AFAT: Adaptive Failure-Aware Tracker for Robust Visual Object Tracking

by   Tianyang Xu, et al.
University of Surrey
Jiangnan University

Siamese approaches have achieved promising performance in visual object tracking recently. The key to the success of Siamese trackers is to learn appearance-invariant feature embedding functions via pair-wise offline training on large-scale video datasets. However, the Siamese paradigm uses one-shot learning to model the online tracking task, which impedes online adaptation in the tracking process. Additionally, the uncertainty of an online tracking response is not measured, leading to the problem of ignoring potential failures. In this paper, we advocate online adaptation in the tracking stage. To this end, we propose a failure-aware system, realised by a Quality Prediction Network (QPN), based on convolutional and LSTM modules in the decision stage, enabling online reporting of potential tracking failures. Specifically, sequential response maps from previous successive frames as well as current frame are collected to predict the tracking confidence, realising spatio-temporal fusion in the decision level. In addition, we further provide an Adaptive Failure-Aware Tracker (AFAT) by combing the state-of-the-art Siamese trackers with our system. The experimental results obtained on standard benchmarking datasets demonstrate the effectiveness of the proposed failure-aware system and the merits of our AFAT tracker, with outstanding and balanced performance in both accuracy and speed.


Efficient Adversarial Attacks for Visual Object Tracking

Visual object tracking is an important task that requires the tracker to...

Updatable Siamese Tracker with Two-stage One-shot Learning

Offline Siamese networks have achieved very promising tracking performan...

DASTSiam: Spatio-Temporal Fusion and Discriminative Augmentation for Improved Siamese Tracking

Tracking tasks based on deep neural networks have greatly improved with ...

Real-Time Visual Object Tracking via Few-Shot Learning

Visual Object Tracking (VOT) can be seen as an extended task of Few-Shot...

Domain Adaptive SiamRPN++ for Object Tracking in the Wild

Benefit from large-scale training data, recent advances in Siamese-based...

SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks

Siamese network based trackers formulate tracking as convolutional featu...

DeepScale: An Online Frame Size Adaptation Framework to Accelerate Visual Multi-object Tracking

In surveillance and search and rescue applications, it is important to p...

Please sign up or login with your details

Forgot password? Click here to reset