Explore the vast range of titles available.

Short-term tracking is an open and challenging problem for which discriminative correlation filters (DCF) have shown excellent performance. We introduce the channel and spatial reliability concepts to DCF tracking and provide a learning algorithm for its efficient and seamless integration in the filter update and the tracking process. The spatial reliability map adjusts the filter support to the part of the object suitable for tracking. This both allows to enlarge the search region and improves tracking of non-rectangular objects. Reliability scores reflect channel-wise quality of the learned filters and are used as feature weighting coefficients in localization. Experimentally, with only two simple standard feature sets, HoGs and colornames, the novel CSR-DCF method—DCF with channel and spatial reliability—achieves state-of-the-art results on VOT 2016, VOT 2015 and OTB100. The CSR-DCF runs close to real-time on a CPU.

Conceptual models are used to communicate information about a domain during the development of information systems. In two experimental studies using business process models, we demonstrate how eye tracking can contribute to understanding the cognitive processes by which readers use conceptual modeling scripts to perform problem solving tasks. In the first study, we compare scripts generated using two process modeling grammars and demonstrate how attention paid to specific parts of scripts generated using grammar variations, and differences in visual association between parts of a diagram, account for task performance. In the second study, we use a combination of eye tracking and verbal protocol analysis to examine how visual association between parts of conceptual modeling scripts can indicate cognitive integration while performing problem solving tasks. The studies show that task performance can be explained with different mental processes, reflected in specific eye tracking behavior, where scripts developed following different rules invoke different cognitive processes. We show that attention can be measured by eye tracking and can explain task performance. In addition, we show that visual association (which is observable) between parts of a modeling script involves cognitive integration (which is not observable). This finding can be used to improve conceptual modeling grammars in several ways, including understanding the effects of alternative visual arrangements of models on how effectively they communicate domain knowledge for particular tasks, and guiding the design of visual modeling notations.

Cross-view multi-object tracking aims to link objects between frames and camera views with substantial overlaps. Although cross-view multi-object tracking has received increased attention in recent years, existing datasets still have several issues, including (1) missing real-world scenarios, (2) lacking diverse scenes, (3) containing a limited number of tracks, (4) comprising only static cameras, and (5) lacking standard benchmarks, which hinder the investigation and comparison of cross-view tracking methods. To solve the aforementioned issues, we introduce DIVOTrack: a new cross-view multi-object tracking dataset for DIVerse Open scenes with dense tracking pedestrians in realistic and non-experimental environments. Our DIVOTrack has fifteen distinct scenarios and 953 cross-view tracks, surpassing all cross-view multi-object tracking datasets currently available. Furthermore, we provide a novel baseline cross-view tracking method with a unified joint detection and cross-view tracking framework named CrossMOT, which learns object detection, single-view association, and cross-view matching with an all-in-one embedding model. Finally, we present a summary of current methodologies and a set of standard benchmarks with our DIVOTrack to provide a fair comparison and conduct a comprehensive analysis of current approaches and our proposed CrossMOT. The dataset and code are available at https://github.com/shengyuhao/DIVOTrack.

Purpose The purpose of this paper is to propose an effective and economical management platform to realize real-time tracking and tracing for prepackaged food supply chain based on Internet of Things (IoT) technologies, and finally ensure a benign and safe food consumption environment. Design/methodology/approach Following service-oriented architecture, a flexible layered architecture of tracking and tracing platform for prepackaged food is developed. Besides, to reduce the implementation cost while realizing fine-grained tracking and tracing, an integrated solution of using both the QR code and radio-frequency identification (RFID) tag is proposed. Furthermore, Extensible Markup Language (XML) is adopted to facilitate the information sharing among applications and stakeholders. Findings The validity of the platform has been evaluated through a case study. First, the proposed platform is proved highly effective on realizing prepackaged food tracking and tracing throughout its supply chain, and can benefit all the stakeholders involved. Second, the integration of the QR code and RFID technologies is proved to be economical and could well ensure the real-time data collection. Third, the XML-based method is efficient to realize information sharing during the whole process. Originality/value The contributions of this paper lie in three aspects. First, the technical architecture of IoT-based tracking and tracing platform is developed. It could realize fine-grained tracking and tracing and could be flexible to adapt in many other areas. Second, the solution of integrating the QR code and RFID technologies is proposed, which could greatly decrease the cost of adopting the platform. Third, this platform enables the information sharing among all the involved stakeholders, which will further facilitate their cooperation on guaranteeing the quality and safety of prepackaged food.

Purpose This paper aims to investigate the problem of adaptive bipartite tracking control in nonlinear networked multi-agent systems (MASs) under the influence of periodic disturbances. It considers both cooperative and competitive relationships among agents within the MASs. Design/methodology/approach In response to the inherent limitations of practical systems regarding transmission resources, this paper introduces a novel approach. It addresses both control signal transmission and triggering conditions, presenting a two-bit-triggered control method aimed at conserving system transmission resources. Additionally, a command filter is incorporated to address the problem of complexity explosion. Furthermore, to model the uncertain nonlinear dynamics affected by time-varying periodic disturbances, this paper combines Fourier series expansion and radial basis function neural networks. Finally, the effectiveness of the proposed methodology is demonstrated through simulation results. Findings Based on neural networks and command filter control method, an adaptive two-bit-triggered bipartite control strategy for nonlinear networked MASs is proposed. Originality/value The proposed control strategy effectively addresses the challenges of limited transmission resources, nonlinear dynamics and periodic disturbances in networked MASs. It guarantees the boundedness of all signals within the closed-loop system while also ensuring effective bipartite tracking performance.

