jats:p Over the past decades, the construction industry lags further and further behind the manufacturing sector when productivity is considered. Current practices for managing labour productivity are labour intensive, time and cost consuming and error prone. They are mainly reactive processes initiated after the detection of a negatively influencing factor. Although research studies have been performed towards leveraging these limitations, a gap still exists in managing the labour productivity of multiple workers at the same time accurately, unobtrusively and cost and time efficiently. This paper proposes a trajectory-based method to address this gap. Firstly, a computer vision-based method extracts the three-dimensional (3D) trajectories of workers. Secondly, a clustering-based method converts the 3D trajectories into work cycles that depict the labour input. The proposed method features an accuracy of 84% in terms of inferring the total labour time spent on construction-related tasks – that is, direct work. </jats:p>