Estimating human posture in crowded smart teaching environments is a fundamental technical challenge for measuringlearners’ level of engagement. This work presents a model for detecting critical points in human posture using ECAv2-HRNetin crowded situations. The paper introduces a method called ECAv2Net, which combines a channel feature reinforcementmethod with the ECANet attention mechanism network. This innovation improves the performance of the network. Additionally,ECAv2Net is integrated into the high-resolution network HRNet to create ECAv2-HRNet. This fusion allows for the incorporationof more useful feature information without increasing the model parameters. The paper also presents a human posture datasetcalled GUET CLASS PICTURE, which is designed for dense scenes. Experimental results using this dataset, as well asa public dataset, demonstrate the superior performance of the human posture estimation model based on ECAv2-HRNetproposed in this paper.