| Maize production occupies an very important strategic position in food production and food security in China.Directional seeding can improve light energy utilization and ventilated effect of field,which is of great significance for close planting and increase of yield per unit area.In order to realize directional seeding,on the one hand,it is necessary to select corn seed before planting,including both corn ears selection and corn seed selection,which is used to remove the corn seed of low germination rate and the deformed seed of which morphological characteristics do not conform to the requirements of directional seeding.On the other hand,it is also necessary to ensure that corn seed is arranged directionally in seeding furrows during the process of seeding.Therefore,based on machine vision technology,in this paper,corn ear selection technology,corn seed selection technology and directional positioning technology were studied mainly,and machine vision-based selection and directional positioning machine of corn seed for directional seeding was developed.(1)The implementation scheme of corn ears image selection device was designed.For directional seeding,the selection algorithm was developed for yellow corn ears on the dynamic assembly line.According to the appearance characteristic parameter,the length ratio between the long axis and short axis of corn ears,the small corn ears were judged;by using the formula,G minus B,the area with yellow characteristics was strengthened and was even extracted after histogram threshold segmentation,and the plumpness of the corn ear was detected by calculating the ratio of the extracted area and the whole area of the corn ear,and then the corn ears which were mildewed or seriously lacked seeds were detected according to their plumpness;based on the characteristics of corn ear image's X cumulative distribution diagram and its Y cumulative distribution diagram,the middle ear row area and every seed area in it were extracted,and then the length-width ratio of the end-face of every seed in the middle ear row,that is,the flatness of every seed in the middle ear row,was calculated by tracking its contour,finally,the corn ears in which the end-faces of corn seeds were mostly round were detected and eliminated.In the experiment,50 random samples of corn ears were detected,and the results showed that the detection accuracy of morphological characteristics is 100%,the detection accuracy of corn ears plumpness(on the other hand,the degree of seed lack or mildew)was 96%,the detection accuracy of rectangular degree of seeds' end-face in corn ears is 98%,and the overall detection accuracy was 94%.(2)The overall structure of the machine,machine vision-based selection and directional positioning machine of corn seed for directional seeding,was designed.Combined with the geometrical characteristics of corrn seed samples,the structural parameters of key components in this device were designed and calculated in detail.For the process of feeding seed from duckbilled seeding mouths in seed-metering unit,the dynamic analysis was carried on,and then the installation angle of the roller,that is,the component which was used to open the duckbilled seeding mouths orderly to feed seed in sequence,was determined.In addition,the actual location distribution of corn seed fed into conveyer belt through guide-localization tube was determined by experiment,the method of blowing unqualified corn seed of blowing device was designed,and through speed and displacement analysis of seed positioning process,the conditions were obtained that seed can be positioned by locating notch effectively and continuously.(3)Based on machine vision technology,the dynamic detection algorithm of corn seed for directional seeding was developed.Through the analysis of RGB color feature of seed images,the extracting solution of whole area,yellow area,normal white area and color-changing area of seed in the images was obtained successively.Then,according to con seed morphological characteristics(such as tip point,long axis and short axis)and totally 20 detection indicators(such as perimeter,area,length of long axis),the centroid position and germ orientation of seed were judged,and the eligibility judgment methods of the following types of seed were analyzed respectively and executed successfully:seed with black embryo exposed in the tip,small seed,round seed,worm-eaten and damaged seed,moldy seed and other seed which did conform to directional seeding.Furthermore,two points on contour line near two joints of adhesive seed were obtained,and it can be found that the ratio of the shorter distance of them along the contour line to the linear distance of them was larger than the corresponding value of any two points on the contour line of a single seed,which according to the adhesive seed can be detected.In the experiment,the results showed that the eligibility detection accuracy of corn seed for one side was 97%,the judgment accuracy of adhesive seed was 99%,the detection accuracy of the centroid position,tip direction and germ surface orientation of qualified seed were 100%,100%,98%,respectively.(4)The power-driven system for everyrpart of the machine was chosen and the pneumatic drive circuit system among them was designed.And after that,the overall design of control system of the machine was carried on,including two parts,upper computer image acquisition and processing system and lower computer power control system.In the upper computer image acquisition and processing system,the system software interface was designed,and the main menu functions included image acquisition,off-line seed detection,online seed selection and directional positioning control,and so on.In the lower computer power control system,the hardware and software of the control system were developed based on PLC.In addition,the main working parameters of different working parts in the machine were analyzed and determined.(5)The test was carried on to test the performance of machine prototype,and the test results showed that the overall structural design of the prototype was reasonable,all parts from the machine operated orderly and in phase,the working parameters were set to be reasonable,and the design requirements and the expected goal were reached. |
PDF Full Text Request