Agricultural pests and diseases significantly affect crop yield and quality, making their identification crucial. imageprocessing technology holds the key to recognizing these threats. To delve into the progression, ...
详细信息
The promises of advanced quantum computing technology have driven research in the simulation of quantum computers on classical hardware, where the feasibility of quantum algorithms for real-world problems can be inves...
详细信息
The promises of advanced quantum computing technology have driven research in the simulation of quantum computers on classical hardware, where the feasibility of quantum algorithms for real-world problems can be investigated. In domains such as High Energy Physics (HEP) and remotesensing Hyperspectral imagery, classical computing systems are held back by enormous readouts of high-resolution data. Due to the multi-dimensionality of the readout data, processing and performing patternrecognition operations for this enormous data are both computationally intensive and time-consuming. In this article, we propose a methodology that utilizes Quantum Haar Transform (QHT) and a modified Grover's search algorithm for time-efficient dimension reduction and dynamic patternrecognition in data sets that are characterized by high spatial resolution and high dimensionality. QHT is performed on the data to reduce its dimensionality at preserved spatial locality, while the modified Grover's search algorithm is used to search for dynamically changing multiple patterns in the reduced data set. By performing search operations on the reduced data set, processing overheads are minimized. Moreover, quantum techniques produce results in less time than classical dimension reduction and search methods. The feasibility of the proposed methodology is verified by emulating the quantum algorithms on classical hardware based on field programmable gate arrays (FPGAs). We present designs of the quantum circuits for multi-dimensional QHT and multi-pattern Grover's search. We also present two emulation techniques and the corresponding hardware architectures for this methodology. A high performance reconfigurable computer (HPRC) was used for the experimental evaluation, and high-resolution images were used as the input data set. Analysis of the methods and implications of the experimental results are discussed.
The fusion of multi-source data with different spatial and spectral resolutions is a crucial task in many remotesensing and computer vision applications. Model-based fusion methods are more interpretable and. flexibl...
详细信息
remotesensing technology holds significant advantages in the analysis of aquatic ecological environments, including rapid processing speed, abundant information, extensive spatial coverage, and high reliability. Tota...
详细信息
LiDAR technology is widely used for point cloud data acquisition in geographic mapping, ecological surveying, etc., which facilitates the research. The PointNet model is a pioneering representative of deep learning te...
详细信息
In this paper, a novel visualization method for GPR data interpretation and target analysis is proposed for underground target detection and recognition. After preprocessing, the original B-scan image has been transfo...
详细信息
ISBN:
(数字)9781665427920
ISBN:
(纸本)9781665427920
In this paper, a novel visualization method for GPR data interpretation and target analysis is proposed for underground target detection and recognition. After preprocessing, the original B-scan image has been transformed into two binary images containing potential targets. Then in the target extraction part, a novel row connection clustering algorithm is applied to separate all possible hyperbolic regions. Finally, a neural network is used to analyze the extracted slices and to estimate the parameters including the material and size of the targets. To illustrate the performance of the proposed method, this paper uses synthetic data generated from gprMax, which demonstrates the exciting accuracy of target detection and recognition.
Texture characterization is very useful for automatic analysis of object surface images for a plethora of applications in medicine, agriculture, industry or remotesensing. Various texture characterization tech-niques...
详细信息
Texture characterization is very useful for automatic analysis of object surface images for a plethora of applications in medicine, agriculture, industry or remotesensing. Various texture characterization tech-niques exist, from the classical Haralick descriptors, Gabor filters, local binary patterns to automatically -extracted features using machine learning models. We propose a new hand-crafted texture characteri-zation technique, based on light polarization property, by deploying a circular polarization filter (rotated from 0 degrees to 360 degrees in steps of 10 degrees) in the image acquisition process. The hypothesis is that different materials and surfaces will exhibit different polarization signatures defined as pixel values variation as a function of polarization angle. Such polarization signature is able to locally characterize texture as a consequence of light reflections captured in every pixel due to the texture intrinsic variations. We show the usefulness of our approach for surface/material classification for the purpose of color image segmentation of natural outdoor scenes.(c) 2022 Elsevier B.V. All rights reserved.
The deep neural network (DNN) has made significant progress in the single remotesensingimage super-resolution (SRSISR). The success of DNN-based SRSISR methods mainly stems from the use of the global information and...
详细信息
ISBN:
(纸本)9783031189159;9783031189166
The deep neural network (DNN) has made significant progress in the single remotesensingimage super-resolution (SRSISR). The success of DNN-based SRSISR methods mainly stems from the use of the global information and the fusion of shallow features and the deep features, which fits the non-local self-similarity characteristic of the remotesensingimage very well. However, for the fusion of different depth (level) features, most DNN-based SRSISR methods always use the simple skip-connection, e.g. the element-wise addition or concatenation, to transform the feature coming from preceding layers to later layers directly. To achieve sufficient complementation between different levels and capture more informative features, in this paper, we propose a stage-mutual-affine network (SMAN) for high-quality SRSISR. First, for the use of the global information, we construct a convolution-transformer dual-branch module (CTDM), in which we propose an adaptive multi-head attention (AMHA) strategy to dynamically rescale the head-wise features of the transformer for more effective global information extraction. Then, the global information is fused with the local structure information extracted by the convolution branch for more accurate recurrence information reconstruction. Second, a novel hierarchical feature aggregation module (HFAM) is proposed to effectively fuse shallow features and deep features by using a mutual affine convolution operation. The superiority of the proposed HFAM is that it achieves sufficient complementation and enhances the representational capacity of the network by extracting the global information and exploiting the interdependencies between different levels of features, effectively. Extensive experiments demonstrate the superior performance of our SMAN over the state-of-the-art methods in terms of both qualitative evaluation and quantitative metrics.
暂无评论