Posture identification method and device based on near-infrared TOF camera depth information

Abstract

The invention discloses a posture identification method based on near-infrared TOF camera depth information. The posture identification method includes the steps that a depth image is obtained through an SR4000, earlier-stage operation processing is carried out on the depth image, a human body object is obtained and skeletonized, then coordinates of end points of the head, the hands, the feet and the mass center of the human body target are obtained, the heights between the end points and the ground and the skeleton line distances between the end points and the mass center are calculated, the attributes of the end points are identified according to the skeleton line distances and the ground heights, and then posture identification is achieved in cooperation with motion characteristics and the depth information. In this way, the target tracking difficulty and the algorithm complexity are lowered, the identification effective rate and the target division accuracy are improved, and convenience is brought to real-time embedded transplanting. The invention further discloses a device used for implementing the posture identification method.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a gesture recognition method and device based on near-infrared TOF camera depth information applied in the field of unmanned vehicles. Background technique [0002] At present, interactive human body recognition has been widely used in industries such as gaming, retail experience, human-computer interaction, security engineering, remote control, and health care. However, since existing gesture recognition systems generally adopt traditional color cameras to capture color images, color images are easily affected by illumination changes and complex backgrounds, resulting in difficult object tracking and imprecise object segmentation. At the same time, the method of obtaining the target by processing the color image in the existing gesture recognition system has problems such as high algorithm complexity and inconvenient real-time embedded transplantation. Content...

AI Technical Summary

Problems solved by technology

However, since existing gesture recognition systems generally use traditional color cameras to capture color images, color images are easily affected by illumination changes and complex backgrounds, resulting in difficult object tracking and imprecise object segmentation.

At the same time, the existing gesture recognition system obtains the target by processing the color image, and there are problems such as high algorithm complexity and inconvenient real-time embedded transplantation.

Images