Performance Measures of Covariance and Information Matrices in Resource Management for Target State Estimation

2012 ◽  
Vol 48 (3) ◽  
pp. 2594-2613 ◽  
Author(s):  
Chun Yang ◽  
Lance Kaplan ◽  
Erik Blasch
Keyword(s):  
Resource Management ◽  
State Estimation ◽  
Performance Measures ◽  
Target State ◽  
Information Matrices

scholarly journals SiamFC++: Towards Robust and Accurate Visual Tracking with Target Estimation Guidelines

2020 ◽  
Vol 34 (07) ◽  
pp. 12549-12556 ◽  
Author(s):  
Yinda Xu ◽  
Zeyu Wang ◽  
Zuoxin Li ◽  
Ye Yuan ◽  
Gang Yu
Keyword(s):  
State Estimation ◽  
Visual Tracking ◽  
High Performance ◽  
Large Scale ◽  
Careful Analysis ◽  
Tracking Problem ◽  
Target State ◽  
Classification Score ◽  
Practical Guidelines ◽  
Estimation Quality

Visual tracking problem demands to efficiently perform robust classification and accurate target state estimation over a given target at the same time. Former methods have proposed various ways of target state estimation, yet few of them took the particularity of the visual tracking problem itself into consideration. Based on a careful analysis, we propose a set of practical guidelines of target state estimation for high-performance generic object tracker design. Following these guidelines, we design our Fully Convolutional Siamese tracker++ (SiamFC++) by introducing both classification and target state estimation branch (G1), classification score without ambiguity (G2), tracking without prior knowledge (G3), and estimation quality score (G4). Extensive analysis and ablation studies demonstrate the effectiveness of our proposed guidelines. Without bells and whistles, our SiamFC++ tracker achieves state-of-the-art performance on five challenging benchmarks(OTB2015, VOT2018, LaSOT, GOT-10k, TrackingNet), which proves both the tracking and generalization ability of the tracker. Particularly, on the large-scale TrackingNet dataset, SiamFC++ achieves a previously unseen AUC score of 75.4 while running at over 90 FPS, which is far above the real-time requirement.

Sign in / Sign up

Export Citation Format

Share Document