Convolutional Neural Network Optimization for Homography Estimation

This thesis proposes an optimized convolutional neural network architecture to improve homography estimation applications. The parameters and structure of the CNN including the number of convolutional filters, stride lengths, kernel size, learning parameters, etc are altered from previous implementations. Multiple modifications of the network are trained and evaluated until a final network yields a corner pixel error of 4.7 which is less than a network proposed in previous literature\u27s