Atpresent, the sit-up test in many school physical fitness test projects still needs to be manually counted, which notonly consumes manpower, butalso is inefficient. In orderto promote the intelligentdevelopmentofphysical fitness, thispaperproposesamethodforcounting sit-upbehaviorbased on afusionimplementationoftheFast-OpenPose human posture estimation modeland supportvector machine(SVM) . The position information ofthe keypoints ofthe human bodyin the continuous video stream of sit-ups is detected by OpenPose, and the SVM is used to classify the motion features ofthe coordinatedataofeach frameofthekeypointsofthehuman body. In view ofthe shortcomingsof the original OpenPose network, such as high complexity, large number of model parameters and long detection time, this paper uses FasterNet to lightweightly improve its main feature extraction part, and optimizes the more efficient single branch network structure and convolution type in the prediction branch. Finally, spatial group-wise enhance (SGE) is introduced to makeupforthelossofaccuracy. Based on theCoCo2017dataset, an additional1000imagedata ofsit-up scene are expanded for model training, and the experimental results show that the improved Fast-OpenPose reduces the numberofmodelparameters by nearly80% and improves the speed of keypointdetection by110% , while losing partof the accuracy but not affecting the sit-up pose estimation. Compared with other improved models in the same series, ithas more lightweightand speed advantages while maintaining similar mAP values.