Long-term Tracking Performance Research Articles

Effective Local and Global Search for Fast Long-Term Tracking.

Compared with short-term tracking, long-term tracking remains a challenging task that usually requires the tracking algorithm to track targets within a local region and re-detect targets over the entire image. However, few works have been done and their performances have also been limited. In this paper, we present a novel robust and real-time long-term tracking framework based on the proposed local search module and re-detection module. The local search module consists of an effective bounding box regressor to generate a series of candidate proposals and a target verifier to infer the optimal candidate with its confidence score. For local search, we design a long short-term updated scheme to improve the target verifier. The verification capability of the tracker can be improved by using several templates updated at different times. Based on the verification scores, our tracker determines whether the tracked object is present or absent and then chooses the tracking strategies of local or global search, respectively, in the next frame. For global re-detection, we develop a novel re-detection module that can estimate the target position and target size for a given base tracker. We conduct a series of experiments to demonstrate that this module can be flexibly integrated into many other tracking algorithms for long-term tracking and that it can improve long-term tracking performance effectively. Numerous experiments and discussions are conducted on several popular tracking datasets, including VOT, OxUvA, TLP, and LaSOT. The experimental results demonstrate that the proposed tracker achieves satisfactory performance with a real-time speed. Code is available at https://github.com/difhnp/ELGLT.

Learning Multifeature Correlation Filter and Saliency Redetection for Long-Term Object Tracking

Recently due to the good balance between performance and tracking speed, the discriminative correlation filter (DCF) has become a popular and excellent tracking method in short-term tracking. Computing the correlation of a response map can be efficiently performed in the Fourier domain by the discrete Fourier transform (DFT) of the input, where the DFT of an image has symmetry in the Fourier domain. However, most of the correlation filter (CF)-based trackers cannot deal with the tracking results and lack the effective mechanism to adjust the tracked errors during the tracking process, thus usually perform poorly in long-term tracking. In this paper, we propose a long-term tracking framework, which includes a tracking-by-detection part and redetection part. The tracking-by-detection part is built on a DCF framework, by integrating with a multifeature fusion model, which can effectively improve the discriminant ability of the correlation filter for some challenging situations, such as occlusion and color change. The redetection part can search the tracked object in a larger region and refine the tracking results after the tracking has failed. Benefited by the proposed redetection strategy, the tracking results are re-evaluated and refined, if it is necessary, in each frame. Moreover, the reliable estimation module in the redetection part can effectively identify whether the tracking results are correct and determine whether the redetector needs to open. The proposed redetection part utilizes a saliency detection algorithm, which is fast and valid for object detection in a limited region. These two parts can be integrated into DCF-based tracking methods to improve the long-term tracking performance and robustness. Extensive experiments on OTB2015 and VOT2016 benchmarks show that our proposed long-term tracking method has a proven effectiveness and high efficiency compared with various tracking methods.

Data-Driven Joint Beam Selection and Power Allocation for Multiple Target Tracking

For the problem of joint beam selection and power allocation (JBSPA) for multiple target tracking (MTT), existing works tend to allocate resources only considering the MTT performance at the current tracking time instant. However, in this way, it cannot guarantee the long-term MTT performance in the future. If the JBSPA not only considers the tracking performance at the current tracking time instant but also at the future tracking time instant, the allocation results are theoretically able to enhance the long-term tracking performance and the robustness of tracking. Motivated by this, the JBSPA is formulated as a model-free Markov decision process (MDP) problem, and solved with a data-driven method in this article, i.e., deep reinforcement learning (DRL). With DRL, the optimal policy is given by learning from the massive interacting data of the DRL agent and environment. In addition, in order to ensure the information prediction performance of target state in maneuvering target scenarios, a data-driven method is developed based on Long-short term memory (LSTM) incorporating the Gaussian mixture model (GMM), which is called LSTM-GMM for short. This method can realize the state prediction by learning the regularity of nonlinear state transitions of maneuvering targets, where the GMM is used to describe the target motion uncertainty in LSTM. Simulation results have shown the effectiveness of the proposed method.

Event-triggered output-feedback adaptive tracking control of autonomous underwater vehicles using reinforcement learning

This paper investigates the event-triggered tracking control of fully actuated autonomous underwater vehicles (AUVs) in the vertical plane. Specifically, this paper studies the ETC in the sensor-to-controller channel, where the X-Z coordinates and the pitch angle are transmitted in an event-triggered manner. The greater communication saving is ensured. Additionally, the recently-raised problem of “jumps of virtual control laws” is solved by establishing an event-triggered adaptive neural observer. This observer can offer the benefit of state recovery, which conforms to the nautical practice. As the observer is co-located with the controller, a succinct triggering condition is devised to avoid the “Zeno” behavior and co-located with the sensors. To achieve the optimization of the long-term tracking performance, the reinforcement learning (RL) technique is performed by using the critic-actor method with the radial basis function (RBF) neural networks (NNs). The critic NN approximates the performance index and is transferred as the reinforcement signal to the actor NN, which accounts for the uncertainties. The closed-loop stability is analyzed based on the observer-based tracking errors, and all of them are proved to be semi-globally uniformly ultimately bounded (SGUUB). Finally, a numerical experiment substantiates the effectiveness of the proposed scheme.

