Centralized control type soccer robot identification system and identification method for double visual information fusion

Abstract

The invention discloses a centralized control type soccer robot identification system and an identification method for double visual information fusion and belongs to the technical field of machine vision. The centralized control type soccer robot identification system comprises a left visual sensor for shooting a left field target body, a right visual sensor for shooting a right field target body, two PCs (Personal Computers), an Ethernet interface line, a color code for representing the robot pose and the ID (Identification) information, and an image processing system. The centralized control type soccer robot identification system and the identification method have the beneficial effects that the two PCs are respectively connected with the left visual sensor and the right visual sensor; the left field target body and the left field target body are identified according to a color code identification algorithm after image acquisition, image calibration and feature extraction are carried out; the two PCs are used for information transmission, information judgment and information fusion through an Ethernet interface to obtain the information of all target bodies on the complete field; and the validity and the information loss situation of the identification information can be reasonably judged and treated, so that the identification precision and the real time of the system is improved, therefore, the system can be taken as a scientific research and innovative practice education platform.

Description

technical field [0001] The invention relates to the technical field of machine vision, in particular to a centralized control soccer robot recognition system and recognition method for dual vision information fusion. Background technique [0002] Robot football was first proposed by Alan Mackworth, a professor at the University of British Columbia in Canada, at an international artificial intelligence conference in 1992. In his paper "On Seeing Robots", he proposed the concept of a robot with vision and decision-making capabilities chasing football. The robot soccer game provides a landmark and challenging subject for the development of artificial intelligence and intelligent robotics. Once this idea was put forward, it has been widely approved and actively responded by scientists from all over the world. Many famous research institutions and organizations in the world have begun to carry out research, put it into practice and continuously promote its development. [0003] ...

AI Technical Summary

Problems solved by technology

[0012] In order to overcome the large field centralized control football robot vision system using a single vision sensor, the acquired image will also cause large image distortion due to ultra-wide-angle and large field of view imaging, which will affect the accuracy of correction and recognition. Considering large-resolution image scanning and multiple Target recognition takes a lot of time, which will inevitably affect the problem of image acquisition, processing speed and real-time performance of the whole system. The present invention provides a centralized control football robot recognition system and recognition method with dual visual information fusion, aiming to improve the system's Recognition accuracy and real-time

Images