Motion identification system by simulating spiking neuron of primary visual cortex

Abstract

The invention provides motion identification system by simulating a spiking neuron of primary visual cortex. The system comprises a video image pretreatment module, a feature extraction module, and a motion identification module. According to the invention, firstly, a 3D gabor space time filter simulates a simple cell in primary visual cortex, so that a video image is processed to obtain motion information being sensitive to a motion speed and a direction; secondly, a neuron in the primary visual cortex is stimulated by employing an integrated and fire spiking neuron model and the obtained motion information is converted into a pulse train responded by the neuron; thirdly, a motion feature vector is extracted according to an average firing rate and a behavior feature of the pulse train and identification is carried out on the motion in the video image by employing a method of support on a vector machine. According to a test result, in the test environment of a Weiziman database, the system provided in the invention not only enables an accuracy of the motion to be improved but also enables an identification rate is accelerated substantially.

Description

technical field [0001] The invention relates to a simulated biological visual perception system, in particular to an action recognition system based on V1 layer visual perception. Background technique [0002] Recognizing human actions from video images has a very wide range of applications in the fields of video surveillance, video retrieval and human-computer interface. However, due to the complexity of the structure of the human body and the individual differences between different people, it is very difficult to recognize fast and accurate actions. For the unsolved problems in action recognition, in recent years, researchers have mainly proposed two types of methods: global representation and local representation. The former uses background subtraction or tracking to locate the human body, and then encodes the region of interest into a whole for recognition; the latter obtains feature blocks by detecting spatiotemporal interest points to complete action recognition. Si...

AI Technical Summary

Problems solved by technology

[0005] Whether it is Jhuang's hierarchical action recognition model or Escobar's V1 / MT bionic feedforward spiking neuron model, in practical applications, the model structure is complex, Large amount of calculation, low efficiency and other defects

Images