Single camera multi-view anthropometric measurement of human height and mid-upper arm circumference using linear regression

Abstract

Background: Manually measured anthropometric quantities are used in many applications including human malnutrition assessment. Training is required to collect anthropometric measurements manually, which is not ideal in resource-constrained environments. Photogrammetric methods have been gaining attention in recent years, due to the availability and affordability of digital cameras.

Objective: The primary goal is to demonstrate that height and mid-upper arm circumference (MUAC)-indicators of malnutrition-can be accurately estimated by applying linear regression to distance measurements from photographs of participants taken from five views, and determine the optimal view combinations. A secondary goal is to observe the effect on estimate error of two approaches which reduce complexity of the setup, computational requirements and the expertise required of the observer.

Methods: Thirty-one participants (11 female, 20 male; 18-37 years) were photographed from five views. Distances were computed using both camera calibration and reference object techniques from manually annotated photos. To estimate height, linear regression was applied to the distances between the top of the participants head and the floor, as well as the height of a bounding box enclosing the participant's silhouette which eliminates the need to identify the floor. To estimate MUAC, linear regression was applied to the mid-upper arm width. Estimates were computed for all view combinations and performance was compared to other photogrammetric methods from the literature-linear distance method for height, and shape models for MUAC.

Results: The mean absolute difference (MAD) between the linear regression estimates and manual measurements were smaller compared to other methods. For the optimal view combinations (smallest MAD), the technical error of measurement and coefficient of reliability also indicate the linear regression methods are more reliable. The optimal view combination was the front and side views. When estimating height by linear regression of the distance from the head to the floor, the mean MAD was 10.51 mm ± 6.52 mm SD, and when estimating height from the bounding box using the reference object, the mean MAD per participant was 11.53 mm ± 6.43 mm SD. When estimating MUAC from the mid-upper arm radius using the reference object, the mean MAD was 7.24 mm ± 4.79 mm SD. The mean MAD for all methods when using camera calibration was 2-3 mm smaller.

Conclusions: Applying linear regression to distance measurements from photos of adults taken from multiple view angles has been shown to accurately estimate height and MUAC to within the accuracy required for nutrition assessment. Future work will focus on automating the landmark detection, and validating the methods on populations that include undernourished adults and children of all nutrition statuses. These future works will improve the practicality of this method as a potential tool for nutrition assessment by novice users.

Fig 1. Illustration of photo capture setup: Views 1 to 5 –relative orientations between the camera and the participant’s left and right arm.

Fig 2

Manually annotated markers of a photo from A) view 1, and B) view 3, of participant 0007. Black circles are the corners of the reference object; black solid line is the floor line; blue cross is the top of the head; red dashed line is the bounding box; green x’s are the two edges of the left mid-upper arm; and yellow x’s are the two edges of the right mid-upper arm. Note that the floor line and the bottom edge of the bounding box do not align.