Fast and High-Precision Analog In-Sensor Visual Computing Using Fully Amorphous Metal Oxide Thin-Film Transistors

In-Sensor computing has emerged as a promising approach for fast, energy-efficient visual perception. This paper presents an in-sensor computing system that leverages amorphous metal oxide thin-film transistors (TFTs) for photo-sensing, computation, and control, enabling rapid and precise visual processing. The system directly computes the first layer of a neural network (NN) during exposure and supports high-resolution raw image readout once a target of interest is detected. The pixel circuit incorporates threshold voltage (V<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">TH</inf>) compensation to ensure computational accuracy. Validated on the MNIST dataset, the system achieves 88% classification accuracy with only a 2.2% degradation under a 2V V<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">TH</inf> shift. Post-Simulation results show that one computation frame can be finished within 500 ns, demonstrating a 20× speed enhancement over state-of-the-art silicon-based solutions.