A Novel Guided Anchor Siamese Network for Arbitrary Target-of-Interest Tracking in Video-SAR

Video synthetic aperture radar (Video-SAR) allows continuous and intuitive observation and is widely used for radar moving target tracking. The shadow of a moving target has the characteristics of stable scattering and no location shift, making moving target tracking using shadows a hot topic. However, the existing techniques mainly rely on the appearance of targets, which is impractical and costly, especially for tracking targets of interest (TOIs) with high diversity and arbitrariness. Therefore, to solve this problem, we propose a novel guided anchor Siamese network (GASN) dedicated to arbitrary TOI tracking in Video-SAR. First, GASN searches for matching areas in the subsequent frames with the initial area of the TOI in the first frame are conducted, returning the most similar area using a matching function, which is learned from general training without TOI-related data. With the learned matching function, GASN can be used to track arbitrary TOIs. Moreover, we also constructed a guided anchor subnetwork, referred to as GA-SubNet, which employs the prior information of the first frame and generates sparse anchors of the same shape as the TOIs. The number of unnecessary anchors is therefore reduced to suppress false alarms. Our method was evaluated on simulated and real Video-SAR data. The experimental results demonstrated that GASN outperforms state-of-the-art methods, including two types of traditional tracking methods (MOSSE and KCF) and two types of modern deep learning techniques (Siamese-FC and Siamese-RPN). We also conducted an ablation experiment to demonstrate the effectiveness of GA-SubNet.

Adaptive robust control of moving-target tracking for marching tank based on constraint following

This paper is devoted to the constraint-following scheme for the moving-target tracking control problem of tank on move. The mission of tank on the battlefield is to find and shoot the armored vehicle, both conditions are required to accomplish this task: complete the process from finding a moving target (time-varying constraints) to pointing to it; keep the barrel stable under highly nonlinear disturbance (which is caused by the battlefield environment). Considering modeling uncertainty and initial condition deviation, an adaptive robust strategy based on Udwadia-Kalaba scheme is presented to solve the matters of target tracking and stable following. Considering the limitation of the analytical model, a tracking system model and a target movement model are built in virtual prototyping environment, complicated road condition, and real target motion state are restored by this method. The model-based control system and the three-dimensional model are combined to verify the feasibility of the control algorithm by the method of RecurDyn/Matlab. By this way, the barrel responds and follows the movement of the target stably within [Formula: see text] s under the action of the stabilization system, and the constraints are approximately satisfied under complex perturbations.

A Moving Target Tracking Control of Quadrotor UAV Based on Passive Control and Super-Twisting Sliding Mode Control

A novel asymptotic tracking controller for an underactuated quadrotor unmanned aerial vehicle (UAV) is proposed to solve a moving target tracking problem. Firstly, the control system is decoupled into the position control system and the attitude control system. Secondly, a method combined artificial potential field with passivity control (APF&PC) is introduced for the positioning system to achieve high-precision tracking of moving target at a fixed distance. Thirdly, a super-twisting sliding mode (STSM) method with an improved reaching law for the attitude system is applied to ensure that the attitude converges to the desired value. Furthermore, the stabilities of two subsystems are proved, and sufficient stability conditions are derived based on the passive method and Lyapunov method, respectively. Finally, simulation results of the moving target tracking verify the superiority and robustness of the proposed control method in the presence of parameter uncertainties and external disturbances.