Single object tracking (SOT) is a fundamental problem in computer vision, with a wide range of applications, including autonomous driving, augmented reality, and robot navigation. The robustness of SOT faces two main challenges: tiny target and fast motion. These challenges are especially manifested in videos captured by unmanned aerial vehicles (UAV), where the target is usually far away from the camera and often with significant motion relative to the camera. To evaluate the robustness of SOT methods, we propose BioDrone—the first bionic drone-based visual benchmark for SOT. Unlike existing UAV datasets, BioDrone features videos captured from a flapping-wing UAV system with a major camera shake due to its aerodynamics. BioDrone hence highlights the tracking of tiny targets with drastic changes between consecutive frames, providing a new robust vision benchmark for SOT. To date, BioDrone offers the largest UAV-based SOT benchmark with high-quality fine-grained manual annotations and automatically generates frame-level labels, designed for robust vision analyses. Leveraging our proposed BioDrone, we conduct a systematic evaluation of existing SOT methods, comparing the performance of 20 representative models and studying novel means of optimizing a SOTA method (KeepTrack Mayer et al. in: Proceedings of the IEEE/CVF international conference on computer vision, pp. 13444–13454, 2021) for robust SOT. Our evaluation leads to new baselines and insights for robust SOT. Moving forward, we hope that BioDrone will not only serve as a high-quality benchmark for robust SOT, but also invite future research into robust computer vision. The database, toolkits, evaluation server, and baseline results are available at http://biodrone.aitestunion.com.

This paper investigates a robust adaptive second-order sliding mode control method for tracking problem of a class of uncertain linear systems with matched and unmatched disturbances. The fundamental idea of the suggested control method is that the discontinuous sign function is used for the time-derivative of the control signal and hence the smooth control input achieved after an integration process is continuous and removes the chattering problem. Using a PID sliding surface, the finite-time convergence of output tracking errors is obtained. The adaptive gain-tuning control law removes the necessity of gaining information about the upper bounds of the external disturbances. The control system is in the sliding mode and then, tracking errors converge to the origin in a finite time under the presence of the external disturbances. Simulation results on an uncertain numerical system and a turntable servo-system are presented to indicate the effectiveness and feasibility of the proposed scheme.

In this paper, we formulate object tracking in a particle filter framework as a structured multi-task sparse learning problem, which we denote as Structured Multi-Task Tracking (S-MTT). Since we model particles as linear combinations of dictionary templates that are updated dynamically, learning the representation of each particle is considered a single task in Multi-Task Tracking (MTT). By employing popular sparsity-inducing mixed norms and we regularize the representation problem to enforce joint sparsity and learn the particle representations together. As compared to previous methods that handle particles independently, our results demonstrate that mining the interdependencies between particles improves tracking performance and overall computational complexity. Interestingly, we show that the popular tracker (Mei and Ling, IEEE Trans Pattern Anal Mach Intel 33(11):2259–2272, 2011 ) is a special case of our MTT formulation (denoted as the tracker) when Under the MTT framework, some of the tasks (particle representations) are often more closely related and more likely to share common relevant covariates than other tasks. Therefore, we extend the MTT framework to take into account pairwise structural correlations between particles (e.g. spatial smoothness of representation) and denote the novel framework as S-MTT. The problem of learning the regularized sparse representation in MTT and S-MTT can be solved efficiently using an Accelerated Proximal Gradient (APG) method that yields a sequence of closed form updates. As such, S-MTT and MTT are computationally attractive. We test our proposed approach on challenging sequences involving heavy occlusion, drastic illumination changes, and large pose variations. Experimental results show that S-MTT is much better than MTT, and both methods consistently outperform state-of-the-art trackers.

This paper proves the uncertainty bound for the multiple Gaussian functions, termed multiple Gaussians Uncertainty (MGU), which significantly generalizes the uncertainty principle for the single Gaussian function. First, as a theoretical contribution, we prove that the momentum (velocity) and position for the sum of multiple Gaussians wave function are theoretically bounded. Second, as for a practical application, we show that the bound can be well exploited for object tracking to detect anomalies of local movement in an online learning framework. By integrating MGU with a given object tracker, we demonstrate that uncertainty principle can provide remarkable robustness in tracking. Extensive experiments are done to show that the proposed MGU can significantly help base trackers overcome the object drifting and reach state-of-the-art results.

Multiple features’ integration and context structure of unlabeled data have proven their effectiveness in enhancing similarity measures in many applications of computer vision. However, in similarity based object tracking, integration of multiple features has been rarely studied. In contrast to conventional tracking approaches that utilize pairwise similarity for template matching, our approach contributes in two different aspects. First, multiple features are integrated into a unified similarity to enhance the discriminative ability of similarity measurements. Second, the neighborhood context of the samples in forthcoming frame are employed to further improve the measurements. We utilize a diffusion process on a tensor product graph to achieve these goals. The obtained approach is validated on numerous challenging video sequences, and the experimental results demonstrate that it outperforms state-of-the-art t racking methods.