Vehicle detectors are an essential device for advanced traffic management and information system (ATMIS). Hence, the accuracy of traffic data from detectors is of fundamental importance. When evaluating detectors, one uses a baseline data source that generates reference data. However, reference data also contain errors and uncertainties, albeit small ones. Nevertheless, little research has been performed to address the errors and uncertainties of reference data. This study proposes a new detector evaluation scheme to resolve the problem. The scheme takes errors and uncertainties of reference data into account for reliable detector evaluation. Moreover, it applies the interval estimation technique, instead of the traditional point estimation, to present detector evaluation results. The suggested scheme is thoroughly verified using a well-facilitated detector test bed, and resultantly produces reliable detector evaluation results.