Pixel-wise object tracking

TL;DR

This paper introduces a real-time pixel-wise object tracking framework that combines global attention and local segmentation models with LSTM structures, enabling efficient tracking of anonymous objects in noisy backgrounds without online refinement.

Contribution

The novel framework integrates global and local models with LSTMs and an iterative training strategy, eliminating the need for online updates and improving efficiency.

Findings

Effective tracking on challenging VOT dataset

Real-time performance achieved

No online refinement needed for specific objects

Abstract

In this paper, we propose a novel pixel-wise visual object tracking framework that can track any anonymous object in a noisy background. The framework consists of two submodels, a global attention model and a local segmentation model. The global model generates a region of interests (ROI) that the object may lie in the new frame based on the past object segmentation maps, while the local model segments the new image in the ROI. Each model uses a LSTM structure to model the temporal dynamics of the motion and appearance, respectively. To circumvent the dependency of the training data between the two models, we use an iterative update strategy. Once the models are trained, there is no need to refine them to track specific objects, making our method efficient compared to online learning approaches. We demonstrate our real time pixel-wise object tracking framework on a challenging VOT dataset