- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Combining Deep and Shallow Neural Networks with Ad Hoc Detectors for the Classification of Complex Multi-Modal Urban Scenes
摘要： This article describes the work?ow of the classi?cation algorithm which ranked at 2nd place in the 2018 GRSS Data Fusion Contest. The objective of the contest was to provide a classi?cation map with 20 classes on a complex urban scenario. The available multi-modal data were acquired from hyperspectral, LiDAR and very high-resolution RGB sensors ?own on the same platform over the city of Houston, TX, USA. The classi?cation was obtained by merging deep convolutional and shallow fully-connected neural networks on a simpli?ed set of classes, complemented by a series of speci?c detectors and adhoc classi?ers.
关键词： hyperspectral,very high-resolution,data fusion,classi?cation,LiDAR
更新于2025-09-04 15:30:14
-
Building Extraction in Very High Resolution Imagery by Dense-Attention Networks
摘要： Building extraction from very high resolution (VHR) imagery plays an important role in urban planning, disaster management, navigation, updating geographic databases, and several other geospatial applications. Compared with the traditional building extraction approaches, deep learning networks have recently shown outstanding performance in this task by using both high-level and low-level feature maps. However, it is difficult to utilize different level features rationally with the present deep learning networks. To tackle this problem, a novel network based on DenseNets and the attention mechanism was proposed, called the dense-attention network (DAN). The DAN contains an encoder part and a decoder part which are separately composed of lightweight DenseNets and a spatial attention fusion module. The proposed encoder–decoder architecture can strengthen feature propagation and effectively bring higher-level feature information to suppress the low-level feature and noises. Experimental results based on public international society for photogrammetry and remote sensing (ISPRS) datasets with only red–green–blue (RGB) images demonstrated that the proposed DAN achieved a higher score (96.16% overall accuracy (OA), 92.56% F1 score, 90.56% mean intersection over union (MIOU), less training and response time and higher-quality value) when compared with other deep learning methods.
关键词： imagery,very high resolution,deep learning,building extraction,attention mechanism
更新于2025-09-04 15:30:14
-
I'm Not Sure What Bothers Me in this Chest X-Ray but an HRCT May Help?
摘要： There are some inevitable risk factors of patient exposure to problems arising from human errors, including missed subtle radiological findings, early identification of which may alter the patient outcomes. Here we are discussing a patient who presented with a prior diagnosis of seasonal allergic rhinitis with symptoms assumed to be bronchial asthma. A second review of chest radiograph after discussion over an online platform (Tabula Rasa group on Facebook) revealed some subtle findings which we missed initially. Further work-up of the case revealed some astonishing findings. This case illustrates the importance of discussing unsolved cases on online platforms with peers and also to proceed for higher imaging to detect what has been missed on plain radiography.
关键词： chest X ray,high resolution computed tomography,subtle findings
更新于2025-09-04 15:30:14
-
Synthesis of TiO2/SiO2-B2O3 Ternary Nanocomposites: Influence of Interfacial Properties on their Photocatalytic Activities with High Resolution Mass Spectrometry Monitoring
摘要： An investigation on unusual interface properties of unprecedented ternary composites, formed by the inclusion of assorted proportions of B2O3 into TiO2/SiO2 structure, is conducted herein. The influences of B2O3 content and calcination temperature were evaluated. The precursor TiO2/SiO2 material was synthesized via a simple sol-gel procedure that was followed by B2O3 inclusion via maceration and calcination. The materials were fully characterized and their photocatalytic performance to degrade the Indigo Carmine dye investigated. The material prepared with a B/Ti molar ratio of 1 and at calcination temperature of 350 °C (B1-350) showed the best performance, with a superior photocatalytic activity than that of commercial TiO2. The presence of B2O3-TiO2-SiO2 interfaces in the structure of such material was of critical importance in producing a material with these attractive features. Finally, high resolution mass spectrometry monitoring allowed for the characterization of the main degradation products formed under these conditions.
关键词： high resolution mass spectrometry,degradation of Indigo Carmine,B2O3-TiO2-SiO2 ternary nanocomposites,photocatalytic activity,by-products characterization,structural defects
更新于2025-09-04 15:30:14
-
[IEEE 2018 Tenth International Conference on Quality of Multimedia Experience (QoMEX) - Cagliari (2018.5.29-2018.6.1)] 2018 Tenth International Conference on Quality of Multimedia Experience (QoMEX) - A Hybrid Quality Metric for Non-Integer Image Interpolation
摘要： A great need of High-Resolution (HR) images has boosted the development of interpolation techniques. However, it is still a challenging task to objectively evaluate the perceptual quality of interpolated images, especially when the interpolation factor is a non-integer. To address this issue, we propose a hybrid quality metric for non-integer image interpolation that combines both reduced-reference and no-reference philosophies. To validate the proposed metric, we construct a non-integer interpolated image database and conduct a subjective user study to collect subjective opinions for each image. Experiments on the new database show that the proposed metric outperforms previous methods by a large margin.
关键词： high-resolution images,perceptual image processing,Image quality assessment,image interpolation
更新于2025-09-04 15:30:14
-
[IEEE 2018 China International SAR Symposium (CISS) - Shanghai, China (2018.10.10-2018.10.12)] 2018 China International SAR Symposium (CISS) - Inverse Synthetic Aperture Ladar Demonstration and Outdoor Experiments
摘要： Inverse synthetic aperture ladar(ISAL)operates at light wavelength and utilizes the synthetic aperture technique, which can obtain very high resolution two-dimensional or three dimensional image of a moving target and thus have many important applications for target detection and recognition. With a very short wavelength, 10000 times smaller compared with that of microwave radar, ISAL can get a high angle resolution with a small telescope in microseconds. However, ISAL is more sensitive to many errors, such as ladar vibration, atmospheric turbulence, moving target jitter, etc., which bring many difficulties to implement an ISAL equipment. In this article, we present an ISAL demonstration and some outdoor experimental results. The ISAL transmits wideband coherent laser which is created by modulating a phase coded signal onto a continuous laser waveform at 1550nm, and detects weak echoes reflected from moving targets by a coherent detection system. A modified phased gradient autofocus algorithm(MPGA)is utilized to suppress errors and improve image quality. The ISAL demonstration acquires high-resolution images of 3-centimeter with a distance about 200m.
关键词： Inverse Synthetic Aperture Ladar,Phased Gradient Autofocus,High-resolution Imaging
更新于2025-09-04 15:30:14