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

TL;DR

SiamFC++ introduces a set of target estimation guidelines for visual tracking, leading to a robust, accurate, and real-time tracker that achieves state-of-the-art results across multiple benchmarks.

Contribution

The paper proposes practical guidelines for target state estimation in visual tracking and designs SiamFC++ based on these, improving robustness and accuracy.

Findings

Achieves state-of-the-art performance on five benchmarks.

Runs at over 90 FPS on large-scale datasets.

Demonstrates the effectiveness of the proposed guidelines.

Abstract

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 .