DeepSORT extends simple motion tracking with a learned appearance feature, so when objects cross or vanish briefly it can re-match them by how they look. It is a common, dependable baseline for multi-object tracking in surveillance and analytics.
Definition
A widely used tracker that combines motion prediction with an appearance fingerprint to keep IDs stable through brief occlusions.
DeepSORT extends simple motion tracking with a learned appearance feature, so when objects cross or vanish briefly it can re-match them by how they look. It is a common, dependable baseline for multi-object tracking in surveillance and analytics.
Also known as
Deep SORT
Specialist software house for video, real-time and AI products. Founded 2005. 50 in-house engineers.
