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

14 Nov 2019  ·  Yinda Xu, Zeyu Wang, Zuoxin Li, Ye Yuan, Gang Yu ·

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. After 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. Code and models are available at: https://github.com/MegviiDetection/video_analyst .

PDF Abstract

Results from the Paper


Ranked #2 on Visual Object Tracking on VOT2017/18 (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Visual Object Tracking GOT-10k SiamFC++ Average Overlap 61.0 # 12
Success Rate 0.5 74.2 # 7
Visual Object Tracking TrackingNet SiamFC++ Precision 68.5 # 12
Normalized Precision 79.8 # 12
Accuracy 74.5 # 8
Visual Object Tracking VOT2017/18 SiamFC++ Expected Average Overlap (EAO) 0.428 # 2

Methods


No methods listed for this paper. Add relevant methods here