We propose a quantitative risk assessment approach for the design of an obstacle detection function for low-speed freight trains with grade of automation 4. In this five-step approach, starting with single detection channels and ending with a three-out-of-three model constructed of three independent dual-channel modules and a voter, we exemplify a probabilistic assessment, using a combination of statistical methods and parametric stochastic model checking. We illustrate that, under certain not unreasonable assumptions, the resulting hazard rate becomes acceptable for specific application settings. The statistical approach for assessing the residual risk of misclassifications in convolutional neural networks and conventional image processing software suggests that high confidence can be placed into the safety-critical obstacle detection function, even though its implementation involves realistic machine learning uncertainties.