ABSTRACT
Longan yield estimation is an important practice before longan harvests. Statistical longan yield data can provide an important reference for market pricing and improving harvest efficiency and can directly determine the economic benefits of longan orchards. At present, the statistical work concerning longan yields requires high labor costs. Aiming at the task of longan yield estimation, combined with deep learning and regression analysis technology, this study proposed a method to calculate longan yield in complex natural environment. First, a UAV was used to collect video images of a longan canopy at the mature stage. Second, the CF-YD model and SF-YD model were constructed to identify Cluster_Fruits and Single_Fruits, respectively, realizing the task of automatically identifying the number of targets directly from images. Finally, according to the sample data collected from real orchards, a regression analysis was carried out on the target quantity detected by the model and the real target quantity, and estimation models were constructed for determining the Cluster_Fruits on a single longan tree and the Single_Fruits on a single Cluster_Fruit. Then, an error analysis was conducted on the data obtained from the manual counting process and the estimation model, and the average error rate regarding the number of Cluster_Fruits was 2.66%, while the average error rate regarding the number of Single_Fruits was 2.99%. The results show that the method proposed in this paper is effective at estimating longan yields and can provide guidance for improving the efficiency of longan fruit harvests.
ABSTRACT
Litchi flowering management is an important link in litchi orchard management. Statistical litchi flowering rate data can provide an important reference for regulating the number of litchi flowers and directly determining the quality and yield of litchi fruit. At present, the statistical work regarding litchi flowering rates requires considerable labour costs. Therefore, this study aims at the statistical litchi flowering rate task, and a combination of unmanned aerial vehicle (UAV) images and computer vision technology is proposed to count the numbers of litchi flower clusters and flushes in a complex natural environment to improve the efficiency of litchi flowering rate estimation. First, RGB images of litchi canopies at the flowering stage are collected by a UAV. After performing image preprocessing, a dataset is established, and two types of objects in the images, namely, flower clusters and flushes, are manually labelled. Second, by comparing the pretraining and testing results obtained when setting different training parameters for the YOLOv4 model, the optimal parameter combination is determined. The YOLOv4 model trained with the optimal combination of parameters tests best on the test set, at which time the mean average precision (mAP) is 87.87%. The detection time required for a single image is 0.043 s. Finally, aiming at the two kinds of targets (flower clusters and flushes) on 8 litchi trees in a real orchard, a model for estimating the numbers of flower clusters and flushes on a single litchi tree is constructed by matching the identified number of targets with the actual number of targets via equation fitting. Then, the data obtained from the manual counting process and the estimation model for the other five litchi trees in the real orchard are statistically analysed. The average error rate for the number of flower clusters is 4.20%, the average error rate for the number of flushes is 2.85%, and the average error for the flowering rate is 1.135%. The experimental results show that the proposed method is effective for estimating the litchi flowering rate and can provide guidance regarding the management of the flowering periods of litchi orchards.
ABSTRACT
OBJECTIVE: The purpose of this study was to analyze the distribution, temporal and spatial clustering characteristics and changes of severe hand, foot, and mouth disease (HFMD) in order to provide evidence-based decision making strategy for control and prevention of severe HFMD cases. METHODS: Severe HFMD cares were extracted from the National Diseases Reporting System of Chinese Center for Disease Control and Prevention (CDC) between 2008 and 2013. Definition and clinical diagnostic criteria of severe HFMD cases were set up by China CDC in the Hand, Foot, and Mouth Disease Control and Prevention Guideline, version 2010. Spatial scan unit was under the district/county of 2 900 in mainland China with temporal scan unit as month and time span as from May 2008 to August 2013. Kulldorff scan statistics was applied and analyses were conducted by SaTScan(TM) 9.1. Mapping and visualizing the results were carried out with ArcGIS 10.0. RESULTS: Data related to the monitoring program on severe HFMD from 2008 to 2013 demonstrated that above 96% of the severe HFMD cases occurred under 5 years old, mostly males, with the ratio of males to females as 1.73-1.80 and over 84% of the children were 'scattered'. Results from SaTScan illustrated that the temporal and spatial clustering existed among severe HFMD cases. The temporal dimension of severe HFMD was from May to July each year. Spatial dimension was located in south-east coastal area and middle-east area. With respect to the changes of temporal and spatial clustering phenomena, Class 1 clustering area was located in south-east coastal region in 2008 and in middle-east region in 2009 and was shifting to the west from middle-east region in 2010. It moved to the north-east from middle-east region in 2011 and to the north-west and south-west from middle-east region in 2012. Class 1 clustering area covered districts/countries from 18 provinces in 2012. The same pattern of Class 1 clustering area was observed as in the previous year-2013, but with less districts/countries from the 13 provinces. CONCLUSION: Temporal and spatial clustering areas of severe HFMD were presented in this report, and the yearly changing pattern of the clustering areas was noted. Findings from this study provided evidence-based data to the decision-making authorities so as to prevent deaths from severe HFMD cases under reasonable prevention and control strategies.