Cereal grain 3D point cloud analysis method for shape extraction and filled/unfilled grain identification based on structured light imaging

Abstract

Cereals are the main food for mankind. The grain shape extraction and filled/unfilled grain recognition are meaningful for crop breeding and genetic analysis. The conventional measuring method is mainly manual, which is inefficient, labor-intensive and subjective. Therefore, a novel method was proposed to extract the phenotypic traits of cereal grains based on point clouds. First, a structured light scanner was used to obtain the grains point cloud data. Then, the single grain segmentation was accomplished by image preprocessing, plane fitting, region growth clustering. The length, width, thickness, surface area and volume was calculated by the specified analysis algorithms for grain point cloud. To demonstrate this method, experimental materials included rice, wheat and corn were tested. Compared with manual measurement results, the average measurement error of grain length, width and thickness was 2.07%, 0.97%, 1.13%, and the average measurement efficiency was about 9.6 s per grain. In addition, the grain identification model was conducted with 25 grain phenotypic traits, using 6 machine learning methods. The results showed that the best accuracy for filled/unfilled grain classification was 90.184%.The best accuracy for indica and japonica identification was 99.950%, while for different varieties identification was only 47.252%. Therefore, this method was proved to be an efficient and effective way for crop research.

Recent developments on the contribution of glutenin and puroindoline proteins to improve wheat grain quality

“…This method has been successfully deployed in analyzing and classifying partial waxy wheat, near-isogenic lines of soft and hard wheat (D. Liu et al, 2019). Recently, an intelligent analysis method based on structured light imaging was developed to extract 3D wheat grain phenotypes traits that predict grain weight whose results were found to be on par with the manual measurements (Qin et al, 2022). Further pioneer studies need to be conducted to address this gap for the benefit of wheat breeders and millers.…”

A Novel Method for Filled/Unfilled Grain Classification Based on Structured Light Imaging and Improved PointNet++

“…3D Structured light imaging could greatly reduce the impact of environmental noise when obtaining high-density rice grain point clouds with texture information through feature stitching algorithm and texture mapping. Qin et al have tried to classify the filled/unfilled rice grains based on structured light imaging and traditional machine learning methods, with a classification accuracy of 90.18% [ 16 ]. Although this method proved the feasibility of a three-dimensional point cloud to achieve rice grains classification, the accuracy needs further improvement.…”

A three-dimensional vision measurement method based on double-line combined structured light

“…Consequently, the data acquired for an object's surface details is often insufficient.On the other hand, the surface-structured light measurement technique employs a projector to cast raster images onto the object's surface. By analyzing the modulated raster image influenced by the object's surface, the 3D contour of the surface can be directly determined [12][13][14][15][16] . This approach obviates the need for scanning, a stark contrast to the point-structured light method.…”