Human body image recognition method and apparatus

Abstract

The present application discloses a human body image recognition method and apparatus. The method comprises: by combining the depth value with the gradient information, obtaining a video image containing a tracking object through capturing; reading a depth image of the video image; determining a depth value d1(x) of each pixel point x in the depth image; determining gradient information f [theta](1, x) around each pixel point x according to the depth value d1(x) of each pixel point x; and determining a human body depth image in the depth image according to the gradient information of each pixel point x. According to the technical scheme of the present application, the purpose of accurately recognizing the depth image of the human body is achieved, rapid recognition of the bone is realized,the problems such as the target is lost and is difficult to be recaptured during the recognition process are avoided, and the recognition effect can be effectively improved.

Description

technical field [0001] The present application relates to the technical field of image recognition and processing, and in particular, to a human body image recognition method and device. Background technique [0002] With the rapid and in-depth development of the field of robotics, human-computer interaction technology has increasingly become one of the research hotspots. Among them, intelligent human body following is the main research part in the field of mobile robots. This technology can better serve users, improve and perfect the intelligence of human-computer interaction, and make effective responses to the instructions issued by users. There are many following methods currently applied to robots, such as based on ultrasonic processing, based on infrared processing, and based on visual image processing. If the ultrasonic processing method is used to determine the specific target, and the infrared processing method has many limitations, such as short detection distance...

AI Technical Summary

Problems solved by technology

If the ultrasonic processing method is used to determine the specific target, and the infrared processing method has many limitations, such as the short detection distance and the difficulty of determining the specific target, the human body tracking is easily disturbed and the tracking fails.

If it is based on visual image processing, the above problems can be solved to a certain extent, but if the human skeleton recognition and follow-up of kinect is used, the skeleton recognition will be slow, and the target will be lost in the middle and it is difficult to re-capture, which will make the following effect poor.

[0003] Aiming at the characteristics of slow bone recognition in related technologies, resulting in the loss of midway targets, and poor follow-up effects, no effective solution has been provided yet.

Images