Study On Detection Method Of Feed Density For Rice Combine By Genetic Algorithm

In order to realize control of suitable feed quantity and decrease breakage and loserate,feed density should be obtained firstly. According to the technology of imageprocessing,total pixels of target area were extracted as the feature of feed density of combine.Functional relationships between the feature values of feed density and actual feed densitywere established.Studying of the application of image segmentation in domestic and abroad,shortcomings in segmentation quality and segmentation speed were found by comparing oftraditional image segmentation method. Iterative threshold method got the larger threshold andvague target profile.It is difficult to cut up the target area from the image of rice. Otsu methodgot right threshold,clear target profile.This method redeced the influence of backgroundimage.But real-time of traditional image segmentation could not meet the demands ofcombine.In the premise of ensuring the quality of segmentation, genetic algorithm can cut downtime of obtaining the threshold. Researching of theoretical basis and implenentation steps, feeddensity detection method of rice combine by genetic algorithm was proposed.In line withadaptability,robustness and parallelism of genetic algorithm,this algorithm is very suitable foroptimization problem in large-scale search space. A new effective method of rice imagesegmentation was proposed to improve the real-time and reliability of feed density detection.Images of differen species,mature stages and density regions obtained the global optimumthreshold quickly and accurately using genetic algorithm.Divided the gray image into binaryimage. Calculated total pixels of target area as the feature of feed density of combine.UsingDPS data processing software, correlation between the feature values of feed density andactual feed density was analyzed.Fitting model of feed density was established.Results showed that the best segmenting threshold from genetic algorithm was the sameas the threshold from Ostu. But numbers of variance calculation of genetic algorithm wereabout140T.The speed was twice as fast as the numbers of variance calculation which were256T. Genetic algorithm can obtain feature values of feed density quickly. Results proved thesuperiority of genetic algorithms in terms of image segmentation.Correlation coefficient between the feature values of feed density and actual feed densitywas higher than0.91.Both of them showed the positive correlation.The more feature values offeed density,the more actual feed density.So the feature values of feed density can reflectactual feed density level.Detection method of feed density for Rice Combine can provide references to control of feed quantity.