Target positioning method based on RGBD

Abstract

The invention provides a target positioning method based on a RGBD, and the main steps comprise hardware environment arrangement and device initialization; the RGBD sensor is adopted to acquire depth data and color image of a mobile robot in current frame, a depth image is segmented based on the depth data to obtain a target region in the depth image, the target image is set as SearchRect_depth and is mapped to the color image, and the corresponding color image part is recorded as SearchRectROI; in the color image SearchRectROI, a CAMSHIFT method is utilized to calculate a position (x, y) of a target in the color image; the depth data is combined to calculate world coordinates (xw, yw, zw) of the current target; the world coordinates (xw, yw, zw) of the current target is transmitted to the mobile robot through a communication system, and the robot can control its self motion. According to the invention, the method has advantage of fast calculation speed, accurate positioning, strong adaptability for environment change and good expandability for different targets.

Description

technical field [0001] The invention belongs to the field of visual positioning, and in particular relates to an RGBD-based target positioning method. Background technique [0002] The positioning ability of a mobile robot is the basis and key to realize high-performance and high-precision navigation. It can move autonomously and complete a given task, and must obtain its own precise position and attitude in real time. At present, mobile robots are equipped with GPS and inertial navigation systems. Their technology is relatively mature, and many excellent products can be purchased easily. While GPS and inertial navigation systems have many advantages, there are also some disadvantages that deserve attention: [0003] (1) GPS data is generally updated every second, which cannot meet the requirements of fast movement of the robot. [0004] (2) When the robot is in some specific postures, such as flying backwards, diving and weightlessness, it is often impossible to receive G...

AI Technical Summary

Problems solved by technology

[0003] (1) GPS data is generally updated every 1 second, which cannot meet the requirements of fast movement of robots

[0004] (2) When the robot is in some specific postures, such as flying back, diving and weightlessness, it is often impossible to receive GPS signals

[0005] (3) In an indoor environment, the GPS signal cannot be received

[0006] When studying mobile robot control algorithms and environmental perception methods, it is often necessary to conduct experiments indoors. In indoor and some environments where GPS cannot be used, robots often cannot know their own location information, weather conditions, and cloud thickness may also affect GPS signals. take over

In addition, the change of the robot's own load will also change the mass distribution and balance conditions of the robot, making the control of the mobile robot more difficult.

Images