Study On The Extraction Method Of Morphological Parameters Of Masson Pine Seedling Based On Multi-view Stereo Vision

The construction of ecological civilization and the construction of modern forestry need the quantity and quality of seedlings.The quality of seedling is embodied in all aspects which are excellent genetic quality and excellent quality of afforestation.Seedling quality evaluation is one of the core problems of seedling quality control.Therefore,it is a key technical problem to accurately evaluate the quality of seedling and control the quality of seedling.The evaluation of seedling quality is mainly based on the seedling height,ground diameter and root status and other morphological index,and measurement of morphological index commonly uses ruler and vernier caliper by artificial direct measurement,consuming a lot of manpower and material resources,and time-consuming.As a result,it has a very important significance for the construction of modern forestry and construction of ecological civilization to apply advanced technology in the realization of fast and accurately evaluation of morphological characteristics of Masson Pine seedlings.A morphological characteristics extraction system of Masson Pine Seedlings is designed in this dissertation.The system with multi view stereo vision,high precision and non contact can reconstruct 3D model of Masson Pine seedlings by the multi view image sequence,and quickly extract the morphological characteristics of seedlings.The main working process includes:hardware experimental platform consists of 2 color CMOS array cameras,Gigabit Ethernet switches,computers,background plate and other auxiliary equipment and software system based on OpenCV library.First of all,the array cameras are used to shoot image of calibration plate and the“zhangzhengyou calibration method”for camera calibration is adopted to get the calibration parameters of the camera.And then cameras are used to shoot image of the Masson Pine seedlings,the image sequence under different perspectives of Pine seedlings was obtained by rotating the seedlings through the rotation of the motor.Then the software system performs image preprocessing,image correction and stereo matching and other operations on the collected image sequence of Masson Pine seedling,using SAD,SSD and NCC stereo matching algorithm to test the corrected image sequence in the process of matching,and the optimal matching algorithm is selected.And then software system gets seedlings’ space point cloud information,using spatial Poisson surface reconstruction algorithm to carry out the surface reconstruction of seedlings’ space point cloud to obtain the 3D model of Masson Pine seedlings.After reconstructing 3D models of Masson Pine seedlings,extracting the seedling height,ground diameter,trunk and root volume and other morphological parameters from the model,the trunk and root volume is respectively fitted with cylindrical geometry,round table geometry,cylindrical and round table geometry and "voxel simulation",which embodies the unique advantages of "voxel simulation" when calculating the volume.Finally,the data extracted fromthe system software is compared with the traditional manual measurement data.It is proved that the 3D reconstruction method of Masson Pine seedlings has high precision and fast speed,and the reconstruction result is very close to the true morphology of the root and stem and leaf of seedlings.Software can be used to replace the traditional manual measurement method,liberating people from the heavy and repeated measurement work,providing a more accurate morphological indicators for the evaluation of the quality of seeding.