Real-time siamese multiple object tracker with enhanced proposals. (March 2023)

• Record Type: Journal Article
• Authors: Vaquero, Lorenzo; Brea, Víctor M.; Mucientes, Manuel
• Is Part Of: Pattern recognition. Volume 135(2023)
• Publication Date: 2023-03
• Subjects: Multiple visual object tracking -- Siamese CNN -- Motion estimation; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2022.109141
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: A visual tracker for multiple-object motion estimation in real-time is proposed. A proposal engine that employs inertia, attention, and multi-resolution modules. A comparison head comprising an RPN and a multi-object penalization mechanism. Abstract: Maintaining the identity of multiple objects in real-time video is a challenging task, as it is not always feasible to run a detector on every frame. Thus, motion estimation systems are often employed, which either do not scale well with the number of targets or produce features with limited semantic information. To solve the aforementioned problems and allow the tracking of dozens of arbitrary objects in real-time, we propose SiamMOTION. SiamMOTION includes a novel proposal engine that produces quality features through an attention mechanism and a region-of-interest extractor fed by an inertia module and powered by a feature pyramid network. Finally, the extracted tensors enter a comparison head that efficiently matches pairs of exemplars and search areas, generating quality predictions via a pairwise depthwise region proposal network and a multi-object penalization module. SiamMOTION has been validated on five public benchmarks, achieving leading performance against current state-of-the-art trackers. Code available at: https://www.github.com/lorenzovaquero/SiamMOTION