Estimation method of calorie intake by deep learning using depth images obtained through a single camera smartphone
Kazuyuki Kaneda, Tatsuya Ooba, Hideki Shimada, Osamu Shiku, Yuji Teshima · 2021 IEEE 10th Global Conference on Consumer Electronics (GCCE) · 2021
In this study, we propose a method of estimating calorie intake considering leftover food using a single camera smartphone. To obtain depth images of the meals, we used the augmented reality core depth application programming interface, which creates depth images using a single camera smartphone. From photos and depth images of the meals, we estimated the type, quantity, and container of the meal both before and after consumption using deep learning. Using these estimated values, we calculated the volume of calorie intake. This method of estimating calorie intake can be applied to home healthcare and health management.