RT Generic
T1 Addressing Multiple Object Tracking with Segmentation Masks
A1 Bendaña Gómez, Manuel
K1 Multiple object tracking
K1 Segmentation
K1 Deep learning
AB 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.
YR 2024
FD 2024
LK https://hdl.handle.net/10347/37791
UL https://hdl.handle.net/10347/37791
LA eng
DS Minerva
RD 23 abr 2026