An Object Tracking Algorithm Based on the "Current" Statistical Model and the Multi-Feature Fusion

Abstract

Aimed at accurary and real-time object tracking under complex background,an object tracking algorithm based on multi feature fusion is proposed. Feature points tracking is used to reduce the match time and improve the real-time of tracking; To overcome the inaccuracy of a single feature tracking, the object model is presented by the color and texture features. For the traditional "current" statistical model in maneuvering object tracking defects, an improved algorithm which combined with adaptive kalman filter (AKF) is proposed to improve the tracking accuracy. Experimental results show that the proposed method is effective and robust under complex background, the object is similar to each other, the target was partial occlusion and when the object is maneuvering

Distributed consensus strong tracking filter for wireless sensor networks with model mismatches

“…To guarantee that y (Ã) i, k asymptotically converges to Y k , h k , S k , h H, k , h R, k , and h z, k , respectively, an internal cycle is added by step 2.2, which is a little different from Olfati-Saber, 2 where the value of T is related to the connectivity of WSNs. According to Wang et al, 21 when T = 5, y (Ã) i, k converges to the average value.…”

“…Second, we shift our attention to the DCSTF algorithm for sensor networks with model mismatches, the key role of which is to use a distributed way to adjust the time-variant fading factor to make the residual error sequences keep orthogonality with the state estimation errors until the variance of the state estimation errors reaches the minimum value. Third, because of model mismatches, the tracker uses the constant-velocity model 19 and the current statistic model 20,21 to track the target that actually moves with segment constant-acceleration model actually. 22 Finally, the simulation results are provided to show that although the tracker model mismatches the target model, the DCSTF algorithm has better state estimation accuracy and robustness in target tracking than DKF in current statistic model.…”

Developing a cost-effective test system for evaluating dynamic performance of articulated heavy vehicles

“…25 In comparison, the “current” statistical model relaxes the strict restrictions of the Wiener and Singer models for the target acceleration and is suitable for the case with more motion situations. 26–29 The “current” statistical model assumes the target acceleration over any sample interval to change in a limited and proper scope of its “current” value, which fully considers the features of motion continuity and consistency as the vehicle has. Therefore, the EKFs for the AHV are designed based on the “current” statistical model.…”

Modified qCurrentq Statisical Model Filtering Algorithm for Carrier Acceleration Calculation

“…filtering using the Kalman filtering process expressed as the formula (4) with the variance of the acceleration calculated by the formula (8).…”

“…The "Current" Statistical Model (CS) uses the modified Rayleigh Distribution to describe the "current" acceleration of the moving target, which can reflect the acceleration change of the target more effectively. At present, the model has been successfully applied in target tracking, track forecasting and other fields [7][8].…”