Addressing Multiple Object Tracking with Segmentation Masks

Multiple Object Tracking (MOT) aims to locate all the objects from a video, assigning them the same identities across all frames. Traditionally, this problem was addressed following the Tracking by Detection (TbD) paradigm, using detections represented by bounding boxes. However, bounding boxes can...

Descripción completa

Detalles Bibliográficos
Autor: Bendaña Gómez, Manuel
Tipo de recurso: tesis de maestría
Fecha de publicación:2024
País:España
Institución:Universidad de Santiago de Compostela (USC)
Repositorio:Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
Idioma:inglés
OAI Identifier:oai:minerva.usc.gal:10347/37791
Acceso en línea:https://hdl.handle.net/10347/37791
Access Level:acceso abierto
Palabra clave:Multiple object tracking
Segmentation
Deep learning
1203 Ciencia de los ordenadores
Descripción
Sumario:Multiple Object Tracking (MOT) aims to locate all the objects from a video, assigning them the same identities across all frames. Traditionally, this problem was addressed following the Tracking by Detection (TbD) paradigm, using detections represented by bounding boxes. However, bounding boxes can contain information from several objects, something that does not happen with segmentation masks. This work takes the ByteTrack MOT system as a starting point. Our proposal, ByteTrackMask, integrates a class-agnostic segmentation method and a segmentation-based tracker in ByteTrack in order to rescue tracks that would have been lost. Results over validation sets of MOT challenge datasets provide improvements in MOT metrics of interest like MOTA, IDF1 and false negatives.