Radio interferometric imaging refers to the construction of images on visibility data observed by radio telescope arrays. Due to the data and computation intensity, existing imaging algorithms are slow for wide field ...
详细信息
ISBN:
(数字)9781665461245
ISBN:
(纸本)9781665461245
Radio interferometric imaging refers to the construction of images on visibility data observed by radio telescope arrays. Due to the data and computation intensity, existing imaging algorithms are slow for wide field measurement. To address this problem, we propose cuGridder, a GPU-based CUDA C program that produces the same result as W-gridder, the latest CPU-based imaging algorithm, but the execution is accelerated effectively by the GPU. Our main idea is to divide the imaging workflow into a sequence of steps, including convolution, 2D FFT, 1D DFT, and correction, and parallelize each step as a GPU kernel program. Furthermore, we design a lock-free algorithm for convolution, the most expensive step in the workflow, adopt a simple yet effective mask function for the convolution, and optimize the memory access pattern. As a result, cuGridder outperforms the state-of-the-art CPU-based and GPU-based libraries in running time and achieves high image quality. Our code package is available at https://***/RapidsAthKUST/cuGridder
Ships in remote sensing images are usually arranged in arbitrary direction, small in size, and densely arranged. As a result, existing object detection algorithms cannot detect ships quickly and accurately. In order t...
详细信息
ISBN:
(纸本)9781665464574
Ships in remote sensing images are usually arranged in arbitrary direction, small in size, and densely arranged. As a result, existing object detection algorithms cannot detect ships quickly and accurately. In order to solve the above problems, a lightweight object detection network for fast detection of ships is proposed. the network is composed of backbone network, four-scale fusion network and rotation branch. First, a lightweight network unit S-LeanNet is designed and used to build a low-computing and accurate backbone network. then, a four-scale feature fusion module is designed to generate a four-scale feature pyramid, which contains more features such as ship shape and texture, and at the same time is conducive to the detection of small ships. Finally, a novel rotation branch module is designed, using balance L1 loss function and R-NMS for post-processing, to realize the precise positioning and regression of the rotating bounding box in one step. Experimental results show that the detection precision of our method in the DOTA remote sensing data set is compared withthe latest SCRDet detection method, the precision is increased by 1.1%, and the operating speed is increased by 8 times, which can meet the fast detection requirements of ships.
the deep learning algorithms require high computational power and memory usage to provide better performance for users. However, the edge devices use different sizes of deep learning networks depending on the applicat...
详细信息
ISBN:
(纸本)9781665401746
the deep learning algorithms require high computational power and memory usage to provide better performance for users. However, the edge devices use different sizes of deep learning networks depending on the application and require hardware optimization due to the limited hardware resources. To minimize the hardware redesign efforts by the networks, we propose a Neural processing Unit (NPU) hardware consisting of one SRAM and 16 processing Element (PEs) that enables various parallel configurations. In this paper, we introduce the NPU hardware details and several combinations of parallel hardware structure. We also demonstrate that our hardware can handle a variety of networks by describing hardware behavior under the data configuration that is written to SRAM
image super-resolution reconstruction is a high-resolution imagethat is reconstructed from a low-resolution image. the learning-based algorithm is one of the more effective algorithms for image super-resolution recon...
详细信息
ISBN:
(数字)9783031138706
ISBN:
(纸本)9783031138706;9783031138690
image super-resolution reconstruction is a high-resolution imagethat is reconstructed from a low-resolution image. the learning-based algorithm is one of the more effective algorithms for image super-resolution reconstruction, and the core idea of the algorithm is to use the sample library to train the information of the image in order to increase the high-frequency information of the test image and achieve the purpose of image super-resolution reconstruction. In this paper, we propose a new image super-resolution algorithm based on morphological component analysis and dictionary learning. Firstly we make independent component analysis for image denoising processing by the K-SVD method. And then, MCA algorithm is utilized to efficiently decompose low-resolution images into texture part and structure part. And the K-SVD method is used to make dictionary training of low-resolution images. the method not only improves the robustness of the images, but also adopts different reconstruction algorithms for the different characteristics of the texture and structure parts, which better retains the details of the images and improves the quality of the reconstructed images.
We consider hyperspectral phase/amplitude imaging from hyperspectral complex-valued noisy observations. Block-matching and grouping of similar patches are main instruments of the proposed algorithms. the search neighb...
详细信息
Advances in non-invasive neuroimaging, such as structural magnetic resonance imaging (sMRI), have en abled the construction of structural brain networks (SBNs), allowing in vivo mapping of anatomical connec tions. thi...
详细信息
In this study, a novel training method is innovatively proposed to address the problem of poor generalisation of trained models due to imbalance in Alzheimer’s disease (AD) data. the method alternates AD image data w...
详细信息
Classification of degraded images is very important in practice because images are usually degraded by compression, noise, blurring, etc. Nevertheless, most of the research in image classification only focuses on clea...
详细信息
Due to a limited bit-depth representation of pixel values and lossy compression methods, an image may exhibit annoying banding or false-contouring artifact. Existing banding-removal approaches mainly include low pass ...
详细信息
the safety of laser coagulation in the treatment of diabetic retinopathy depends on the correct selection of laser exposure parameters. In this paper, it was proposed to use technology for numerical modeling of the te...
详细信息
ISBN:
(数字)9781510644250
ISBN:
(纸本)9781510644250
the safety of laser coagulation in the treatment of diabetic retinopathy depends on the correct selection of laser exposure parameters. In this paper, it was proposed to use technology for numerical modeling of the temperature distribution in the fundus based on its structure formed from optical coherence tomography (OCT) images. For such a formation, it is required to process each image and then interpolate the three-dimensional surfaces. Further, the formed structure is used for numerical simulation. this approach will potentially allow automating the extremely time-consuming procedure for choosing a coagulate placement plan. the paper considers algorithmsthat improve performance when solving the problem of mathematical modeling using the maximum load of CPU and GPU devices, i.e. parallel and high-performance algorithms.
暂无评论