Context
As my research concentrates on the perception part of Robotics, my research is in the Informatics Institute part of the
Computer Vision group.
Started
Labbook 2020.
December 18, 2019
December 5, 2019
December 2, 2019
November 28, 2019
- Short discussion with Theo Gevers on the new Atlas lab, a cooperation with TomTom. The lab will be headed by an assistant professor, the CV students will work on 3D reconstruction from segmented data, 3D reconstruction from point-clouds and object detection from point-clouds.
- Bosch lab has for instance this publications:
- Kim, J. ; Rohrbach, A. ; Darrell, T. ; Canny, J. ; Akata, Z. / Textual Explanations for Self-Driving Vehicles. Computer Vision – ECCV 2018: 15th European Conference, Munich, Germany, September 8-14, 2018: proceedings. editor / V. Ferrari ; M. Hebert ; C. Sminchisescu ; Y. Weiss. Vol. 2 Cham : Springer, 2018. pp. 577-593 (Lecture Notes in Computer Science).
- Looking if I could get deep driving code working on my workstation (Ubuntu for Windows mode). Install the requirements with pip install --user.
- Download script only worked for platform darwin, but modified it that it also works for linux (and python3).
- Preprocess step fails in line 104. Cannot read json files in ./data/Videos/info, which is correct, because this directory doesn't exist. The json files are also not downloaded in Step0, so a not clear where they should come from. Annotations can be found in data/Sample.csv