This paper discusses and analyzes the performance of the Adaptive Threshold Detection Algorithm for vehicle detection based on road traffic vibrations. The algorithm, originally developed for magnetometer- and microphone-based vehicle detection, is adapted for the usage with seismic signals and then analyzed in a statistical framework. It is found that the algorithm can be applied to this kind of signals and promising results are obtained in simulations and tests on measurement data. Further testing using real traffic data is required in order to obtain more significant results.