Back to Search Start Over

TICNet: A Target-Insight Correlation Network for Object Tracking

Authors :
Chia-Wen Lin
Wu Liu
Jun Chen
Chao Liang
Ge Li
Ruan Weijian
Mang Ye
Yi Wu
Source :
IEEE Transactions on Cybernetics. 52:12150-12162
Publication Year :
2022
Publisher :
Institute of Electrical and Electronics Engineers (IEEE), 2022.

Abstract

Recently, the correlation filter (CF) and Siamese network have become the two most popular frameworks in object tracking. Existing CF trackers, however, are limited by feature learning and context usage, making them sensitive to boundary effects. In contrast, Siamese trackers can easily suffer from the interference of semantic distractors. To address the above problems, we propose an end-to-end target-insight correlation network (TICNet) for object tracking, which aims at breaking the above limitations on top of a unified network. TICNet is an asymmetric dual-branch network involving a target-background awareness model (TBAM), a spatial-channel attention network (SCAN), and a distractor-aware filter (DAF) for end-to-end learning. Specifically, TBAM aims to distinguish a target from the background in the pixel level, yielding a target likelihood map based on color statistics to mine distractors for DAF learning. SCAN consists of a basic convolutional network, a channel-attention network, and a spatial-attention network, aiming to generate attentive weights to enhance the representation learning of the tracker. Especially, we formulate a differentiable DAF and employ it as a learnable layer in the network, thus helping suppress distracting regions in the background. During testing, DAF, together with TBAM, yields a response map for the final target estimation. Extensive experiments on seven benchmarks demonstrate that TICNet outperforms the state-of-the-art methods while running at real-time speed.

Details

ISSN :
21682275 and 21682267
Volume :
52
Database :
OpenAIRE
Journal :
IEEE Transactions on Cybernetics
Accession number :
edsair.doi.dedup.....b65615f823ae99b4d23b96147fe41805