Neural Networks applied to 3D Object Depth Recovery

In this work the application of neural networks (NNs) in tridimensional object depth recovery and structured light projection system calibration tasks is presented. In a first approach, a NN using radial basis functions (RBFNN) is proposed to carry out fringe projection system calibration. In this case the RBFNN is modeled to fit the phase information (obtained from fringe images) to the real physical measurements. In a second approach, a Multilayer Perceptron Neural Network (MPNN) is applied to phase and depth recovery from the fringe patterns. A scanning window is used as the MPNN input and the phase or depth gradient measurements is obtained at the MPNN output. Experiments considering real object depth measurement are presented.