Bionic target identification system based on event driving

Abstract

The present invention relates to the field of image processing technology. In order to realize real-time acquisition and processing of image information collected from an AER image sensor, an event-based processing method is always adopted in a rear-end bionic visual system processing stage to realize the target recognition function and provide target position parameters. A bionic target identification system based on event driving comprises an image sensor representing AER based on address-event, and a rear-end bionic processing system, wherein the AEM image sensor is used as an information acquisition source of moving objects, and the acquired image data is inputted in parallel to the rear-end bionic processing system. The bionic target identification system further comprises a feature extraction module for processing input image data by using feature extraction algorithm based on event driving, and a target identification module based on event driving, wherein the target identification module employs SNN (spiking neural network) to process the output of the feature extraction module. The bionic target identification system is mainly used for image processing.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a back-end bionic processing system based on an AER image sensor, which has the advantages of real-time, high speed, parallelism and precision, and realizes intelligent visual image applications for target recognition and tracking. Background technique [0002] Vision sensors are widely used in scientific research, national defense security, industrial production and daily life and other fields. Combining image processing and network technology, visual sensing technology carries most of the information acquisition tasks in the Internet of Things, and has increasingly become an important foundation and technical support for the realization of intelligence in various fields such as scientific research, national defense, production and life. Computer vision technology has a wide range of applications in the perception and processing of visual information, and the re...

AI Technical Summary

Problems solved by technology

For example: the image sensor serially transmits the collected data backwards, and there is a serious bandwidth limitation; the back-end processing system also processes the image pixel by pixel serially, due to the limitation of serial transmission and serial processing, the traditional target The processing speed of the recognition system is far from meeting the high-speed real-time requirements

In addition, although the traditional target recognition algorithm is simple to operate, there are many processing steps. Considering the diversity of target shapes, the shape model set and calculation are very complicated, which cannot achieve the real-time output of target tracking, and face complex targets and background noise interference. image, the extraction results are not ideal

Images