Gait 3 is a tri-modal: Event-based, RGB, and Thermal database for gait recognition (Identifying people by analysis of the way they walk). This database is the first that contains event-camera acquisition, simultaneously with conventional RGB and thermal videos.
The database was collected from 56 subjects and contains recordings of people in three variations: normal walking, quick walking, and walking with a backpack. For each variation, the subject is recorded twice, walking from left to right and walking from right to left.
For privacy purposes, faces in RGB recordings are blurred.
support
If you have any question or request regarding the Gait 3 Database, please contact Prof. Jean-Luc DUGELAY via jld@eurecom.fr