A method and system for collecting data set based on event camera

Abstract

The present invention relates to a data collection method and system based on an event camera. The method includes: displaying video data collected by an event camera through a screen; The video data in the video data set constitutes a video data set; convert the video data corresponding to each area in the video data set into csv format, and obtain the csv format data corresponding to each area; perform an event every second set time in the csv format data Accumulate, and the accumulated number of events exceeding the set threshold corresponds to the csv format data within the second set time to generate pictures; filter the generated pictures according to the number of background noises in the generated pictures, and obtain the filtered pictures, each screened The csv format data corresponding to the last picture is used as a sample, and multiple samples constitute a data set. The invention reduces the redundancy of the data in the data set and simultaneously reduces the complexity of the data in the data set.

Description

technical field [0001] The invention relates to the field of data collection, in particular to a data collection method and system based on an event camera. Background technique [0002] At present, most of the existing data sets are videos or pictures collected by frame cameras. The amount of data processing is large, and the calculation takes a long time, and useless backgrounds will also be collected, wasting storage space. Existing data sets are often prepared for convolutional neural networks, and the data itself is relatively complex, and usually needs to be pulse-encoded before it can be input into the spiking neural network. Contents of the invention [0003] The purpose of the present invention is to provide a data collection method and system based on an event camera, which can reduce the redundancy of data in the data set and reduce the complexity of the data in the data set. [0004] To achieve the above object, the present invention provides the following sch...

AI Technical Summary

Problems solved by technology

[0002] At present, most of the existing data sets are videos or pictures collected by frame cameras. The amount of data processing is large, and the calculation takes a long time, and useless backgrounds will also be collected, wasting storage space.

Existing data sets are often prepared for convolutional neural networks. The data itself is relatively complex, and usually needs to be pulse-encoded before it can be input into the spiking neural network.

Images