We validated a multi-sensor chest-strap against indirect calorimetry and further introduced the total-acceleration-variability (TAV) method for analyzing high-resolution accelerometer data. Linear regression models were developed to predict oxygen uptake from the TAV-processed multi-sensor data. Individual correlations between observed and TAV-predicted oxygen uptake (V̇O2) were strong (mean r = 0.94) and bias low (1.5 mL·min(-1)·kg(-1), p < 0.01; 95% confidence interval: 8.7 mL·min(-1)·kg(-1); -5.8 mL·min(-1)·kg(-1)); however, caution should be taken when a single-model value is used as a surrogate for V̇O2.