IDEAS home Printed from https://ideas.repec.org/a/gam/jmathe/v10y2022i16p2841-d884265.html
   My bibliography  Save this article

HOME: 3D Human–Object Mesh Topology-Enhanced Interaction Recognition in Images

Author

Listed:
  • Weilong Peng

    (School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou 511442, China
    These authors contributed equally to this work.)

  • Cong Li

    (School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou 511442, China
    These authors contributed equally to this work.)

  • Keke Tang

    (Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou 511442, China)

  • Xianyong Liu

    (Robotics Institute, Ningbo University of Technology, Ningbo 315100, China)

  • Meie Fang

    (School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou 511442, China
    These authors contributed equally to this work.)

Abstract

Human–object interaction (HOI) recognition is a very challenging task due to the ambiguity brought by occlusions, viewpoints, and poses. Because of the limited interaction information in the image domain, extracting 3D features of a point cloud has been an important means to improve the recognition performance of HOI. However, the features neglect topological features of adjacent points at low level, and the deep topology relation between a human and an object at high level. In this paper, we present a 3D human–object mesh topology enhanced method (HOME) for HOI recognition in images. In the method, human–object mesh (HOM) is built by integrating the reconstructed human and object mesh from images firstly. Therefore, under the assumption that the interaction comes from the macroscopic pattern constructed by spatial position and microscopic topology of human–object, HOM is inputted into MeshCNN to extract the effective edge features by edge-based convolution from bottom to up, as the topological features that encode the invariance of the interaction relationship. At last, topological cues are fused with visual cues to enhance the recognition performance greatly. In the experiment, HOI recognition results have achieved an improvement of about 4.3% mean average precision (mAP) in the Rare cases of the HICO-DET dataset, which verifies the effectiveness of the proposed method.

Suggested Citation

  • Weilong Peng & Cong Li & Keke Tang & Xianyong Liu & Meie Fang, 2022. "HOME: 3D Human–Object Mesh Topology-Enhanced Interaction Recognition in Images," Mathematics, MDPI, vol. 10(16), pages 1-15, August.
  • Handle: RePEc:gam:jmathe:v:10:y:2022:i:16:p:2841-:d:884265
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2227-7390/10/16/2841/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/2227-7390/10/16/2841/
    Download Restriction: no
    ---><---

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jmathe:v:10:y:2022:i:16:p:2841-:d:884265. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    We have no bibliographic references for this item. You can help adding them by using this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.