Object recognition method based on their signal-geometric signs by means of a robotic security complex

The article considers a methodological approach to the recognition of intrusion objects into a protected area using optoelectronic means of a robotic complex, which is based on the existence of a certain feature space (a set of signal and geometric features) for each class and type of object. The solved problem of comparing Bayesian a posteriori probabilities of classes (types) of objects is reduced to calculating a priori probabilities and energy distribution functions of signals and geometric parameters of objects, i.e. likelihood functions of a feature to a specific class (type) of an object. On the basis of the obtained parameters, the dependences of the probability of correct recognition, the probability of skipping, false recognition and confusion of objects on the coefficient of distinctness when the object signal energy deviates from the standard in smaller and larger directions are analyzed. The results obtained are necessary to solve the problem of adaptive group control of robotic complexes when solving operational and tactical tasks in an uncertain dynamic environment.