Estimating and evaluating the rice cluster distribution uniformity with UAV-based images

The uniformity of the rice cluster distribution in the field affects population quality and the precise management of pesticides and fertilizers. However, there is no appropriate technical system for estimating and evaluating the uniformity at present. For that reason, a method based on unmanned aerial vehicle (UAV images) is proposed to estimate and evaluate the uniformity in this present study. This method includes rice cluster recognition and location determination based on the RGB color characteristics of the seedlings of aerial images, region segmentation considering the rice clusters based on Voronoi Diagram, and uniformity index definition for evaluating the rice cluster distribution based on the variation coefficient. The results indicate the rice cluster recognition attains a high precision, with the precision, accuracy, recall, and F1-score of rice cluster recognition reaching > 95%, 97%, 97%, 95%, and 96%, respectively. The rice cluster location error is small and obeys the gamma (3.00, 0.54) distribution (mean error, 1.62 cm). The uniformity index is reasonable for evaluating the rice cluster distribution verified via simulation. As a whole process, the estimating method is sufficiently high accuracy with relative error less than 0.01% over the manual labeling method. Therefore, this method based on UAV images is feasible, convenient, technologically advanced, inexpensive, and highly precision for the estimation and evaluation of the rice cluster distribution uniformity. However, the evaluation application indicates that there is much room for improvement in terms of the uniformity of mechanized paddy field transplanting in South China.

LCBRG: A lane-level road cluster mining algorithm with bidirectional region growing

Lane-level road cluster is a most representative phenomenon in road networks and is vital to spatial data mining, cartographic generalization, and data integration. In this article, a lane-level road cluster recognition method was proposed. First, the conception of lane-level road cluster and our motivation were addressed and the spatial characteristics were given. Second, a region growing cluster algorithm was defined to recognize lane-level road clusters, where constraints including distance and orientation were used. A novel moving distance (MD) metric was proposed to measure the distance of two lines, which can effectively handle the non-uniformly distributed vertexes, heterogeneous length, inharmonious spatial alignment, and complex shape. Experiments demonstrated that the proposed method can effectively recognize lane-level road clusters with the agreement to human spatial cognition.

Mean Shift Cluster Recognition Method Implementation in the Nested Sampling Algorithm

Nested sampling is an efficient algorithm for the calculation of the Bayesian evidence and posterior parameter probability distributions. It is based on the step-by-step exploration of the parameter space by Monte Carlo sampling with a series of values sets called live points that evolve towards the region of interest, i.e., where the likelihood function is maximal. In presence of several local likelihood maxima, the algorithm converges with difficulty. Some systematic errors can also be introduced by unexplored parameter volume regions. In order to avoid this, different methods are proposed in the literature for an efficient search of new live points, even in presence of local maxima. Here we present a new solution based on the mean shift cluster recognition method implemented in a random walk search algorithm. The clustering recognition is integrated within the Bayesian analysis program NestedFit. It is tested with the analysis of some difficult cases. Compared to the analysis results without cluster recognition, the computation time is considerably reduced. At the same time, the entire parameter space is efficiently explored, which translates into a smaller uncertainty of the extracted value of the Bayesian evidence.

Percolation and universality

Percolation deals with global properties of random configurations of local objects. While simple to implement in models, understanding percolation requires skill in pattern recognition and analysis. A cluster recognition algorithm is developed to obtain properties of percolation models. The fractal nature of a percolating system is discussed, along with general features of fractals. Scaling laws and critical exponents, which are central features of modern approaches to complex systems, are also introduced and illustrated with percolating systems. The important concept of a correlation function is also used to characterize these systems. Finally, the insensitivity of large classes of model systems with respect to short range dynamics, known as universality, is discussed in the context of percolation. This is illustrated with the modern concepts of coarse graining and the renormalization group.