Background Precise anthropometric data are vital for ergonomic assessment and farm machinery design. Manual methods, although dependable, are labor-intensive and susceptible to error. Objective This study aimed to develop and validate a computer vision (CV) based non-contact system for anthropometric measurements, focusing on stature, vertical reach, trochanteric height, and chest circumference. Methods An Intel RealSense D435i stereo camera with OpenCV, mediapipe captured images from three angles (front, diagonal, side) at 2.5–3.5 m. Thirty-two participants (16 male, 16 female) were measured, with manual anthropometry as reference. Accuracy was assessed using mean absolute difference (MAD) and mean absolute percentage error (MAPE), while reliability was examined via intraclass correlation coefficient (ICC, p 0.90, α > 0.85). Vertical reach showed the largest bias (83–90 mm; MAPE 4–5%), yet reliability remained high (ICC 0.88–0.91). Trochanteric height had minimal discrepancies (29–36 mm; MAPE ≤ 4%) with good consistency (ICC 0.85–0.90). Chest circumference showed small bias (±10 mm; MAPE 3–4%) but lower reliability (ICC 0.75–0.80), likely due to respiration. Overall, CV measurements were reliable, non-invasive, and scalable. Conclusions The CV-based system offers a precise, scalable, and non-contact alternative to manual anthropometry, enabling reliable data collection for ergonomic evaluation and improved man–machine compatibility in agriculture.
Lohan et al. (Fri,) studied this question.