Recent years have witnessed the top performances of integrating multi-level features from the pre-trained convolutional neural network (CNN) into correlation filters framework. However, they still suffer from background interference in detection stage due to the large search region and contamination of training samples caused by inaccurate tracking. In this paper, to suppress the interference of background features in target detection stage, an effective spatial attention map (SAM) is proposed to differently weight the multi-hierarchical convolutional features from search region to obtain the attentional features. This way helps to reduce the filter values corresponding to background features. Moreover, we construct multiple elementary correlation filter (ECF) models on multi-hierarchical deep features from CNN to track the target in parallel. To further improve the tracking stability, a multi-model adaptive response fusion (MAF) mechanism is presented. The mechanism can adaptively choose the outputs of reliable ECF models for adaptive weighted fusion by evaluating the confidences of response maps generated by attentional features convolved with ECF models. Finally, to adapt the target appearance changes in the following frames and avoid model corruption, we propose an adaptive updating strategy for the updates of the SAM and ECF models. We perform comprehensive experiments on OTB-2013 and OTB-2015 datasets and the experimental results show the superiority of our algorithm over other 12 state-of-the-art approaches.INDEX TERMS Adaptive updating strategy, convolutional neural network, correlation filter, multi-model adaptive response fusion mechanism, object tracking, spatial attention map.
As the energy management system (EMS) participates in the closed-loop control of shipboard integrated power system (IPS), the information network of EMS is closely coupled with the power system and its characteristics affect power system performance significantly. To study the close-coupling relationship between the two systems, a cyber–physical co-simulation platform based on the high level architecture (HLA) framework is constructed in this paper. The proposed platform uses PSCAD and OPNET to simulate shipboard power system and information network respectively, and utilizes OPNET HLA nodes and PSCAD user-defined modules to implement co-simulation interfaces. In order to achieve a higher co-simulation precision without impairing efficiency, an optimized event-driven co-simulation synchronization method is also proposed. By pre-defining power system synchronization points and detecting information network synchronization points in the co-simulation process, both systems can be synchronized in time and the synchronization error is eliminated. Furthermore, the co-simulation efficiency is also improved by optimizing the data transmission in the synchronization process. A co-simulation model of shipboard power distribution network protection based on CAN bus communication is built and analyzed. Simulation results show that the proposed co-simulation platform and synchronization method are feasible and effective.
-In the process of virtual inertia control (VIC), the frequency regulation capability of the directly-driven wind turbine with permanent-magnet synchronous generator (D-PMSG) on wind farm is related to its rotor kinetic energy and capacity margin. This paper proposes the method for assessing the D-PMSG frequency regulation capability and defining its coefficient according to the operating state of wind power generators. In addition, the calculating method of parameters in VIC is also discussed according to the principles of primary frequency regulation and inertia response of synchronous generators. Then, by introducing the capability coefficient into the proportion-differential virtual inertia control (PD-VIC) for power coordination, a coordinated virtual inertia control (C-VIC) strategy is developed, with the consideration of the difference in frequency regulation capability between wind power generators. The proposed control method can not only give full play to the frequency regulation capability of wind power generators, decrease the movements of the pitch angle control system but also bring some self-coordination capability to different wind power generators thus to avoid a secondary drop in system frequency. The simulations and experiments prove the proposed method to be effective and practicable.
Object tracking is a vital topic in computer vision. Although tracking algorithms have gained great development in recent years, its robustness and accuracy still need to be improved. In this paper, to overcome single feature with poor representation ability in a complex image sequence, we put forward a multifeature integration framework, including the gray features, Histogram of Gradient (HOG), color-naming (CN), and Illumination Invariant Features (IIF), which effectively improve the robustness of object tracking. In addition, we propose a model updating strategy and introduce a skewness to measure the confidence degree of tracking result. Unlike previous tracking algorithms, we judge the relationship of skewness values between two adjacent frames to decide the updating of target appearance model to use a dynamic learning rate. This way makes our tracker further improve the robustness of tracking and effectively prevents the target drifting caused by occlusion and deformation. Extensive experiments on large-scale benchmark containing 50 image sequences show that our tracker is better than most existing excellent trackers in tracking performance and can run at average speed over 43 fps.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.