Locked, unlocked and semi-locked network weights for four different camera calibration problems

Backpropagation training algorithms typically view network weights as a single vector of isotropic parameters to be minimized. In contrast, we present a neural network in which each network weight has its own physical meaning and its different role during network training. The network is used to solve four different types of calibration problems found in computer vision applications. A network weight may be unlocked, locked or semi-locked during training according to the available information about the problem. Experiments show the network trained with the available backpropagation-based algorithms can provide superior results to some other widely-used calibration techniques