Deep Learning of Appearance Affinity for Multi-Object Tracking and Re-Identification: A Comparative View

Deep Learning of Appearance Affinity for Multi-Object Tracking and Re-Identification: A Comparative View

Recognizing the identity of a query individual in a surveillance sequence is the core of Multi-Object Tracking (MOT) and Re-Identification (Re-Id) algorithms. Both tasks can be addressed by measuring the appearance affinity between people observations with a deep neural model. Nevertheless, the diff...

Full description

Bibliographic Details
Main Authors: María J. Gómez-Silva, Arturo de la Escalera, José M. Armingol
Format: Article
Language:English
Published: MDPI AG 2020-10-01
Series:Electronics
Subjects:
appearance affinity
triplet model
contrastive loss function
deep convolutional neural network
re-identification
multi-object tracking
Online Access:https://www.mdpi.com/2079-9292/9/11/1757

Internet

https://www.mdpi.com/2079-9292/9/11/1757

Similar Items