Saliency map generation system, method and device based on dynamic vision sensor

Abstract

The invention belongs to the field of data processing, particularly relates to a saliency map generation system, method and device based on a dynamic vision sensor, and aims to solve the problems. Themethod comprises the following steps: acquiring event data through a dynamic vision sensor, accumulating and caching DVS event data and information acquired from mutually associated neurons through each neuron in a target detection network, acquiring a neuron membrane potential through an activation function every other preset time, and outputting a pulse signal according to the size relationshipbetween the neuron membrane potential and a preset saturation threshold; accumulating the membrane potential u (t0) at the previous moment with the currently received excitation through attenuation,and using the result for updating and judging the pulse signal and the membrane potential. According to the invention, redundant background information of the saliency map generated by the target detection network array is eliminated, the credibility and accuracy of target detection are improved, and misjudgment is avoided.

Description

technical field [0001] The invention belongs to the field of data processing, and in particular relates to a dynamic visual sensor-based saliency map generation system, method and device. Background technique [0002] Dynamic vision sensor (Dynamic vision sensor, DVS) has gradually gained attention. DVS is an event-driven photoelectric sensor. The information output by this type of sensor is different from the concept of "frame" of traditional image sensors, but is composed of a large number of independent events. In the data stream, each event contains information about an activated pixel point, so that the pixel information not only has brightness information, but also implies the time sequence information of event occurrence. At the same time, the dynamic vision sensor only generates output for areas where the brightness contrast changes, so it has the characteristics of filtering the background and only capturing moving targets, which can greatly reduce redundant backgro...

AI Technical Summary

Problems solved by technology

[0003] In order to solve the problems in the prior art that the dynamic visual sensor data cannot eliminate redundant background information, the amount of data is huge, too many resources are occupied, and the captured moving targets are not clear, the present invention provides a saliency map generation for dynamic visual sensors A system, the system comprising an event data acquisition module and an event data processing module;

Images