Model-based Test-Case Generation for Testing Robustness of Vision Components of Robotic Systems

Wolfgang Herzner (1) , Markus Murschitz (1) , Olivier Zendel (1)

1 AIT - Austrian Institute of Technology [Vienna]

This extended abstract outlines a model-based approach for generating test data to assess the robustness of computer vision (CV) solutions with respect to a given task or application. The outlined approach enables the automatic generation of test data with a measurable coverage of optical situations both typical as well as critical for a given application. In addition, expected results are generated, all with almost no manual effort.

Mots clés: Safety; Embedded systems; computer vision testing; robustness testing; model-based test case generation

Domaines: Systèmes embarqués

Wolfgang Herzner, Markus Murschitz, Olivier Zendel. Model-based Test-Case Generation for Testing Robustness of Vision Components of Robotic Systems. SAFECOMP 2013 - Workshop DECS (ERCIM/EWICS Workshop on Dependable Embedded and Cyber-physical Systems) of the 32nd International Conference on Computer Safety, Reliability and Security, Sep 2013, Toulouse, France. pp.NA. ⟨hal-00848601⟩