Abstract: An algorithm is proposed to deal with the issues that the existing detection algorithms cannot exclude the interference of ortho parking spaces and the corresponding judgment criteria fail to accommodate multiple types of vehicles and parking scenarios.Based on the analysis of the magnetic dipole model, the geomagnetic disturbance vector of targeted parking space is extracted through a vector operation during parking process, which can effectively eliminate the negative impact on geomagnetic field caused by the parking process from the ortho parking spaces.With a collection of large number of real geomagnetic disturbance data, the intensity of geomagnetic disturbances and characteristics of direction changes are statistically deduced and the multilevel thresholds are thus determined as the detection criterion, which ensures that the detection algorithm is suitable to various vehicle types and parking application scenarios.With a three-month field test, it is found that the detection precision of the proposed algorithm achieves 99.3%, superior to the algorithms with a single-feature using either pure intensity or certain direction.Moreover, the method could detect whether the parking is standard.The algorithm has not been applied to large passenger cars, trucks or special vehicles.