Research On Target Recognition Method Based Onhuman Echolocation

Echolocation is a basic cognitive skill of mankind.The study of echolocation has important research significance and application value.Through research on the mechanism of human echolocation,we can extract a new signal processing method of environment perception and autonomous navigation.On the one hand,it can provide some theoretical basis and technical support for the manufacturing of blind echo positioning device.On the other hand,this kind of cognitive method can provide a new way of thinking and signal processing methods for the sensing equipment such as radar and sonar.Based on the deep research and analysis of human echolocation behavior experiment for two-dimensional shape target recognition,we constructed human echolocation experiment system and simulated two scenarios of human echolocation behavior experiment,namely,"keep static" scene and "free movement" scene.After carrying out signal acquisition under two scenes,the corresponding method of feature extraction of sound signal is studied,and the two-dimensional shape target recognition method under two scenes is studied respectively.The main work of this paper can be summarized as follows:1)The results of human echolocation behavior experiment for two-dimensional shape target recognition are studied and analyzed,and the corresponding experimental system for human echolocation is built and tested accordingly.2)Feature extraction methods based on sound signal are studied,Total intensity(TS),average frequency(AF),low frequency intensity(LFS),intermediate frequency intensity(IFS),high frequency intensity(HFS),brightness(TB),three color values(T1,T2,T3),and irregularity(IRG)were extracted from the sound signal;3)The experiment of human echolocation in the "keep static" scene is simulated.The original data and the feature extraction from the original data are analyzed.The results show that it is difficult to distinguish the different shape targets by the single position’s sound signal.The result is consistent with the result of the behavior experiment.4)The experiment of human echolocation in the "free movement" scene is simulated.The results of feature extraction and visual analysis of 40 cm composite signal,80 cm composite signal and 80 cm echo signal show that the two-dimensional targets with different shapes can be effectively distinguished according to the total energy or the average frequency of three kinds of sound signals.The results are consistent with the results of the behavior experiments.