Using Segmentation With Multi-Scale Selective Kernel for Visual Object Tracking

doi:10.1109/LSP.2022.3143360

Using Segmentation With Multi-Scale Selective Kernel for Visual Object Tracking

2022-01-01

10

PRE

AI

DOI：10.1109/LSP.2022.3143360

Original

Original request for help

Save

Abstract

En 中文

Generic visual object tracking is challenging due to various difficulties, e.g. scale variations and deformations. To solve those problems, we propose a novel multi-scale selective kernel module for tracking, which contains small-scale and large-scale branches to model the target at different scales and attention mechanism to capture the more effective appearance information of the target. In our module, we cascade multiple small-scale convolutional blocks as an equivalent large-scale branch to extract large-scale features of the target effectively. Besides, we present a hybrid strategy for feature selection to extract significant information from features of different scales. Based on the current excellent segmentation tracking framework, we propose a novel tracking network that leverages our module at multiple places in the up-sample phase to construct a more accurate and robust appearance model. Extensive experimental results show that our tracker outperforms other state-of-the-art trackers on multiple challenging benchmarks including VOT2018, TrackingNet, DAVIS-2017, and YouTube-VOS-2018 while achieves real-time tracking.

Keywords:

Target tracking

Feature extraction

Kernel

Object tracking

Benchmark testing

Annotations

Convolution

Feature selection

object tracking

selective ker-nel

video segmentation

Using Segmentation With Multi-Scale Selective Kernel for Visual Object Tracking

Abstract

Journal

Organization