Automatic building extraction based on high-resolution aerial images has important applications in urban planning and environmental management. In recent years advances and performance improvements have been achieved in building extraction through the use of deep learning methods. However, the design of existing models focuses attention to improve accuracy through an overflowing number of parameters and complex structure design, resulting in large computational costs during the learning phase and low inference speed. To address these issues, we propose a new, efficient end-to-end model, called ARC-Net. The model includes residual blocks with asymmetric convolution (RBAC) to reduce the computational cost and to shrink the model size. In addition, dilated convolutions and multi-scale pyramid pooling modules are utilized to enlarge the receptive field and to enhance accuracy. We verify the performance and efficiency of the proposed ARC-Net on the INRIA Aerial Image Labeling dataset and WHU building dataset. Compared to available deep learning models, the proposed ARC-Net demonstrates better segmentation performance with less computational costs. This indicates that the proposed ARC-Net is both effective and efficient in automatic building extraction from high-resolution aerial images.
Algorithm are implemented.A novel parameter tuning workflow of stochastic optimization algorithms for waveform-based location is proposed.Three algorithms are tested and analyzed using both synthetic and field data.The characteristics of two imaging operators are also revealed.
Authorship statementL. Li contributed to method development and testing, and drafted the manuscript. J. Tan contributed to manuscript review and funding acquisition. Y. Xie and Y. Tan contributed to algorithm implementation of the study. J. Walda and Z. Zhao revised the manuscript carefully. D. Gajewski advised the study design and revised the manuscript.
Fracture characterization is essential for estimating the stimulated reservoir volume and guiding subsequent hydraulic fracturing stimulations in shale reservoirs. Laboratory fracturing experiments can help provide theoretical and technical guidance for field operations. In this study, hydraulic fracturing experiments on the shale samples from Niutitang Formation in Hunan Province (China) under a uniaxial loading condition are conducted. The multifractal method is used to analyze the acoustic emission (AE) signals and characterize fracture initiation and propagation. The hydraulic fracturing process can be divided into three stages based on the characteristics of AE signals: the initial stage, the quite stage, and the fracturing stage. The multifractal analysis results showed that: (1) the value of the spectrum width, Δα, continues to increase as the energy accumulates until the fracturing stage starts; and (2) the difference in the multifractal spectrum values, Δf, reflects the relationship between small and large signal frequencies and can quantify the fracture scale, i.e., the lower the Δf, the larger the fracture scale and vice versa. The results were further verified using a time-frequency analysis of the AE signals and micro-CT scanning of the samples. This study demonstrates that the multifractal method is feasible for quantitatively characterizing hydraulic fractures and can aid field hydraulic fracturing operations.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.