Human body shape and posture estimation method for object occlusion scene

Abstract

The invention discloses a human body shape and posture estimation method for an object occlusion scene, and the method comprises the steps: converting a weak perspective projection parameter obtainedthrough calculation into a camera coordinate, and obtaining a UV image containing human body shape information under the condition of no occlusion; adding a random object picture to the human body two-dimensional image for shielding, and obtaining a human body mask under the shielding condition; training a UV map restoration network of an encoding-decoding structure by using the obtained virtual occlusion data; inputting a human body color image shielded by a real object, and constructing a saliency detection network of an encoding-decoding structure by taking the mask image as a true value; supervising human body coding network training by using the hidden space features obtained by coding; inputting the shielded human body color image to obtain a complete UV image; and recovering the human body three-dimensional model under the shielding condition by using the vertex corresponding relationship between the UV image and the human body three-dimensional model. According to the method, the shape estimation of the shielded human body is converted into the image restoration problem of the two-dimensional UV chartlet, so that the real-time and dynamic reconstruction of the human body inthe shielded scene is realized.

Description

technical field [0001] The invention belongs to the fields of computer vision and three-dimensional vision, and in particular relates to a method for estimating human body shape and posture in an object-occluded scene. Background technique [0002] Estimating the shape and pose of a 3D human body from a single image is a research hotspot in the field of 3D vision in recent years. It plays an important role in the application of virtual reality technology such as human motion capture, virtual fitting and human animation. In recent years, deep learning technology has simplified the solution to restore the overall shape of the human body from a single image. Especially after the SMPL model was proposed and widely used, the 3D human body shape and pose estimation of monocular images has undergone multiple stages of vigorous development. , including (1) optimize and solve SMPL parameters by matching two-dimensional visual features; (2) use convolutional neural network (CNN) to d...

AI Technical Summary

Problems solved by technology

However, most of the existing methods do not consider the common phenomenon of occlusion between people and objects.

Such methods cannot be directly transferred to human estimation in occluded scenarios without explicitly considering occlusion.

This makes them very sensitive to scenes with occlusion or even slight object occlusion, which is difficult to meet the needs of reality

[0003] For a long time, the 3D shape and pose estimation of the human body in occlusion scenes has always been a difficult point in the field. The main reasons are: (1) Object occlusion will introduce serious ambiguity in network training, and lead to a significant reduction in image features that can be directly used , thus affecting the complete 3D human body shape estimation effect

(2) Due to the universality and randomness of occluded objects, it is difficult for the network to accurately segment the pixels where the human body and occluded objects are located in the image, resulting in interference with the reconstruction results

Images