Study on the method of converting asynchronous event stream into grid representation
Wang Yanwei
Zhang Jiayu
Chen Kaiyun
Ren Chunping
Abstract：Objectives To address the complexity and sparsity of asynchronous event streams,which compli-cate data analysis,reduce storage and computational efficiency,a method was proposed to convert asyn-chronous event stream into grid representation.Methods Each event was replaced by a Dirac delta function and represented as a set of event fields.Based on tensor characteristics,average measurements were as-signed to events missing the same category of information,reducing computation while preserving high dy-namic resolution.Usable data were selected,and a multilayer perceptron(MLP)was used to replace manu-ally chosen aggregation kernels to identify optimal measurement functions.In ECTResNet,convolution was performed and dimension was reduced through periodic sampling to retain key information for quantization.The convolved data were discretized in continuous 3D space to generate a fixed-size grid.Finally,the event stream was transformed into a grid representation suitable for deep learning.Results The proposed method was evaluated on the N-Cars and N-Caltech101 datasets.Recognition accuracies reached 97.07%and 87.72%,respectively,improving by 10.09%and 11.44%over the event spike tensor method.Conclusions Ex-periments showed that converting asynchronous event stream into grid representation enhanced compatibility with deep learning models,improved accuracy and efficiency of event processing and recognition,and en-abled end-to-end representation learning.This approach held broad potential in sensor data processing and event recognition.
Keywords：event cameraasynchronous event streamdeep learningconvolutional neural network
Publication Date：2025-09-30
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：10( 17-26 )