Optical flow-based target detection method based on compound eye vision enlightenment

Abstract

The invention provides an optical flow-based target detection method for compound eye visual inspiration, which comprises the following steps of: determining synaptic input conductance matrixes for a first neural network and a second neural network according to an optical flow matrix output by an EMD (Empirical Mode Decomposition) array; obtaining output matrixes of the first neural network and the second neural network according to the membrane potential matrixes of the first neural network and the second neural network, and further determining a synaptic input conductance matrix of a third neural network; and according to the synaptic input conductance matrix of the third neural network, obtaining a neuron membrane potential matrix of the third neural network, establishing a nonlinear relationship between a single neuron membrane potential and a single neuron output in the third neural network, and obtaining a motion detection result of the target object. According to the method, the working principle of a perfectly evolved compound eye vision system is used as a starting point for reference, and parallel point-by-point space-time smoothing and nonlinear dichotomy transformation are performed on the primary motion detector array estimation optical flow, so that motion detection and target-background separation based on a biological perception optical flow mechanism are realized.

Description

technical field [0001] The present disclosure relates to the intersection of brain science and computer vision, and in particular, to an optical flow-based target detection method inspired by compound eye vision. Background technique [0002] There are many methods in computer vision, machine vision and other fields to detect moving objects. For the case where the information of the detected target is known in advance, the target object is often detected by constructing and training a neural network classifier; for the case where the prior knowledge of the target is unknown, it is necessary to detect the target according to the motion salient features. The common method is the optical flow method. , background modeling, etc. [0003] Optical flow is an important application of the optical flow concept proposed by psychologist Gibson in the 1950s in computer vision based on the optical flow field characteristics of the physical world. To apply the optical flow method, it is...

AI Technical Summary

Problems solved by technology

Since the background modeling method needs to buffer several frames to learn and establish the background, the limitation of this type of method is that it cannot update the background model in time in complex and changeable scenes.

Images