Motion-blur parameter estimation of remote sensing image based on quantum neural network

During optical remote sensing imaging procedure, the relative motion between the sensor and the target may corrupt image quality seriously. The precondition of restoring the degraded image is to estimate point spread function (PSF) of the imaging system as precisely as possible. Because of the complexity of the degradation process, the transfer function of the degraded system is often completely or partly unclear, which makes it quite difficult to identify the analytic model of PSF precisely. Inspired by the similarity between the quantum process and imaging process in the probability and statistics fields, one reformed multilayer quantum neural network (QNN) is proposed to estimate PSF of the degraded imaging system. Different from the conventional artificial neural network (ANN), an improved quantum neuron model is used in the hidden layer instead, which introduces a 2-bit controlled NOT quantum gate to control output and 4 texture and edge features as the input vectors. The supervised back-propagation learning rule is adopted to train network based on training sets from the historical images. Test results show that this method owns excellent features of high precision, fast convergence and strong generalization ability.