首页> 外国专利> POSE RECOGNITION METHOD AND APPARATUS BASED ON TWO-DIMENSIONAL CAMERA, AND DEVICE AND STORAGE MEDIUM

POSE RECOGNITION METHOD AND APPARATUS BASED ON TWO-DIMENSIONAL CAMERA, AND DEVICE AND STORAGE MEDIUM

机译:基于二维相机的姿态识别方法和装置,以及设备和存储介质

摘要

A pose recognition method and apparatus based on a two-dimensional camera, and a device and a storage medium, which relate to the field of artificial intelligence. The method comprises: acquiring, by means of a two-dimensional camera, a human body image of a human body to be subjected to recognition (S1); according to the human body image, extracting body contour information, pose information and gender information of said human body (S2); generating an SMPL model according to the body contour information, the pose information and the gender information (S3); acquiring a 3D node feature from the SMPL model (S4); extracting a 2D node feature of said human body from the human body image (S5); generating an error function according to the 3D node feature and the 2D node feature (S6); adjusting the SMPL model according to the error function, and extracting a target 3D joint feature from the adjusted SMPL model (S7); acquiring skeleton information according to the target 3D joint feature (S8); and performing pose analysis according to the skeleton information (S9). The pose recognition method and apparatus based on a two-dimensional camera, and the device and the storage medium can be applied to the field of blockchains, and can accurately recognize a pose of a human body to be subjected to recognition.
机译:一种基于二维相机的姿势识别方法和装置,以及涉及人工智能领域的装置和存储介质。该方法包括:借助于二维相机获取人体的人体图像以进行识别(S1);根据人体图像,提取体轮廓信息,姿势信息和所述人体的性别信息(S2);根据主体轮廓信息,姿势信息和性别信息生成SMPL模型(S3);从SMPL模型获取3D节点功能(S4);从人体图像中提取所述人体的2D节点特征(S5);根据3D节点特征和2D节点特征生成错误功能(S6);根据误差函数调整SMPL模型,并从调整后的SMPL模型中提取目标3D关节功能(S7);根据目标3D联合特征获取骨架信息(S8);根据骨架信息(S9)执行姿势分析。基于二维相机的姿势识别方法和装置和装置和存储介质可以应用于块状的场,并且可以准确地识别要受到识别的人体的姿势。

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号