BOBBY2: Buffer Based Robust High-Speed Object Tracking

by   Keifer Lee, et al.

In this work, a novel high-speed single object tracker that is robust against non-semantic distractor exemplars is introduced; dubbed BOBBY2. It incorporates a novel exemplar buffer module that sparsely caches the target's appearance across time, enabling it to adapt to potential target deformation. As for training, an augmented ImageNet-VID dataset was used in conjunction with the one cycle policy, enabling it to reach convergence with less than 2 epoch worth of data. For validation, the model was benchmarked on the GOT-10k dataset and on an additional small, albeit challenging custom UAV dataset collected with the TU-3 UAV. We demonstrate that the exemplar buffer is capable of providing redundancies in case of unintended target drifts, a desirable trait in any middle to long term tracking. Even when the buffer is predominantly filled with distractors instead of valid exemplars, BOBBY2 is capable of maintaining a near-optimal level of accuracy. BOBBY2 manages to achieve a very competitive result on the GOT-10k dataset and to a lesser degree on the challenging custom TU-3 dataset, without fine-tuning, demonstrating its generalizability. In terms of speed, BOBBY2 utilizes a stripped down AlexNet as feature extractor with 63 less parameters than a vanilla AlexNet, thus being able to run at a competitive 85 FPS.


page 4

page 5

page 6


Multi-Template Temporal Siamese Network for Long-Term Object Tracking

Siamese Networks are one of most popular visual object tracking methods ...

Learning Mobile CNN Feature Extraction Toward Fast Computation of Visual Object Tracking

In this paper, we construct a lightweight, high-precision and high-speed...

EnKCF: Ensemble of Kernelized Correlation Filters for High-Speed Object Tracking

Computer vision technologies are very attractive for practical applicati...

Kernalised Multi-resolution Convnet for Visual Tracking

Visual tracking is intrinsically a temporal problem. Discriminative Corr...

The Second-place Solution for CVPR 2022 SoccerNet Tracking Challenge

This is our second-place solution for CVPR 2022 SoccerNet Tracking Chall...

Towards Enabling High-Five Over WiFi

The next frontier for immersive applications is enabling sentience over ...

Uniform Object Rearrangement: From Complete Monotone Primitives to Efficient Non-Monotone Informed Search

Object rearrangement is a widely-applicable and challenging task for rob...

Please sign up or login with your details

Forgot password? Click here to reset