The application of sports game video analysis in athlete training and competition analysis feedback has attracted extensive attention, but the traditional sports human body posture estimation method has a large error between the athlete’s human body posture estimation results and the actual results in the complex environment and the athlete’s body parts are blocked. Therefore, this study proposes a convolutional neural network for athlete pose estimation in sports game video. Based on the improved model, multiscale model, and large perception model, a superimposed hourglass network is constructed, and the gradient disappearance problem of the convolutional neural network is solved using intermediate supervision. The experimental results show that the athlete pose estimation model based on the convolutional neural network can improve the accuracy of athlete pose estimation and reduce the negative impact of occlusion environment on athlete pose estimation to a certain extent. In addition, compared with other athletes’ standing posture estimation methods, the model has competitive advantages and high accuracy under widely used standard conditions.

With the development of the information age, there is almost one mobile smart device based on android, which is inseparable from mobile smart devices in both learning and life. In order to explore the effects of mobile smart devices on tennis teaching, this article mainly introduces the research on the tennis online teaching information platform based on android mobile smart terminals. This article first uses the android system framework and software architecture to design the technical aspects of the tennis online teaching information platform and then analyzes and improves the functional and nonfunctional requirements of the tennis online teaching information platform and students’ needs for mobile learning. For the design of aspects other than the technology of the online teaching information platform, the control group and the experimental group were designed to carry out teaching experiments, comparing the traditional teaching methods and the teaching methods of the online teaching information platform to bring out different teaching effects to tennis teaching. The results show that online teaching has a better learning effect on tennis skills and tennis theory knowledge, and the academic performance of the traditional teaching method is improved by 20%. In terms of increasing interest in tennis courses, the online teaching information platform has improved 70% of students’ interest.