Image Based Food Energy Estimation With Depth Domain Adaptation

TL;DR

This paper introduces a novel image-based method using depth domain adaptation to estimate food energy from mobile images, improving accuracy over existing approaches.

Contribution

It proposes an Energy Density Map combined with depth information to enhance food energy estimation accuracy from images.

Findings

Achieved an average error of 13.29 kcal in energy estimation.

Improved accuracy over baseline methods.

Demonstrated effectiveness on the Nutrition5k dataset.

Abstract

Assessment of dietary intake has primarily relied on self-report instruments, which are prone to measurement errors. Dietary assessment methods have increasingly incorporated technological advances particularly mobile, image based approaches to address some of these limitations and further automation. Mobile, image-based methods can reduce user burden and bias by automatically estimating dietary intake from eating occasion images that are captured by mobile devices. In this paper, we propose an "Energy Density Map" which is a pixel-to-pixel mapping from the RGB image to the energy density of the food. We then incorporate the "Energy Density Map" with an associated depth map that is captured by a depth sensor to estimate the food energy. The proposed method is evaluated on the Nutrition5k dataset. Experimental results show improved results compared to baseline methods with an average error of 13.29 kCal and an average percentage error of 13.57% between the ground-truth and the estimated energy of the food.