Single-pixel sensing with optimal binarized modulation

Conventional high-level sensing techniques require high-fidelity images as input to extract target features. The images are produced by either complex imaging hardware or high-complexity reconstruction algorithms. In this Letter, we propose single-pixel sensing (SPS) that performs high-level sensing directly from a small amount of coupled single-pixel measurements, without the conventional image acquisition and reconstruction process. The technique consists of three steps, including binarized light modulation at ∼22.7kHz refresh rate, single-pixel coupled detection with a wide working spectrum and high signal-to-noise ratio, and end-to-end deep-learning-based decoding that reduces both hardware and software complexity. Also, the binarized modulation patterns are optimized with the decoding network by a two-step training strategy, leading to the least required measurements and optimal sensing accuracy. The effectiveness of SPS is experimentally demonstrated on the classification task of the handwritten MNIST dataset, and 96% classification accuracy at ∼1kHz is achieved. The reported SPS technique is a novel framework for efficient machine intelligence, with data-reduced acquisition and load-relieved processing.