원문정보
초록
영어
The lower limbs of motion body contain rich identification of individuals in the process of walking. A gait recognition method based on ankle joint motion trajectory and bending angle is proposed. First it obtains lower limb joint points according to each part of the body and height proportion. It obtains the position coordinates of the toe by using skeleton algorithm. According to the position relationship between joint points and toe, we can extract bending angle information. The feature vector is made up of the relative velocity of ankle joint motion trajectory and the bending angle. Support vector machine (SVM) Classifier and the Nearest Neighbor (NN) Classifier are used for the gait classification. In addition, the most methods are tested experiment performance under 0 degree viewing angle. We use 45 degree viewing angle which has a larger view in our experiment. CASIA_A database is used to evaluate the performance of the proposed method. The experimental results demonstrate that the approach has an encouraging recognition performance.
목차
1. Introduction
2. Gait Feature Extraction
2.1. Motion Region Segmentation
2.2. Joint Point Position Extraction
2.3. Toe Coordinates Extraction
2.4. Feature Extraction
3. Experimental
3.1. Experimental Results
3.2. Method Comparison
4. Conclusion
Acknowledgements
References