Adaptive sampling for scanning pixel cameras

TL;DR

This paper introduces an adaptive sampling algorithm for scanning pixel cameras that reduces data acquisition and transmission costs by dynamically adjusting the sampling rate, maintaining image quality for classification and segmentation tasks.

Contribution

It presents a novel adaptive sampling method that optimizes sampling rates during scanning, significantly reducing data needs while preserving image analysis performance.

Findings

Achieves similar classification and segmentation accuracy with 80% fewer samples.

Reduces bandwidth and time for scene imaging and transmission.

Demonstrates effectiveness on image classification and semantic segmentation tasks.

Abstract

A scanning pixel camera is a novel low-cost, low-power sensor that is not diffraction limited. It produces data as a sequence of samples extracted from various parts of the scene during the course of a scan. It can provide very detailed images at the expense of samplerates and slow image acquisition time. This paper proposes a new algorithm which allows the sensor to adapt the samplerate over the course of this sequence. This makes it possible to overcome some of these limitations by minimising the bandwidth and time required to image and transmit a scene, while maintaining image quality. We examine applications to image classification and semantic segmentation and are able to achieve similar results compared to a fully sampled input, while using 80% fewer samples