Harvesting Robot
Artist Impression
Sweet-pepper crop
in the greenhouse

THe Sweeper project resulted in a number of image datasets that are available for download:

Database 1

Summary

During two visit to the grower's greenhouse (July and Sep 2015), the first set of field data was collected and organized. While deliverable 5.1 is the dataset itself, this short report describes its design and content, and how to publically access it.

Report describing the content of the database

Deliverable number 5.1: Image database #1

Web-link to database

http://icvl.cs.bgu.ac.il/lab_projects/agrovision/DB/Sweeper01/#/scene

Database 2

Summary

In May 2016, the first integrated gripper with sensor and illumination was produced and used for data collection in the greenhouse under conditions resembling best (thus far) the acquisition likely to happen by the Sweeper harvester. This includes the EFFILUX LED array surrounding the iDS camera and an acquisition process that triggers the LEDs during very short exposure times in order to overcome ambient illumination and sun light.

Report describing the content of the database

Deliverable number 5.3: Image database #2

Web-link to database

http://icvl.cs.bgu.ac.il/lab_projects/agrovision/DB/Sweeper02/#/scene

Database 3

Summary

This deliverable reports on image database 3#, consisting of synthetic images generated from 3D models of plants and fruits based on empirical information. The database is intended for the advanced sensing algorithms with particular focus on obstacle detection.

Report describing the content of the database

Deliverable number D5.8: Image Database #3

Web-link to database

http://dx.doi.org/10.4121/uuid:884958f5-b868-46e1-b3d8-a0b5d91b02c0

Database 4

Summary

This deliverable reports on image database #4 consisting of images obtained from the Fotonic F80 RGB-D camera in experiments conducted in a greenhouse in IJsselmuiden, The Netherlands in June 2017 with peppers from the Gialte cultivar (E20B.0132, Seed company - Enza Zaden). The database is intended for development of the advanced sensing algorithms with particular focus on depth data and maturity evaluation.

Report describing the content of the database

Deliverable number D5.10: Image databases #4 with different crop conditions

Web-link to database

http://icvl.cs.bgu.ac.il/lab_projects/agrovision/DB/Sweeper04/#/scene