A multi-sample parallel estimation method using in the volume-holographic scene matching system is proposed. The method makes good use of the characteristics of stationary random of the remote sensing image and the characteristics of the high speed, multi-channel and high parallelism of the volume holographic correlator, and implements scene matching with high accuracy. Theoretical basement of multi-sample parallel estimation method is analyzed. The essential steps of the method including image preprocessing, template images preparation and estimation equation establishing are discussed in detail and the requirements for these steps are introduced. The experimental results show the validity of the multi-sample parallel estimation method, and the recognition accuracy is improved by increasing the sample numbers.