For daily motion recognition, each researcher builds their own method to recognize their own specific target actions. However, for other types of target motions, they cannot use their method to recognize other kinds of motions because the features of their target motions that they extracted cannot be extracted from other kinds of motions. Therefore, we wanted to develop a general method that can be used in most kinds of motions. From our observations, we found that a meaningful motion is combined with some basic motions. Therefore, we could recognize basic motions and then combine them to recognize a target motion. First, we simply defined the basic motions according to the sensor’s basic sensing directions. Second, we used k-nearest neighbors (KNN) and dynamic time warping (DTW) to recognize different categories of basic motions. Then, we gave each basic motion a specific number to represent it, and finally, used continuous dynamic programming (CDP) to recognize a target motion by the sequence of basic motions we collected. In our experiment on our basic motions, the accuracy of all of the basic motions is higher than 80%, so the recognition of basic motions is reliable. Then, we performed an experiment for recognizing the target motions. The results of recognizing the target motions were not good, the average accuracy being only 65.9%, and we still have to improve our system. However, we also compared our system with recognizing motions by using another general recognition method, KNN. And the average accuracy of using KNN to recognize motions was 53.4%. As this result shows, our method still obtains better results in recognizing different kinds of motions than using KNN.
Read full abstract