Published November 13, 2024 | Version v1
Dataset Open

Synthetic dataset for warehouse equipment and pallet recognition (Camera 1)

Creators

  • 1. TalTech

Description

This dataset provides a collection of synthetic images simulating various warehouse scenarios, specifically designed for training and evaluating computer vision models for equipment and pallet recognition tasks. The images feature a diverse range of warehouse environments, including different lighting conditions, object arrangements, and occlusions.

This dataset was created as part of a project funded by AI & ROBOTICS ESTONIA (EDIH)

Due to upload size limits the dataset was split into 4 pieces.

For an in depth explaination about the dataset creation and model training process see the thesis in Related works.

Technical info

Format: COCO

Dataset description:
Both camera 1 and 2 contain images from the same virtual warehouse.
The difference between the two sets in how much the camera position is randomized between frames.
Camera 1 has a wide movement and rotation range to capture objects of interest from as many different angles as possible.
Camera 2 mimics a security camera - staying high up and looking down. Its position and orientation is randomized somewhat but it is much more constrained.

Split:

  • Train -  2236 (65%)
  • Test - 686 (20%)
  • Val -  514 (15%)
     

Total: 3436

Classes:

  1. person
  2. pallet_jack_empty
  3. mover_pallet
  4. forklift
  5. forklift_full
  6. pallet_jack
  7. pallet_jack_full
  8. stacker
  9. stacker_full
  10. forklift_empty
  11. stacker_empty

Files

camera1.zip

Files (10.0 GB)

Name Size Download all
md5:1ca07236e2d09b3f54f63d084bd59495
10.0 GB Preview Download

Additional details

Related works

Is described by
Thesis: https://digikogu.taltech.ee/et/Item/4113691b-eb47-4bc5-87b8-8e2c399a66ed (URL)