MULTICLOD: Multiclass object detection
Computer vision for smart cars and safer roads
Project activities
Dissemination
-
international workshops and conferences:
iccv2017_cvrsuad,
gcpr2016a,
gcpr2016b,
gcpr2015a,
gcpr2015b,
visapp2015a,
visapp2015b,
cvprw2015
-
presentations at local scientific events:
ccvw2017,
ccvw2015a,
ccvw2015b
-
science fairs and media coverage:
AI2Future,
HRT,
skeptici u pubu;
-
image datasets:
KITTI semantic segmentation,
TS2010a
Software development and design
-
Software
components
for real-time control of the robotic car
-
required for autonomous navigation experiments
-
web application
for dense image annotation at the pixel level
-
suitable for collecting semantic segmentation groundtruth
Collaboration
-
project meeting in Graz
-
joint publication with INRIA Grenoble
(gcpr2015a)
Other activities
-
acquisition of training and evaluation samples
for semantic segmentation
-
acquisition of a workstation with two high-end GPUs
-
design and maintenance of the project's
web site