With the rapid development of urban rail transit, unmanned train driving technology is also advancing rapidly. Automatic obstacle detection is particularly crucial and plays a vital role in ensuring train operation safety. This paper focuses on train obstacle detection technology and testing methods. First, we review existing obstacle detection systems and their testing methods, analyzing their technical principles, application status, advantages, and limitations. In the experimental section, the Intelligent Train Eye (ITE) system is used as a case study. Black-box testing is conducted in the level high-precision (LH) mode, with corresponding test cases designed based on various scenarios that may arise during train operations. White-box testing is performed in the level exploration (LE) mode, where the test results are meticulously recorded and analyzed. The test cases in different modes comprehensively cover the testing requirements for train operations. The results indicate that the ITE system successfully passes most of the test cases and meets the primary functional requirements.
To address the issue of low efficiency and inability to cover all test scenarios in manually generated test datasets, an automated test case generation method called Critical Network Layer Fuzzy testing (CNF) is proposed, based on the key network layer neuron coverage guidance criterion. The convolutional layer is selected as the key network layer. It is verified through experiments that the trend of neuron coverage changes in the key network layer is consistent with that of the entire network layer, significantly improving computational efficiency. Then, through visual and quantitative comparisons, the number of affine transformations required for automatic label generation is preliminarily determined. Finally, a network model is trained and comparative experiments are conducted, obtaining final results that verify the effectiveness of the CNF automatic label generation strategy.