A visual guidance and visual odometry multiplexing method

Abstract

The invention relates to a multiplexing method for visual guidance and a visual odometer. Guide wires with two alternating colors are provided in a moving path of a mobile robot. Wire information of the guide wires is extracted as visual guidance amount by a visual image processing while an alternating frequency of the red and white color is calculated, and thus the function of the visual odometeris achieved. The invention also provides a visual mileage calculation method and an odometer. The multiplexing method for visual guidance and a visual odometer is simple to be implemented, small in calculation amount, more suitable for engineering application and speed measurement of various carriers. According to the multiplexing method for visual guidance and visual odometer, the design cost isreduced based on the existing camera sensor mileage calculation. The displacement of the robot is determined when the wires with the two colors alternately occurs, so that the speed of the robot is determined without complex feature extraction and matching, and the calculation amount is reduced. In addition, the computational power requirement for the CPU is reduced, and the cost is further reduced.

Description

technical field [0001] The invention relates to a visual guidance and visual odometer multiplexing method, belonging to the technical field of visual guidance and visual odometer. Background technique [0002] With the concepts of "Industry 4.0" and "Made in China 2025" being proposed one after another, the technology of Automated Guided Vehicle (AGV) has been fully developed. In recent years, mobile robots have been widely used in logistics handling, sorting, unmanned parking, security patrols and other fields. Guidance and positioning technology, as one of the most important technologies of mobile robot control system, is related to the safety, reliability and efficiency of mobile robot operation. At present, relevant scholars at home and abroad mainly use vision, magnetic induction, laser, inertial, wireless positioning and combination methods for guidance and positioning. Among them, the visual method has become a research hotspot because of its obvious cost advantage a...

AI Technical Summary

Problems solved by technology

These two typical visual odometry methods have high requirements on the accuracy of feature point matching and tracking. At the same time, feature point extraction consumes a lot of computing resources, which is difficult to meet real-time requirements.

Another fatal shortcoming is that it relies too much on the correlation between image frames, which leads to large errors when there are drastic changes in the scene, such as turning, high-speed movement, etc.

Images