Semantic segmentation with inexpensive simulated data

Jukka Peltomäki, Mengyang Chen, Heikki Huttunen

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review


This paper studies the benefits of adding inexpensively gathered simulated data to improve the training of semantic segmentation models. We introduce our implementation to gather simulated datasets with minimal effort. In our implementation, we utilize a commonly available game engine (Unity) and aux-illiary graphical assets to assemble an environment to generate simulated data inexpensively. We also demonstrate that even the usage of spartan simulated data mixed with real-life data can increase the performance of the trained model slightly, given that the ratio of simulated data is suitable for the datasets.
Original languageEnglish
Title of host publication2019 IEEE Nordic Circuits and Systems Conference (NORCAS): NORCHIP and International Symposium of System-on-Chip (SoC)
Number of pages6
ISBN (Electronic)978-1-7281-2769-9
ISBN (Print)978-1-7281-2770-5
Publication statusPublished - Oct 2019
Publication typeA4 Article in conference proceedings
EventIEEE Nordic Circuits and Systems Conference -
Duration: 1 Jan 2000 → …


ConferenceIEEE Nordic Circuits and Systems Conference
Period1/01/00 → …

Publication forum classification

  • Publication forum level 1


Dive into the research topics of 'Semantic segmentation with inexpensive simulated data'. Together they form a unique fingerprint.

Cite this