Research On Key Technologies Of Automatic Picking System For Industrial Planting Of Agaricus Bisporus

The factory planting of crops is one of the characteristics of the transformation from traditional agriculture to new agriculture.After entering the factory cultivation,the yield of Agaricus bisporus has been greatly increased,but the picking link is still mainly manual picking,with high cost and low efficiency.Therefore,it is of great significance to realize automatic picking of Agaricus bisporus.Taking the industrial stereoscopic cultivation of Agaricus bisporus as the research object,this paper studies the key technologies of the automatic picking system of Agaricus bisporus,puts forward an efficient recognition algorithm of Agaricus bisporus,and develops a prototype of the automatic picking system of Agaricus bisporus.The main research contents are as follows:(1)In order to solve the problems that the picking action of narrow distance between mushroom beds is difficult to perform,undifferentiated picking is easy to damage mushrooms,and picking machines are difficult to change layers,the mechanical structure of automatic picking system of double spore mushrooms is designed.the system includes two parts:mobile picking platform and auxiliary layer changing module,on the basis of which the visual module is designed.(2)In order to solve the problem that it is difficult to identify large area adhesion of Agaricus bisporus,a segmentation and recognition algorithm of adhesive mushroom group is proposed.Firstly,the two-dimensional feature of Agaricus bisporus image is analyzed,and the complex background is filtered by Otsu threshold segmentation algorithm and multiple morphological open operations,then the pixel preprocessing and watershed marker iterative preparation method are proposed for the large area adhesion region of Agaricus bisporus.Finally,the individual segmentation and recognition of Agaricus bisporus are realized by the watershed algorithm based on markers.The algorithm is used to process the image samples of Agaricus bisporus,and the results show that the positive detection rate of the algorithm is 95.7%,and the average processing time of a single image is 705.7 ms.Taking the manual marking results as the standard,the fitting results are compared with the traditional Hoff circle algorithm,and the results show that this algorithm is more effective than the Hoff circle algorithm in determining the center coordinates and diameter measurement of mushroom cap.(3)In order to simplify the control mode of the automatic picking system of Agaricus bisporus,the motion control system of the whole machine was designed.In terms of hardware,the motion controller of the mobile picking platform is determined according to the functional needs of the system.By analyzing the motion characteristics in all directions,the selection of each motion executive element is carried out,and the hardware assembly of the picking platform is completed.In the aspect of software,according to the work flow of the system,the main control program,the mobile picking platform control program and the auxiliary layer change module control program are designed,and the motion control interface of the picking platform is designed by using the MFC interface creation library.(4)On the basis of the above research work,a prototype of automatic picking system of Agaricus bisporus was built,and the whole machine was tested in the laboratory simulation environment.The test results show that the picking success rate of the mobile picking platform is 93.32%,the average picking time of a single double spore mushroom is 7.76 s,the preset operation flow can be completed successfully,and the average time of the auxiliary layer changing module is 99.6 s,which achieves the design target of the main technical parameters and provides the technical basis and solution for the subsequent research and development of the automatic picking system of double spore mushroom.