Large Margin Structured Convolution Operator for Thermal Infrared Object Tracking

TL;DR

This paper introduces LMSCO, a novel large margin structured convolution operator for thermal infrared object tracking, combining SOSVM and DCF advantages to improve accuracy and robustness in challenging TIR conditions.

Contribution

The paper presents the first integration of SOSVM and DCF for TIR tracking, employing deep features and a collaborative optimization strategy for enhanced performance.

Findings

Outperforms most state-of-the-art trackers in accuracy and robustness

Achieves higher frame rates in thermal infrared tracking

Demonstrates effectiveness on VOT-TIR2015 and VOT-TIR2016 benchmarks

Abstract

Compared with visible object tracking, thermal infrared (TIR) object tracking can track an arbitrary target in total darkness since it cannot be influenced by illumination variations. However, there are many unwanted attributes that constrain the potentials of TIR tracking, such as the absence of visual color patterns and low resolutions. Recently, structured output support vector machine (SOSVM) and discriminative correlation filter (DCF) have been successfully applied to visible object tracking, respectively. Motivated by these, in this paper, we propose a large margin structured convolution operator (LMSCO) to achieve efficient TIR object tracking. To improve the tracking performance, we employ the spatial regularization and implicit interpolation to obtain continuous deep feature maps, including deep appearance features and deep motion features, of the TIR targets. Finally, a collaborative optimization strategy is exploited to significantly update the operators. Our approach not only inherits the advantage of the strong discriminative capability of SOSVM but also achieves accurate and robust tracking with higher-dimensional features and more dense samples. To the best of our knowledge, we are the first to incorporate the advantages of DCF and SOSVM for TIR object tracking. Comprehensive evaluations on two thermal infrared tracking benchmarks, i.e. VOT-TIR2015 and VOT-TIR2016, clearly demonstrate that our LMSCO tracker achieves impressive results and outperforms most state-of-the-art trackers in terms of accuracy and robustness with sufficient frame rate.