To address the problems of cumbersome operation and low efficiency of manual annotation in current traditional sitting posture annotation methods, this article proposes an automatic annotation method for pressure data based on three-dimensional sitting posture. Real time synchronous collection of binocular visual data and pressure data based on dual pointer timestamp matching. The normalization and adaptive median filtering are utilized to process pressure data, and remove the dimensional influence and peak noise of pressure data. By using 2D pose estimation and matching optimization, coordinate transformation, and multi-point triangulation to process visual data, 6 key point information of the 3D human body are extracted. A skeleton image based on sitting posture features and a 3D projection angle feature between adjacent nodes are constructed, and a 3D sitting posture based annotation information generation model is formulated. The annotation information is utilized to label the pressure data and create an annotated sitting pressure dataset. In practical applications, the average time difference between real-time synchronous collection of single sample data is only 21 ms, and the accuracy of label generation is 98. 98% . The average time for automatic labeling is 0. 199 s, and the labeling speed is 13. 3 times faster than manual labeling.