- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE 2018 9th International Conference on Mechanical and Aerospace Engineering (ICMAE) - Budapest (2018.7.10-2018.7.13)] 2018 9th International Conference on Mechanical and Aerospace Engineering (ICMAE) - Resident Space Objects Streak Extraction and Angular Measurement Error Analysis Base on Space Image Synthesis System
摘要： To maintain awareness, space development of space-based visible system has gained much attention in recent years. Because the angular measurement accuracy of space-based sensor is very sensitive to orbit determination, it’s necessary to analyze the factors of angular measurement error, which can provide references for optimal design of space-based sensor. In this paper, a space image synthesis system is developed to provide the image source for resident space object detection and extraction. Then image extraction error and pose error of observation platform are analyzed, with which that the angle measurement error decreases as the focal length and size of pixel increase under same image extraction error can be concluded. Compared with position and velocity error of satellite, attitude angle error has greater impact on angle measurement error of RSOs. By using Otsu method and mathematical morphology method, the angle measurement error of RSOs can be controlled within 7 arcseconds.
关键词： resident space object,error analysis,angular measurement,space situational awareness,space image synthesis
更新于2025-09-23 15:22:29
-
3D auto-context-based locality adaptive multi-modality GANs for PET synthesis
摘要： Positron emission tomography (PET) has been substantially used recently. To minimize the potential health risk caused by the tracer radiation inherent to PET scans, it is of great interest to synthesize the high-quality PET image from the low-dose one to reduce the radiation exposure. In this paper, we propose a 3D auto-context-based locality adaptive multi-modality generative adversarial networks model (LA-GANs) to synthesize the high-quality FDG PET image from the low-dose one with the accompanying MRI images that provide anatomical information. Our work has four contributions. First, different from the traditional methods that treat each image modality as an input channel and apply the same kernel to convolve the whole image, we argue that the contributions of different modalities could vary at different image locations, and therefore a unified kernel for a whole image is not optimal. To address this issue, we propose a locality adaptive strategy for multi-modality fusion. Second, we utilize 1×1×1 kernel to learn this locality adaptive fusion so that the number of additional parameters incurred by our method is kept minimum. Third, the proposed locality adaptive fusion mechanism is learned jointly with the PET image synthesis in a 3D conditional GANs model, which generates high-quality PET images by employing large-sized image patches and hierarchical features. Fourth, we apply the auto-context strategy to our scheme and propose an auto-context LA-GANs model to further refine the quality of synthesized images. Experimental results show that our method outperforms the traditional multi-modality fusion methods used in deep networks, as well as the state-of-the-art PET estimation approaches.
关键词： Image synthesis,Positron emission topography (PET),Locality adaptive fusion,Generative adversarial networks (GANs),Multi-modality
更新于2025-09-23 15:21:01
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Potential of the Reverse Synthesis Method for the High-Quality SAR Image Synthesis
摘要： A potential of a new Reverse synthesis method proposed at IGARSS 2017 for the high-quality Synthetic Aperture Radar (SAR) image synthesis is presented. Images produced by the method are compared with the best existing approaches for the speckle noise reduction. Further capabilities for the image quality improvement like side lobe, range and azimuth reduction, contrast improvement, autofocusing and target detectability improvement are considered. The novel approach allows both: to produce high quality and high-resolution images from existing SAR raw data and to create new high-quality systems with reduced demands to the on-board equipment.
关键词： SAR,speckle noise,image synthesis,high resolution,synthetic aperture radar,synthetic aperture imaging,image quality
更新于2025-09-09 09:28:46