Animal Exercise: A New Evaluation Method

Abstract

At present, Animal Exercise courses rely too much on teachers’ subjective ideas in teaching methods and test scores, and there is no set of standards as a benchmark for reference. As a result, students guided by different teachers have an uneven understanding of the Animal Exercise and cannot achieve the expected effect of the course. In this regard, the authors propose a scoring system based on action similarity, which enables teachers to guide students more objectively. The authors created QMonkey, a data set based on the body keys of monkeys in the coco dataset format, which contains 1,428 consecutive images from eight videos. The authors use QMonkey to train a model that recognizes monkey body movements. And the authors propose a new non-standing posture normalization method for motion transfer between monkeys and humans. Finally, the authors utilize motion transfer and structural similarity contrast algorithms to provide a reliable evaluation method for animal exercise courses, eliminating the subjective influence of teachers on scoring and providing experience in the combination of artificial intelligence and drama education.