Single pixel image classification using an ultrafast digital light projector

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 benchmarking MNIST dataset. We compare the classification performance of two low complexity machine learning models, an extreme learning machine (ELM) and a backpropagation-trained deep neural network, ensuring their inference-time overhead remains comparable to image-generation time. By exploring the performance of our SPI-based ELM as a binary classifier, we demonstrate its potential for efficient anomaly detection in ultrafast imaging scenarios. Crucially, our single pixel image classification approach is based on a spatiotemporal transformation of the information, entirely bypassing the need for image reconstruction.