A hybrid framework for automatic joint detection of human poses in 110 depth frames

作者：Kong, Longbo; Yuan, Xiaohui^*; Maharjan, Amar Man

来源：Pattern Recognition, 2018, 77: 216-225.

DOI：10.1016/j.patcog.2017.12.020

• Human pose detection
• Joint detection
• Human body model
• Geodesic features

Human pose detection has been an active research topic, and many studies have been done to address different problems in the topic. However, very few methods are proposed to detect joints in the human body. In this paper, we proposed a novel hybrid framework to detect joints automatically by using depth camera. In the proposed method, joints are categorized into two classes: implicit joints and dominant joints. Implicit joints are the joints on the torso, such as neck and shoulders. Dominant joints include elbows and knees. In the hybrid framework we proposed, a loose skeleton model is used to locate implicit joints, and data-driven method is applied to detect dominant joints. The highlight of the proposed work is that geodesic features of the human body are used to build the skeleton model and detect joints. To evaluate our work, experiments are conducted on the dataset recorded by a Microsoft Kinect and compared with state-of-art methods. The results demonstrate that the proposed work can deliver stable and accurate detection results of joints.

• 出版日期2018-5
• 单位中国地质大学（北京）