Inverse lens distortion modelling allows one to find the pixel in a distorted image which corresponds to a known point in object space, such as may be produced by a RADAR. This paper extends recent work using neural networks as a compromise between processing complexity, memory usage and accuracy. The already encouraging results are further enhanced by considering different neuron activation functions, architectures, scaling methodologies and training techniques. The errors are given in terms of microns on the detector to facilitate fair comparison between different resolutions and pixel sizes.
Reference:
De Villiers, JP, Cronje, J and Nicolls, FC. 2011. Improved neural network modeling of inverse lens distortion. Defense, Security, and Sensing (DSS11), Orlando World Center Marriott Resort & Convention Centre, Orlando, Florida, USA, 26-28 April 2011, 9 pp
De Villiers, J., Cronje, J., & Nicolls, F. (2011). Improved neural network modeling of inverse lens distortion. http://hdl.handle.net/10204/5488
De Villiers, JP, J Cronje, and FC Nicolls. "Improved neural network modeling of inverse lens distortion." (2011): http://hdl.handle.net/10204/5488
De Villiers J, Cronje J, Nicolls F, Improved neural network modeling of inverse lens distortion; 2011. http://hdl.handle.net/10204/5488 .
