Hip-hop action image recognition based on symmetric algorithm and iterative weighting of dense sampling
- PDF / 1,191,359 Bytes
- 11 Pages / 595.276 x 790.866 pts Page_size
- 82 Downloads / 186 Views
ORIGINAL RESEARCH
Hip‑hop action image recognition based on symmetric algorithm and iterative weighting of dense sampling Zhen Han1 · Minhang Ma1 Received: 28 May 2020 / Accepted: 11 September 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract With the rapid increase of hip-hop video data, facing a large number of rapidly updated data, automatic, accurate and fast analysis and recognition of relevant information in hip-hop video has become an urgent problem to be solved. An image recognition method of hip-hop action based on symmetric algorithm and iterative weighting of dense sampling is proposed. Firstly, the symmetric action feature of human hip-hop action image is extracted by the feature extraction method based on symmetric algorithm. Then, the symmetric action feature is obtained by fusion of the hip-hop action recognition algorithm based on iterative weighting of dense sampling. Finally, the action feature is obtained based on the fused action feature. The K-nearest neighbor classification learning method is used to recognize the hip-hop action image. The experimental results show that, under the same sample number, the number of omissions of children is 3, the extraction rate is 92.5%; the number of omissions of adults is 0, the extraction rate is 100%. This method can extract the human hip-hop image well, which lays a good foundation for the subsequent image recognition. Keywords Symmetric algorithm · Dense sampling · Iterative weighting · Hip-hop · Action · Image · Recognition
1 Introduction From an intuitive point of view, human body actions generally include walking, running, arm waving, squatting, sitting, jumping and other daily life processes, which are the most external manifestations of human dynamics. On the one hand, these actions are specific manifestations of people’s life, learning, work and other aspects, and are the basic form of human existence and life (Gao et al. 2017). On the other hand, human action itself contains powerful information, e.g. the recognition of facial expression can reflect the psychological and physiological state of the human body— smile, sadness or fatigue, and gesture recognition can convey a lot of valuable information (Lozano-Monasor et al. 2017). By recognizing these actions, we can effectively recognize and analyze the dynamic process of human body, understand the information conveyed by human body, and thus * Zhen Han [email protected] Minhang Ma [email protected] 1
Ministry of Physical Education and Research, Zhejiang International Studies University, Hangzhou, China
achieve intelligent monitoring, and provide basic basis for other intelligent applications (Qian et al. 2017). Recognition of human action is an important step in pattern recognition and artificial intelligence development (Zhao et al. 2013). Through recognition of human action, we can grasp the spatial and temporal characteristics of action occurrence, basic classification and other information to provide more effective basis for future applications. This is a v
Data Loading...
