Fast Integral Image Estimation at 1% measurement rate

TL;DR

This paper introduces ReFInE, a novel framework for fast integral image estimation from minimal measurements, enabling efficient object tracking without full image reconstruction at very low measurement rates.

Contribution

ReFInE jointly designs measurement matrices and linear estimators for rapid integral image computation directly from compressed measurements, bypassing iterative reconstruction.

Findings

High-quality integral image estimates at very low measurement rates.

Object tracking performance comparable to state-of-the-art at 1% measurement rate.

Efficient single-shot estimation method demonstrated on real video data.

Abstract

We propose a framework called ReFInE to directly obtain integral image estimates from a very small number of spatially multiplexed measurements of the scene without iterative reconstruction of any auxiliary image, and demonstrate their practical utility in visual object tracking. Specifically, we design measurement matrices which are tailored to facilitate extremely fast estimation of the integral image, by using a single-shot linear operation on the measured vector. Leveraging a prior model for the images, we formulate a nuclear norm minimization problem with second order conic constraints to jointly obtain the measurement matrix and the linear operator. Through qualitative and quantitative experiments, we show that high quality integral image estimates can be obtained using our framework at very low measurement rates. Further, on a standard dataset of 50 videos, we present object tracking results which are comparable to the state-of-the-art methods, even at an extremely low measurement rate of 1%.