Improved neural network modeling of inverse lens distortion
| Autor: | Jason P. de Villiers, Jaco Cronje, Fred Nicolls |
|---|---|
| Rok vydání: | 2011 |
| Předmět: |
Pixel
Artificial neural network business.industry Computer science Distortion (optics) ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Inverse law.invention Image (mathematics) Lens (optics) law Distortion Computer data storage Point (geometry) Computer vision Artificial intelligence Radar business |
| Zdroj: | Visual Information Processing |
| ISSN: | 0277-786X |
| DOI: | 10.1117/12.884065 |
| Popis: | 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 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|