Abstract: To improve the accuracy and automation level of volume measurement for excavated soil during tunnel construction, a method for measuring the volume of excavated soil in shield tunnels based on laser point cloud and vision technology is proposed. The system hardware includes two single-line laser radars and one 4 K camera. The two laser radars are used to collect cross-section point cloud and longitudinal point cloud data, while the camera captures video information around the equipment. An improved optical flow method is used to determine the motion status of the conveyor belt. By combining the Triangle Accumulated Cross-sectional Area method (TACA) with the improved Adaptive Edge Iterative Closest Point (AE-ICP) algorithm, accurate measurement of the cross-sectional area of the excavated soil is achieved, and the volume of excavated soil is obtained through numerical integration using the Simpson′s rule. Experimental results indicate that this method demonstrates high measurement accuracy and robustness in complex tunnel environments, with the relative error of volume measurement controlled within 5% and the average error of speed measurement within 1%, showing promising prospects for engineering applications.