search

David0tt / DeepGTAV

A system to easily extract ground truth training data for different machine learning tasks from GTAV
GNU General Public License v3.0
89 stars 9 forks source link

I am curious about the format of the metadata. #3

Closed jongphago closed 2 years ago

jongphago commented 2 years ago

Hello. Thank you for the good research results you showed using synthetic data.

I would like to ask for information about the format of metadata.

The pre-generated dataset you posted was very helpful to me. Thank you.

<Sample of meta data>
a: -425.1471252441406
b: -559.9451293945312 
c: 77.26197814941406 
d: 50.85673904418945 
e: -427.5518493652344 
f: -558.969970703125 
g: 57.43088912963867 
h: -81.8794174194336 
i: -6.996013164520264 
j: 137.6229705810547 
k: 17 
l: 0 
m: 36 
n: EXTRASUNNY
David0tt commented 2 years ago

Hello.

The format of the metadata is:

[x y z heightAboveGround, campos_x, campos_y, campos_z, camrot_x, camrot_y, camrot_z, time_hours, time_min, time_sec, weather]

x,y,z: the location of the player vehicle in GTAV world coordinates. heightAboveGround: The height difference of the player vehicle to the ground (or water) campos_x, campos_y, campos_z: The positions of the camera in world coordinates. camrot_x, camrot_y, camrot_z: The camera rotations time_hours, time_min, time_sec: The ingame time weather: the ingame weather condition

Note that the camera position in general is offset wrt. the player vehicle. Also the height of the camera above ground is different from the heightAboveGround for the vehicle, so if you need this you need to calculate it.