Target tracking is popular in computer vision field. Although the classic BPNN completes targets tracking, its computation is complex and tracking accuracy is low when tracking scene is uncertain or complex. To deal with difficulties above, in this paper, we propose an innovative target tracking method combined adaptive α-β filter with robust BPNN. First, we utilize the adaptive α-β filter to compute the location region on optimal filtering parameters in prediction stage. Of course, the novel filter reduces the region and gives effective image information to the robust BPNN that has optimal number and weight of neurons as well as improved learning rate. Subsequently, the network makes an accurate recognition and sents back the updated positions of targets to the filter for the next cycle. Employing the novel interactive mechanism, the numerical study and experiments indicate that the proposed method has remarkable improvement on average performance in the uncertain and complex environment.

In most filtering algorithms involving measurement data association, handling the complex computations due to multiple hypotheses is necessary. This paper introduces a novel Trajectory Poisson Multi-Bernoulli (TPMB) filter for tracking extended targets, facilitated by a synergy between the model and the data. This filter can track extended targets under unknown process and measurement noise. Initially, on the model-driven side, we compute multi-model transition probabilities using the posterior probabilities from models at two consecutive time points with the targets in high maneuverability state. The accuracy of the tracking algorithm is improved by calculating the improved Interacting Multiple Model (IMM) transition probability at each time step. For the data-driven aspect, the Gate-control Belief Propagation (GBP) is set in the message- passing algorithm to reduce the running time of false hypothesis associations. Thus, it is unnecessary to consider all message information when computing the likelihood matrix for target-measurement associations. Subsequently, the posterior density function of the Adaptive Square Root Cubature Kalman Filter (ASCKF) is constructed to adaptively estimate unknown process and measurement noises, while importance sampling in the current particle filter further mitigates particle degradation. Experiments demonstrate that our algorithm reduces the running time of data associations, alleviates particle degradation, and more accurately tracks maneuvering targets under nonlinear conditions and estimates their states.

The Sage–Husa filter can estimate states of multitarget from available measurements. To address the imprecise estimations of the conventional Sage–Husa filter, an optimized method and its implementation are put forward in this study. Unlike previous approaches, the beta distribution for unknown detection profile is improved, and the transfer probability is applied to update the implicit probability of detection. With respect to the positive definiteness of the estimated covariance, the Cholesky decomposition is used in both prediction and update of the Sage–Husa filter. Recalling the estimated probability of detection, the track gate strategy in the proposed filtering framework is derived to distinguish clutter-generated and target-generated measurements. On the basis of updated measurements, both the state and the track of multitarget are achieved. Finally, the experiments of multitarget tracking are made to indicate the performance of the proposed Sage–Husa filtering method.

Owing to multi-target tracking in scenarios with nonlinearity, uncertain measurement model and high clutter density, the Poisson multi-Bernoulli mixture (PMBM) recursion is prone to unstable covariance propagation under nonlinear dynamics as well as uncertainty in measurement-to-target association caused by mismatched gate that causes erroneous updates from clutters. In the prediction stage, the singular value decomposition (SVD) is used in place of Cholesky factorization to construct and propagate the square-root covariance factor in the square-root cubature Kalman filter (SCKF), yielding a numerically stable square-root implementation. Then, the resulting SVD-SCKF is incorporated into the PMBM prediction step and used to propagate the Gaussian-mixture components of both the Poisson point process (PPP) intensity and the Bernoulli component in the Multi-Bernoulli mixture (MBM), yielding predicted means and covariances under nonlinear dynamics. An adaptive fading factor is determined from innovation statistics, and covariance inflation is performed to improve robustness under target maneuvers and model mismatch. In the update stage, the unknown measurement function is regressed by Gaussian process (GP) using historical state–measurement samples, yielding an equivalent measurement mapping and state-dependent uncertainty. Furthermore, the predicted measurement distribution is generated from the GP-based conditional measurement distribution with state prior approximated by SVD-SCKF cubature points. An adaptive gate is determined from the GP-based conditional measurement distribution, which is approximated by an equivalent ellipsoidal gate via fitting for screening the current measurements and filtering out clutter. Residual in-gate clutter measurements are handled via Bayesian target discrimination, where the posterior probability of measurement originated from target is employed as a weight and incorporated into association weights and update likelihoods. Simulation results further confirm the effectiveness and stability of the proposed filter in complex scenarios.

Aiming at the unstable performance on fast-moving and deformational target tracking in current kernel correlation filter (KCF), an innovative approach based on heterogeneous features fusion is proposed in this paper. Firstly, a histogram of oriented gradient is utilized to cater for motion state change in complex surveillance background. Combined with a colour-free template as a novel heterogeneous feature, the proposed approach improves the tracking performance on the fast-moving target in KCF. Subsequently, the optimized spatial regularization and quadruple block method are implemented in order to solve the difficulties of scale change and boundary effect in the cyclic matrix. The simulation results indicate that the proposed approach has better precision and success rate than other popular tracking algorithms when dealing with both fast motion and deformation on the platform of the object tracking benchmark and actual traffic datasets.

In view to the unstable navigation risk assessment and make the future navigation risk forecasting, an innovative decision and forecasting approach is put forward in this study. Different from the existing literature, at the current time step, we first deduce an enhanced evidence combination rule to integrate uncertain and conflicting evidences by using weighted basic probabilistic assignment and matrix operation. As a result, a stable decision is effectively achieved no matter what characteristics of the available evidences are. Further, an improved α-β filter is designed with its adaptive coefficients in the novel filtering framework in order to forecast the future navigation risk. What’s more, it is an excellent communication between the combined basic probabilistic assignment and the improved α-β filter for the first time. After the deep analysis of the computational complexity, a plenty of numeric simulations and actual experiments are provided to indicate the reliability and efficiency of the proposed approach.