Bristol Egocentric Object Interactions Dataset

Release Date: July 2014 - New Annotations: June 2016

Dima Damen, Teesid Leelasawassuk, Osian Haines, Michael Wray, Davide Moltisanti, Andrew Calway and Walterio Mayol-Cuevas

Bristol Egocentric Object Interactions Dataset - Sample Images

Hardware Setup: The wearable gaze tracker hardware (ASL Mobile Eye XG) consists of two cameras sharing a half-mirror, one looking at the scene and another looking at the eye. After calibration, the scene images are synchronised with, if available, 2D gaze points.

Locations: Six locations were chosen: kitchen (K), workspace (W), laser printer (P), corridor with a locked door (D), cardiac gym (G) and weight-lifting machine (M) (Fig. 3). For the first four locations (K, W, P, D), sequences from five different operators were recorded, and from three operators for the last two locations (G, M). Two sequences were recorded for each operator.

Dataset Statistics
LocationNumber of SequencesAvg. Sequence length (in frames)Avg. Percentage of Frames with Gaze Fixation Data
Kitchen10 (5 operators)190558.9 %
Workspace10 (5 operators)122161.9 %
Printer10 (5 operators)59670.5 %
Corridor with Locked Door10 (5 operators)30356.2 %
Cardiac Gym9 (3 operators)5183 66.7 %
Weight-Lifting Machine9 (3 operators)2059 14.6 %

Verbal Instructions Given to Operators
LocationVerbal Instructions with fixed [] and moveable () objects
KitchenPrepare coffee using the machine, place the cup on the mat and add sugar
[tap, coffee machine, heat mat, cutlery drainer], (cup, sugar jar)
WorkspacePlug the screwdriver for charging and place the tape in the red box
[Socket, Box], (screwdriver, charger, tape)
PrinterCheck the printer is loaded with paper manually and using the keypad
[drawer, keypad]
Corridor with DoorGo through the locked door
[door lock, door handle]
Cardiac GymUse the treadmill and the bicycle next to it
[treadmill panel, bicycle panel]
Weigt-lifting MachineAdjust the seat, chest pad and weight then use the machine
[seat adjuster, pad adjuster, weight adjuster]