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

• Published in: IEEE signal processing letters Vol. 29; pp. 553 - 557
• Main Authors: Bao, Feng, Cao, Yifei, Zhang, Shunli, Lin, Beibei, Zhao, Sicong
• Format: Journal Article
• Language: English
• Published: New York IEEE 2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Annotations; Benchmark testing; Convolution; Feature extraction; Feature selection; Kernel; Kernels; Modules; Object tracking; Optical tracking; Segmentation; selective ker-nel; Target tracking; Tracking networks; video segmentation
• ISSN: 1070-9908; 1558-2361
• DOI: 10.1109/LSP.2022.3143360

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.