Real-time monitoring of optimum timing for harvesting fresh tea leaves based on machine vision

The harvesting time of fresh tea leaves has a significant impact on product yield and quality.The aim of this study was to propose a method for real-time monitoring of the optimum harvesting time for picking fresh tea leaves based on machine vision.Firstly,the shapes of fresh tea leaves were distinguished from RGB images of the tea-tree canopy after graying with the improved B-G algorithm,filtering with a median filter algorithm,binary processing with the Otsu algorithm,and noise reduction and edge smoothing using open and close operations.Then the leaf characteristics,such as leaf area index,average length,and leaf identification index,were calculated.Based on these,the Bayesian discriminant principle and method were used to construct a discriminant model for fresh tea-leaf collection status.When this method was applied to a RGB tea-tree canopy image acquired at 45°shooting angle,the fresh tea-leaf recognition rate was 90.3%,and the accuracy for fresh tea-leaf harvesting status was 98%by cross validation.Hence,this method provides the basic conditions for future tea-plantation operation and management using information technology,automation,and intelligent systems.

Recognition and localization of strawberries from 3D binocular cameras for a strawberry picking robot using coupled YOLO/Mask R-CNN

To solve the problem of high labour costs in the strawberry picking process,the approach of a strawberry picking robot to identify and find strawberries is suggested in this study.First,1000 images including mature,immature,single,multiple,and occluded strawberries were collected,and a two-stage detection Mask R-CNN instance segmentation network and a one-stage detection YOLOv3 target detection network were used to train a strawberry identification model which classified strawberries into two categories:mature and immature.The accuracy ratings for YOLOv3 and Mask R-CNN were 93.4%and 94.5%,respectively.Second,the ZED stereo camera,triangulation,and a neural network were used to locate the strawberry in three dimensions.YOLOv3 identification accuracy was 3.1 mm,compared to Mask R-CNN of 3.9 mm.The strawberry detection and positioning method proposed in this study may effectively be used to supply the picking robot with a precise location of the ripe strawberry.

Cost-effective method for degradability identification of MSW using convolutional neural network for on-site composting

Automatically identifying the degradability of municipal solid waste(MSW)is one of the key prerequisites for on-site composting to prevent contaminations from undegradable wastes.In this study,a cost-effective method was proposed for the degradability identification of MSW.Firstly,the trainable images in the datasets were increased by performing four different sizes of cropping operations on the original images captured on-site.Secondly,a lite convolutional neural network(CNN)model was built with only 3.37 million parameters,and then a total of eight models were trained on these datasets with and without the image augmentation operations,respectively.Finally,a degradability identification system was built for on-site composting,where the images were cut to different sizes of small squares for prediction,and the experiments were conducted to find the best combinations of the trained models and the cutting size.The results showed that the validation accuracies of the models trained with the augmentation operations were 0.91-2.07 percentage points higher,and in the evaluation of the degradability identification system the best result was achieved by the combination of W8A dataset and cutting size of 1/14 reached an accuracy of 91.58%,which indicated the capability of this cost-effective method to identify the degradability of MSW.

Method for C/N ratio estimation using Mask R-CNN and a depth camera for organic fraction of municipal solid wastes

Fast assessment of the initial carbon to nitrogen ratio(C/N)of organic fraction of municipal solid waste(OFMSW)is an important prerequisite for automatic composting control to improve efficiency and stability of the bioconversion process.In this study,a novel approach was proposed to estimate the C/N of OFMSW,where an instance segmentation model was applied to predict the masks for the waste images.Then,by combining the instance segmentation model with the depth-camera-based volume calculation algorithm,the volumes occupied by each type of waste were obtained,therefore the C/N could be estimated based on the properties of each type of waste.First,an instance segmentation dataset including three common classes of OFMSW was built to train mask region-based convolutional neural networks(Mask R-CNN)model.Second,a volume measurement algorithm was proposed,where the measurement result of the object was derived by accumulating the volumes of small rectangular cuboids whose bottom area was calculated with the projection property.Then the calculated volume was corrected with linear regression models.The results showed that the trained instance segmentation model performed well with average precision scores AP_(50)=82.9,AP_(75)=72.5,and mask intersection over unit(Mask IoU)=45.1.A high correlation was found between the estimated C/N and the ground truth with a coefficient of determination R2=0.97 and root mean square error RMSE=0.10.The relative average error was 0.42%and the maximum error was only 1.71%,which indicated this approach has potential for practical applications.