Unlock instant, AI-driven research and patent intelligence for your innovation.

Multi-person human body model reconstruction method for low-resolution image

A low-resolution image and high-resolution image technology, applied in the field of 3D vision, can solve the problem of relative accuracy, and achieve the effect of improving the amount of feature information and optimizing feature extraction.

Pending Publication Date: 2022-07-22
TIANJIN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a low-resolution image-oriented multi-person human body model reconstruction method for existing methods that cannot obtain relatively accurate reconstruction results in low-resolution images. The dual-branch reconstruction network for high-resolution images, and through the constraints of contrastive learning and other constraints, high-resolution branch features are fused to realize the basic reconstruction function of low-resolution branches; a cross-scale feature reference strategy is proposed to use high-resolution image features to guide low-resolution Branch feature generation, which effectively guides low-resolution branch features by shortening the feature distance between two branches; introduces an instance segmentation network, optimizes the instance segmentation network and reconstruction network at the same time under the multi-task learning mechanism, and improves human detection frame accuracy, thereby effectively improving the accuracy of the reconstruction results

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Multi-person human body model reconstruction method for low-resolution image
  • Multi-person human body model reconstruction method for low-resolution image
  • Multi-person human body model reconstruction method for low-resolution image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] A multi-person human body model reconstruction method for low-resolution images, comprising the following steps:

[0050] S1. Perform data preprocessing on the public data set, reduce the resolution by downsampling the high-resolution image to obtain a low-resolution image, and scale the low-resolution image to a uniform size on the basis of maintaining the original aspect ratio of the image for training low-resolution branch networks;

[0051] The preprocessing process described in S1 mainly includes the following steps:

[0052] S101, maintaining the original aspect ratio of the high-resolution image, and down-sampling the high-resolution image to (208, 128) to obtain a low-resolution image;

[0053] S102, the low-resolution image is unified to (832, 512) by bilinear interpolation, and the insufficient part is filled with 0;

[0054] S2. Train a high-resolution branch network through the original high-resolution image, and the high-resolution branch network is divid...

Embodiment 2

[0078] see Figure 1-5 , based on a low-resolution image-oriented multi-person human body model reconstruction method described in Embodiment 1, the specific implementation process is as follows:

[0079] (1) Data preprocessing:

[0080] In the present invention, the published Human3.6M, MPI-INF 3DHP, COCO, MPII datasets are used, and the above datasets include crowd activities in various situations; in order to obtain low-resolution images, the original aspect ratio of the images is maintained On the basis of , the data is first downsampled to (208, 128), and the image is fixed to (832, 512) by bilinear interpolation for unified training, and the insufficient area is filled with 0;

[0081] (2) Dual-branch multi-person reconstruction network:

[0082] In the training process, the high-resolution image is first input into the high-resolution branch for training, and the feature information from the high-resolution image is obtained; then the network parameters of the branch ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a multi-person human body model reconstruction method for a low-resolution image, and relates to the technical field of three-dimensional vision. According to the multi-person human body model reconstruction method for the low-resolution image, provided by the invention, based on an end-to-end top-down multi-person reconstruction network, aiming at a double-branch network of a high-resolution image and a low-resolution image, the recognition degree of the network on images with different resolutions is improved through a space attention mechanism; a cross-scale feature reference strategy is proposed, high-resolution image features are utilized to guide generation of low-resolution branch features, and the low-resolution branch features are effectively guided by shortening the feature distance between two branches; a contrast learning constraint is introduced, and feature information from different scenes is distinguished, so that low-resolution branch features from the same scene are closer to high-resolution branch features; and a multi-task learning mechanism is utilized to optimize the added instance segmentation network and reconstruction network at the same time, so that the precision of a reconstruction result is effectively improved.

Description

technical field [0001] The invention belongs to the technical field of three-dimensional vision, and relates to a low-resolution image-oriented multi-person human body model reconstruction method. Background technique [0002] Human body 3D reconstruction technology has always been the focus and development direction in the field of computer vision; this technology has been widely used in film and television, games and other industries; however, these applications are all high-precision 3D human models, which require the help of complex motion capture systems and high-definition cameras; in real life, such high-quality images captured by expensive equipment are often difficult to obtain and cannot be promoted to consumers; considering that in daily life, due to the limitations of various camera equipment , such as mobile phones, tablets or network restrictions, etc., the image will be compressed during the transmission process, and the resolution will be greatly reduced; at ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06T17/00G06T3/40G06V40/10G06V10/40
CPCG06T17/00G06T3/40
Inventor 李坤刘云珂杨敬钰
Owner TIANJIN UNIV