Single Image Based Infant Body Height and Weight Estimation
The collection of infant body data such as height and weight is a useful mean of tracking its growth and wellness. The contact-based measurements using height and weight scales are manual and cumbersome, camera-based methods were proposed to obtain features from the adult face or body for height and weight estimation. In this paper, we created a clinical dataset including 200 newborns collected at obstetrics, and benchmarked four convolutional neural networks for infant height estimation, where the MobileNet, a lightweight and efficient network, was chosen as the backbone for deep feature extraction. Moreover, we investigated different MobileNet-based variants for infant weight estimation, including the linear regression model, one-task model and multi-task model. Several sets of experiment were carried out on the newborn dataset to validate the effectiveness of the proposed methods. The results show that the Mean Absolute Error (MAE) of different models are quite similar, which are in a decent error range (average MAE for height estimation is <1.1 cm and average MAE for weight estimation is <0.28 kg). Among them, the multi-task MobileNet has better temporal stability given its lower variance of measurement in a video.