Automatic driving target detection system test method and system based on object replacement

The invention discloses an automatic driving target detection system test method and system based on object replacement, and defines a metamorphic relation suitable for a target detection system in an automatic driving scene on the basis of applying a metamorphic test theory. Identifiable objects are replaced by using an automated driving scene dataset with instance level labels. And replacing the object pixel in the scene by adopting a mask matching mode, namely replacing the pixel of a certain recognizable object in the original scene with an object from other scenes so as to generate a derived test case. Compared with the prior art, the method has the advantages that the generated test case scene is more real, and the error revealing capability is improved. And meanwhile, a test result is evaluated based on a complete intersection-parallel ratio matrix, so that the possibility of misjudgment on the overlapping condition of the predicted bounding box is reduced. 本发明公开了一种基于对象替换的自动驾驶目标检测系统测试方法及系统，本发明在应用蜕变测试理论