Image Classification in the Dark using Quanta Image Sensors

TL;DR

This paper introduces a novel low-light image classification method using Quanta Image Sensors and student-teacher learning, enabling accurate classification at extremely low photon levels where traditional sensors struggle.

Contribution

It presents the first study on using QIS for image classification and develops a student-teacher learning scheme for classifying noisy low-light data.

Findings

Achieves classification at one photon per pixel or lower.

Outperforms existing low-light imaging solutions.

Validates effectiveness through experimental results.

Abstract

State-of-the-art image classifiers are trained and tested using well-illuminated images. These images are typically captured by CMOS image sensors with at least tens of photons per pixel. However, in dark environments when the photon flux is low, image classification becomes difficult because the measured signal is suppressed by noise. In this paper, we present a new low-light image classification solution using Quanta Image Sensors (QIS). QIS are a new type of image sensors that possess photon counting ability without compromising on pixel size and spatial resolution. Numerous studies over the past decade have demonstrated the feasibility of QIS for low-light imaging, but their usage for image classification has not been studied. This paper fills the gap by presenting a student-teacher learning scheme which allows us to classify the noisy QIS raw data. We show that with student-teacher learning, we are able to achieve image classification at a photon level of one photon per pixel or lower. Experimental results verify the effectiveness of the proposed method compared to existing solutions.