Three-dimensional point cloud head posture estimation system and method based on ordered regression and soft labels

Abstract

The invention discloses a three-dimensional point cloud head posture estimation system and method based on ordered regression and soft labels. The system comprises a feature learning network module which is used for the layered feature extraction of point cloud data; the prediction network module is used for mapping the features obtained by the feature learning network module to a head attitude angle to obtain an angle prediction value, and substituting the angle prediction value and the head attitude angle serving as a label into a first loss function; the sorting network module is used for carrying out dimension division on the head attitude angle to form a plurality of subtasks, generating a soft label according to the relationship between the head attitude angle serving as a label andthe subtasks, carrying out value prediction on the features obtained by the feature learning network module, and substituting the value prediction of the point cloud data and the soft label into a second loss function; network updating module. The loss of the sorting network module and the loss of the prediction network module are combined to introduce the sorting network so as to guide the learning of the prediction network, so that the feature extraction is more accurate, and the precision of the prediction network is improved.

Description

technical field

[0001] The invention relates to the field of head pose estimation, in particular to a system and method for 3D point cloud head pose estimation based on ordered regression and soft labels. Background technique

[0002] Robust head pose estimation is the basis of many problems in computer vision and computer graphics, and has a wide range of applications in human-computer interaction, such as: VR / AR, driver behavior analysis, etc. In recent years, head pose estimation from RGB images has made great progress and has been successfully applied to constrained scenes. However, the challenges posed by unconstrained scenes, such as illumination changes, large pose changes, and more severe occlusions, make RGB-based methods unreliable. Moreover, using RGB images to convey facial appearance information is considered a threat to individual privacy, which is one of the major concerns in modern society and limits its further applications.

[0003] With the popularity of...

Images