Multiple Convolutional Features In Siamese Networks For Object Tracking

Abstract

Siamese trackers demonstrated high performance in object tracking due to their balance between accuracy and speed. Unlike classification-based CNNs, deep similarity networks are specifically designed to address the image similarity problem, and thus are inherently more appropriate for the tracking task. However, Siamese trackers mainly use the last convolutional layers for similarity analysis and target search, which restricts their performance. In this paper, we argue that using a single convolutional layer as feature representation is not an optimal choice in a deep similarity framework. We present a Multiple Features-Siamese Tracker (MFST), a novel tracking algorithm exploiting several hierarchical feature maps for robust tracking. Since convolutional layers provide several abstraction levels in characterizing an object, fusing hierarchical features allows to obtain a richer and more efficient representation of the target. Moreover, we handle the target appearance variations by cali

Stats

• citations7
• S2 citations—
• github stars2
• HF likes0
• heat score7.73
• arxiv keyli2021multiple

Related papers

• MFST: Multi-features Siamese Tracker (2021)0.95
• A Twofold Siamese Network For Real-time Object Tracking (2018)20.50
• Smiletrack: Similarity Learning For Occlusion-aware Multiple Object Tracking (2022)17.36
• Deep Similarity Metric Learning For Real-time Pedestrian Tracking (2018)0.00
• Object Cosegmentation Using Deep Siamese Network (2018)0.00
• An Experimental Evaluation Of Siamese Neural Networks For Robot Localization Using Omnidirectional Imaging In Indoor Environments (2024)6.34
• Mmf-track: Multi-modal Multi-level Fusion For 3D Single Object Tracking (2023)7.16
• Siamese Network Of Deep Fisher-vector Descriptors For Image Retrieval (2017)0.00