Trackves Dataset

The <strong>TrackVes</strong> dataset provides to the computer assisted surgery community a dataset for the validation of soft tissue tracking algorithms. It is composed of nine folders: EV1:3 - 3 video sequences of ex-vivo organs (kidney and liver);<br> IV1:6 - 6 video sequences of in-vivo organs (real abdominal surgical scenes); Each folder contains: <strong>videoLeft.avi</strong> - video sequence;<br> <strong>GT.xml </strong> - xml file with ground truth defined as a 2D polygon around the area to be tracked, with an interframe step of 10;<br> <strong>Attributes.xml</strong> - xml file indicating one of the following attributes associated to each frame (with an interframe step of 10): 0 - Safety Area Visible (SAV);<br> 1 - Partial Occlusion (PO);<br> 2 - Safety Area Out of Field of View (OFV);<br> 3 - Total Occlusion (TO);<br> 4 - DEFormation (DEF);<br> 5 - Illumination Changes (IC);<br> 6 - Abrupt Camera Motion (ACM);<br> 7 - Blur (BLR);<br> 8 - Presence of Smoke (SMK). <br> The C++ code implementing the ground truth generation and the tracking algorithm evaluation is available on Bitbucket -<br> https://bitbucket.org/ververo/envisors_track/ as: app/gt_generator<br> app/tracking_evaluation. If you use this dataset, please cite: V. Penza, X. Du, D. Stoyanov, A. Forgione, L. Mattos and E. De Momi. "Long Term Safety Area Tracking (LT-SAT) with Online Failure Detection and Recovery for Robotic Minimally Invasive Surgery", Medical Image Analysis, 2017. For further information, please contact [e-mail]