Search

The automatic detection of wheat ears in the field has important scientific research value in yield estimation, gene character expression and seed screening. The manual counting method of wheat ears commonly used by breeding experts has some problems, such as low efficiency and high influence of subjective factors. In order to accurately detect the number of wheat ears in the field, based on mobilenet series network model, deep separable convolution module and alpha channel technology, the yolov4 model is reconstructed and successfully applied to the task of wheat ear yield estimation in the field. The model can adapt to the accurate recognition and counting of wheat ear images in different light, viewing angle and growth period, At the same time, the model volume with different alpha parameters is more suitable for mobile terminal deployment. The results show that the parameters of the improved yolov4 model are five times smaller than the original model, the average detection accuracy is 76.45%, and the detection speed FPS is two times higher than the original model, which provides accurate technical support for rapid yield estimation of wheat in the field.

The acquisition of traditional wheat ear phenotypic parameters is labour intensive and subjective, and some trait parameters are difficult to measure, which greatly limits the progress of wheat ear research. To obtain the phenotypic parameters of wheat ears in batches at a low cost, this paper proposed a convenient and accurate method for extracting phenotypic parameters of wheat ears. First, three improvement directions were proposed based on the Mask Region-Convolutional Neural Network (Mask-RCNN) model. 1) To extract the multiscale features of wheat ears, a hierarchical residual link was constructed in a single residual block of the backbone network ResNet101 to obtain information on different sizes of receptive fields. 2) The feature pyramid network (FPN) was improved to increase the recognition accuracy of wheat ear edges through multiple two-way information flow sampling. 3) The mask evaluation mechanism was improved, specific network blocks were used to learn and predict the quality of the mask, and the detection of wheat ears and grains was performed by precise segmentation; an automatic extraction algorithm was designed for wheat ear phenotypic parameters based on the segmentation results to extract 22 phenotypic parameters. The experiments showed that the improved Mask-RCNN was superior to the existing model in the segmentation accuracy of wheat ears and grains; the parameters of wheat ear length, width, and number of grains extracted by the automatic extraction algorithm were close to the manual measurement values. This research meets the demand for automatic extraction of wheat ear phenotype data for large-scale quality testing and commercial breeding and has strong practicability.

There is an increasing demand to replace Pb(Zr,Ti)O 3 -based piezoelectric materials with lead-free alternatives, because of the toxicity of lead oxide which is largely used during the production process. (K 0.5 Na 0.5 )NbO 3 is considered as one of the most promising candidates for lead free piezoelectric ceramics due to its high Curie temperature and good electrical properties. However, it is well known that dense and well-sintered K 0.5 Na 0.5 NbO 3 ceramics are very difficult to obtain by the ordinary sintering process owing to the high volatility of alkali elements at high temperatures. The major strategy to overcome this problem is simply adding excess alkali metals in the starting composition. In this work, the K excess lead free ceramics (K 0.5+x Na 0.5 )NbO 3 (0⩽x⩽0.3, KNN) were prepared by a novel method mixing perovskite structure of NaNbO 3 and KNbO 3 powders. Effects of K excess and sintering temperatures on phase structure, micromorphology and electrical properties of KNN ceramics were investigated. Result showed that the KNN ceramic with x=0.2 showed optimized ferroelectric property and the single phase perovskite structure.

In this paper, we introduce the concept of Edge Linking Coefficient(ELC), which is a value positively proportional to the number of the common neighbors shared by a pair of connected nodes and used as the measurement of the connection strength between them, and present a new divisive clustering algorithm for discovering communities hidden in large-scale complex networks based on it. Combining with the weak and the strong criteria of the communities, the ELCA method can effectively identify community structure in networks, which is shown in the experimental results on the synthetic and four real-world network data sets. In addition, the clustering algorithm is much faster than the GN algorithm and its variants, and suitable to the large-scale complex network clustering.