Dataset Restricted Access

EndoAbS Dataset

Veronica Penza

Dublin Core Export

<?xml version='1.0' encoding='utf-8'?>
<oai_dc:dc xmlns:dc="" xmlns:oai_dc="" xmlns:xsi="" xsi:schemaLocation="">
  <dc:creator>Veronica Penza</dc:creator>
  <dc:description>The EndoAbS Dataset (Endoscopic Abdominal Stereo Images Dataset) aims to provide to the computer assisted surgery community a dataset for the validation of 3D reconstruction algorithms.
It is composed of:
- 120 pair of endoscopic stereo images of abdominal organs (liver, kidneys, spleen);
- corresponding ground truth in left-camera reference frame, generated using a laser scanner;
- camera calibration parameters;

The images were captured under different conditions:
- different light levels;
- presence of smoke;  
- two phantom-endoscope distances (~5cm or ~10cm);
If you use this dataset, please cite:
 Penza, V., Ciullo, A. S., Moccia, S., Mattos, L. S., &amp; De Momi, E. (2018). EndoAbS dataset: Endoscopic abdominal stereo image dataset for benchmarking 3D stereo reconstruction algorithms. The International Journal of Medical Robotics and Computer Assisted Surgery, e1926.

For further information, please contact</dc:description>
  <dc:subject>endoscopic stereo image dataset</dc:subject>
  <dc:subject>3D reconstruction algorithm evaluation</dc:subject>
  <dc:subject>ground truth</dc:subject>
  <dc:subject>abdominal phantom model</dc:subject>
  <dc:title>EndoAbS Dataset</dc:title>
All versions This version
Views 1,5701,589
Downloads 114114
Data volume 20.5 GB20.5 GB
Unique views 1,1771,185
Unique downloads 9393


Cite as