Adaptive driver assistance system with robust estimation of object properties

摘要

A computer-implemented method for estimating properties of objects in digital images comprises the steps:
- encoding input data from a sensor in a neural map comprising neurons having numerical activation values; wherein the activation values in the neural maps have continuous time dynamics defined by an update scheme;
- creating, adapting and deleting weights of the neural map in unsupervised, incremental manner;
- transmitting data from an input map to an output map, based on the values of the weights; wherein each weight between the input map (IM) and a neural output map (OM) has a unique source and destination neuron; and wherein data transmission is directed; and
- detecting correlations between the input map (IM) and the output map (OM).