Dataset for semantic segmentation of the laboratory model of manufacturing environment

This dataset includes images and labels used for semantic segmentation of the laboratory model of the manufacturing environment, at the University of Belgrade - Faculty of Mechanical Engineering. The dataset is gathered by using mobile robot RAICO (Robot with Artificial Intelligence based COgnition) and its stereo visual system made from two Basler acA1920-25uc cameras with Fujinon lens DF6HA-1B. The dataset includes close to 430 images with a resolution of 640x360. Images are acquired by both cameras at different mobile robot poses in the laboratory model of a manufacturing environment. Five classes are introduced in the dataset, machines 1 to 4, and a background class. The exact names of the classes are:

classNames = ["Machine_1", "Machine_2", "Machine_3", "Machine_4", "Background"];

while the labels of the classes (RGB values of label images) are:

labelIDs = [ ...
    000 000 255; ... % "Machine 1"
    000 255 255; ... % "Machine 2"
    255 255 000; ... % "Machine 3"
    255 000 000; ... % "Machine 4"
    255 255 255; ...   % "Background"
    ];

Image and label pairs are entitled 1 to 430, and e.g. label 5 corresponds to images 5.

This dataset was developed with the support of the Science Fund of the Republic of Serbia, Grant No. 6523109, AI - MISSION4.0, 2020-2022.