engineered features. This re-detection module is activated only when the correlation response of the object is below some pre-defined threshold. This generates high score detection proposals which are temporally filtered using a Gaussian mixture probability hypothesis density (GM-PHD) filter to find the detection proposal with the maximum weight as the target state estimate by removing the other detection proposals as clutter. Finally, we learn a scale correlation filter for estimating the scale of a target by constructing a target pyramid around the estimated or re-detected position using the HOG features. We carry out extensive experiments on both sparse and dense data sets which show that our method significantly outperforms state-of-the-art methods.
Recently, weighted patch representation has been widely studied for alleviating the impact of background information included in bounding box to improve visual tracking results. However, existing weighted patch representation models generally exploit spatial structure information among patches in each frame separately which ignore (1) unary featureof each patch and (2) temporal correlation among patches in different frames. To address this problem, we propose a novel unified temporal coherence and graph optimized ranking model for weighted patch representation in visual tracking problem. There are three main contributions of this paper. First, we propose to employ a flexible graph ranking for patch weight computation which exploits both structure information among patches and unary feature of each patch simultaneously. Second, we propose a new more discriminative ranking model by further considering the temporal correlation among patches in different frames. Third, a neighborhood preserved, low-rank graph is learned and incorporated to build a unified optimized ranking model. Experiments on two benchmark datasets show the benefits of our model.
We propose a new framework that extends the standard Probability Hypothesis Density (PHD) filter for multiple targets having $N\geq2$ different types based on Random Finite Set theory, taking into account not only background clutter, but also confusions among detections of different target types, which are in general different in character from background clutter. Under Gaussianity and linearity assumptions, our framework extends the existing Gaussian mixture (GM) implementation of the standard PHD filter to create a N-type GM-PHD filter. The methodology is applied to real video sequences by integrating object detectors' information into this filter for two scenarios. For both cases, Munkres's variant of the Hungarian assignment algorithm is used to associate tracked target identities between frames. This approach is evaluated and compared to both raw detection and independent GM-PHD filters using the Optimal Sub-pattern Assignment metric and discrimination rate. This shows the improved performance of our strategy on real video sequences.
We propose a new long-term tracking performance evaluation methodology and present a new challenging dataset of carefully selected sequences with many target disappearances. We perform an extensive evaluation of six long-term and nine short-term state-of-the-art trackers, using new performance measures, suitable for evaluating long-term tracking - tracking precision, recall and F-score. The evaluation shows that a good model update strategy and the capability of image-wide re-detection are critical for long-term tracking performance. We integrated the methodology in the VOT toolkit to automate experimental analysis and benchmarking and to facilitate the development of long-term trackers.