Comparison of Stochastic Gradient-Based Optimization Techniques for Nonlinear Satellite Image Coregistration Problem

Information-oriented intensity-based cost functions are generally used for optimization frameworks in automatic satellite image registration. Optimization mechanics which updates the transform parameters in the iterative loop requires estimation of derivatives of the cost function to set-up update rules that retrieve the deformation model between the image pairs. Application of stochastic approximation of cost function and its derivatives for solving optimization problems while the objective function is non-differentiable or non-smooth or computed with noise is encountered in real-world problems. The known methods of approximation for solving these problems use the idea of stochastic gradient and certain rules of changing the step length for ensuring convergence. In this article, satellite image coregistration problem is chosen for comparing the performance of two important stochastic optimizers like adaptive stochastic gradient descent and simultaneous perturbation stochastic approximation. Coregistration datasets from Resourcesat-2 LISS-4 MX sensor are chosen for different terrains and features to study subpixel accuracies of order better than 1/20th of a pixel achieved in the comparison of two different optimization techniques employed in intensity-based automatic image registration framework.