Single Pixel Image Classification using an Ultrafast Digital Light Projector

TL;DR

This paper demonstrates ultrafast single pixel image classification using a microLED-on-CMOS digital light projector combined with simple machine learning models, achieving high frame rates suitable for real-time applications like autonomous vehicles.

Contribution

It introduces a novel combination of single pixel imaging with ultrafast pattern projection and low-complexity machine learning for real-time image classification without image reconstruction.

Findings

Achieved multi-kHz frame rate classification on MNIST dataset.

Compared ELM and deep neural network, showing ELM's efficiency.

Demonstrated potential for anomaly detection in ultrafast imaging.

Abstract

Pattern recognition and image classification are essential tasks in machine vision. Autonomous vehicles, for example, require being able to collect the complex information contained in a changing environment and classify it in real time. Here, we experimentally demonstrate image classification at multi-kHz frame rates combining the technique of single pixel imaging (SPI) with a low complexity machine learning model. The use of a microLED-on-CMOS digital light projector for SPI enables ultrafast pattern generation for sub-ms image encoding. We investigate the classification accuracy of our experimental system against the broadly accepted benchmarking task of the MNIST digits classification. We compare the classification performance of two machine learning models: An extreme learning machine (ELM) and a backpropagation trained deep neural network. The complexity of both models is kept low so the overhead added to the inference time is comparable to the image generation time. Crucially, our single pixel image classification approach is based on a spatiotemporal transformation of the information, entirely bypassing the need for image reconstruction. By exploring the performance of our SPI based ELM as binary classifier we demonstrate its potential for efficient anomaly detection in ultrafast imaging scenarios.