As a batch processing method, the Hough transform hardly overcomes the accumulation phenomenon of single-scan data sets for it gets confused with the time sequence information of measurements. To solve this nonlinear problem, a track initiation method based on the parallel Hough transform that changes the processing structure of the Hough transform and the accumulating manner of the counter is proposed. After mapping sets of different time measurements to the parameter space separately, the accumulated result of the measurement sets with the same index constitute an accumulated vector. According to the rules, the value of the accumulator can be obtained using the sliding window method. Finally, we make a decision on whether to initiate a track or not through threshold detection. Simulation experiment results of track initiation problems with different scan times under heavy clutters show the efficiency of the parallel Hough transform.