| The development of the domestic civil aviation industry has made the air cargo volume increase year by year.The automatic baggage sorting system adopted by domestic civil aviation airports has greatly improved the efficiency of airport baggage handling.However,for most of the bags after automatic sorting at airports,they still need to be manually transported from the baggage chute to the check-in truck.This is not only labor-intensive,but also prone to damage to the baggage,which is time-consuming and labor-intensive,which greatly affects the airport luggage Handling efficiency,so there is an urgent need to study a set of intelligent handling equipment for intelligent handling of airport luggage.In this paper,using machine vision recognition technology,through the calibration principle of Zhang Zhengyou calibration method through two softwares of MATLAB and Open CV,the calibration board checkerboard is calibrated respectively,and the camera calibration software with high calibration accuracy is selected through comparative experiments.Then by comparing the two target recognition results based on the edge feature and the HSV color feature,the appropriate target recognition method is selected.Finally,the hardware selection and overall layout design of the airport baggage handling intelligent handling system were carried out,and the intelligent handling test of different types,sizes and materials of baggage was carried out.Through the analysis of the test results,the feasibility and effectiveness of the visual identification system were verified.The main contents of this paper are as follows:(1)Clarified the concepts of the four coordinate systems of image coordinate system,pixel coordinate system,world coordinate system and camera coordinate system and the conversion relationship between them under the camera coordinate system,and converted the pixel coordinates of the target object shot by the camera to the camera Under the coordinate system,MATLAB and Open CV software are used to calibrate the checkerboard.Through comparative experiments,the camera parameters are calculated using the principle of Zhang Zhengyou calibration method,and the camera calibration results and errors are analyzed.(2)A preliminary visual recognition system was built in the laboratory,and target recognition experiments were carried out on objects of different shapes,sizes,and materials in different backgrounds.The two methods of edge extraction and HSV color recognition were compared to extract target objects.Through comparative experiments,a suitable target extraction method was selected.Different image processing methods,such as image filtering,image edge extraction,etc.,were compared and tested,and the optimal image processing method was selected.(3)The overall layout and field test of the intelligent luggage handling system,including camera selection,light source selection,robotic arm selection,etc.,were used to obtain the luggage pose through hand-eye calibration,and the luggage intelligent handling visual recognition system based on robotic arms was used,Carry out grabbing and handling tests on baggage,and analyze the test results.This paper uses image processing algorithms to identify and extract luggage of different materials,sizes,and shapes.Due to the irregular shape of the baggage and the complicated background,it is difficult to identify and extract.Using two different extraction methods based on edge features and based on HSV color features,the extraction of different luggage is realized,which lays a certain foundation for the practical application of the airport luggage intelligent handling system. |
PDF Full Text Request