TY - GEN
T1 - Multiple human upper bodies detection via deep deformable part model
AU - Zhu, Aichun
AU - Jin, Jing
AU - Wang, Tian
AU - Wan, Xili
AU - Guan, Xinjie
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/12/29
Y1 - 2017/12/29
N2 - Upper body detection is a challenging problem in practical application scenarios and shares all the difficulties of object detection. This paper focuses on the problems of multiple upper bodies detection in still images, including the diversity of appearances and a non-rigid human body. We present a new architecture for upper body detection using a Convolutional Neural Network (CNN). In this architecture, it contains the appearance model and deformable model. The appearance model is built by 8 upper body parts, and the deformable model uses a Relative Mixture Deformable Model (RMDM). RMDM is defined by each pair of connected parts to compute the relative spatial information in the graphical model. This model is compared with the state of the art on the TV Human Interaction (TVHI) dataset. The experimental results demonstrate the effectiveness of the proposed method.
AB - Upper body detection is a challenging problem in practical application scenarios and shares all the difficulties of object detection. This paper focuses on the problems of multiple upper bodies detection in still images, including the diversity of appearances and a non-rigid human body. We present a new architecture for upper body detection using a Convolutional Neural Network (CNN). In this architecture, it contains the appearance model and deformable model. The appearance model is built by 8 upper body parts, and the deformable model uses a Relative Mixture Deformable Model (RMDM). RMDM is defined by each pair of connected parts to compute the relative spatial information in the graphical model. This model is compared with the state of the art on the TV Human Interaction (TVHI) dataset. The experimental results demonstrate the effectiveness of the proposed method.
KW - Convolutional Neural Network
KW - deformable model
KW - upper body detection
UR - https://www.scopus.com/pages/publications/85050344273
U2 - 10.1109/CAC.2017.8243722
DO - 10.1109/CAC.2017.8243722
M3 - 会议稿件
AN - SCOPUS:85050344273
T3 - Proceedings - 2017 Chinese Automation Congress, CAC 2017
SP - 5299
EP - 5303
BT - Proceedings - 2017 Chinese Automation Congress, CAC 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2017 Chinese Automation Congress, CAC 2017
Y2 - 20 October 2017 through 22 October 2017
ER -