DeepAI AI Chat
Log In Sign Up

Attention Mechanisms for Object Recognition with Event-Based Cameras

by   Marco Cannici, et al.
Politecnico di Milano

Event-based cameras are neuromorphic sensors capable of efficiently encoding visual information in the form of sparse sequences of events. Being biologically inspired, they are commonly used to exploit some of the computational and power consumption benefits of biological vision. In this paper we focus on a specific feature of vision: visual attention. We propose two attentive models for event based vision. An algorithm that tracks events activity within the field of view to locate regions of interest and a fully-differentiable attention procedure based on DRAW neural model. We highlight the strengths and weaknesses of the proposed methods on two datasets, the Shifted N-MNIST and Shifted MNIST-DVS collections, using the Phased LSTM recognition network as a baseline reference model obtaining improvements in terms of both translation and scale invariance.


page 4

page 5

page 6

page 8


Event-based Vision: A Survey

Event cameras are bio-inspired sensors that work radically different fro...

Event-based Convolutional Networks for Object Detection in Neuromorphic Cameras

Event-based cameras are bioinspired sensors able to perceive changes in ...

DART: Distribution Aware Retinal Transform for Event-based Cameras

We introduce a new event-based visual descriptor, termed as distribution...

Pose-Invariant Object Recognition for Event-Based Vision with Slow-ELM

Neuromorphic image sensors produce activity-driven spiking output at eve...

Fast Wavelet-Based Visual Classification

We investigate a biologically motivated approach to fast visual classifi...

Invariant feature extraction from event based stimuli

We propose a novel architecture, the event-based GASSOM for learning and...