Sparse Learning-Based Correlation Filter for Robust Tracking.

Many objective tracking methods are based on the framework of correlation filtering (CF) due to its high efficiency. In this paper, we propose a l2 -norm based sparse response regularization term to restrain unexpected crests in response for CF framework. CF trackers learn online to regress the region of interest into a Gaussian response. However, due to the uncertain transformations of tracked object, there are many unexpected crests in the response map. When the response of tracked object is corrupted by other crests, the tracker will lost the object. Therefore, the sparse response is used to increase the robustness to transformations of tracked object. Since the novel term is directly incorporated into the objective function of the CF framework, it can be used to improve the performance of many methods which are based on this framework. Moreover, from the solutions we derive, the new method will not increase the computational complexity. Through the experiments on benchmarks of OTB-100, TempleColor, VOT2016 and VOT2017, the proposed regularization term can improve the tracking performance of various CF trackers, including those based on standard discriminative CF framework and those based on context-aware CF framework. We also embed the sparse response regularization term in the state-of-the-art integrated tracker MCCT to test its generalization performance. Although MCCT is an expert integrated tracker and owns an exquisite algorithm for selecting experts, the experimental results show that our method can still improve its long-term tracking performance without increasing computational complexity.

Correlation filters based on temporal regularization and background awareness,

Information about background appearance and previous tracked frames is significant for effectively discriminating a target from a complex scene. In this paper, we propose a novel tracker called temporal regularization and background-aware correlation filter (TRBACF) tracker based on the theory of correlation filter. In the proposed TRBACF tracker, an improved circular shift operation for collecting training samples is used to obtain more background information, which can enhance the discrimination ability of the learned correlation filters. Furthermore, to ensure the long-term tracking performance, a temporal regularization term is added to the appearance model of the classical correlation filter. The developed appearance model can take advantage of the similarity of the filters in the adjacent frames and improve the learned filter to be more adaptive to variations in the scene. Extensive experimental results on various challenging videos demonstrate that the proposed TRBACF tracker achieves superior accuracy than some state-of-the-art trackers.

Energy- and Mobility-Aware Scheduling for Perpetual Trajectory Tracking

Energy-efficient location tracking with battery-powered devices using energy harvesting necessitates duty-cycling of GPS to prolong the system lifetime. We propose an energy- and mobility-aware scheduling framework that adapts to real-world dynamics to achieve optimal long-term tracking performance. To forecast energy, the framework uses an exponentially weighted moving average filter to compute a virtual energy budget for the remainder of the forecast period. The virtual energy budget is then used as input for our proposed information-based GPS sampling approach, which estimates the current tracking error through dead-reckoning and schedules a new GPS sample when the error exceeds a given threshold. In order to improve the long-term tracking performance, the threshold is adapted based on the current energy and movement trends to balance the expected information gain from a new GPS sample with its energy cost. We evaluate our approach on empirical traces from wild flying foxes and compare it to strategies that sample GPS using fixed and adaptive duty cycles and by using dead-reckoning with a fixed threshold. Our analysis shows that the proposed information-based GPS sampling strategy reduces the mean tracking error compared to existing methods and approaches the performance of the optimal offline sampling strategy.

Bright Polymer Dots Tracking Stem Cell Engraftment and Migration to Injured Mouse Liver.

Stem cell therapy holds promise for treatment of intractable diseases and injured organs. For clinical translation, it is pivotal to understand the homing, engraftment, and differentiation processes of stem cells in a living body. Here we report near-infrared (NIR) fluorescent semiconductor polymer dots (Pdots) for bright labeling and tracking of human mesenchymal stem cells (MSCs). The Pdots exhibit narrow-band emission at 775 nm with a quantum yield of 22%, among the highest value for various NIR probes. The Pdots together with a cell penetrating peptide are able to track stem cells over two weeks without disturbing their multipotent properties, as confirmed by the analyses on cell proliferation, differentiation, stem-cell markers, and immunophenotyping. The in vivo cell tracking was demonstrated in a liver-resection mouse model, which indicated that the Pdot-labeled MSCs after tail-vein transplantation were initially trapped in lung, gradually migrated to the injured liver, and then proliferated into cell clusters. Liver-function analysis and histological examination revealed that the inflammation induced by liver resection was apparently decreased after stem cell transplantation. With the bright labeling, superior biocompatibility, and long-term tracking performance, the Pdot probes are promising for stem cell research and regenerative medicine.