中国科学院机构知识库网格系统: 检索

浏览/检索结果: 共8条，第1-8条

帮助

条数/页：排序方式：
	DC-KD: double-constraint knowledge distillation for optical satellite imagery object detection based on YOLOX model 会议论文 OAI收割 Hangzhou, China, 2023-11-03 作者: Yang, Hongbo; Qiu, Shi; Feng, Xiangpeng \| 收藏 \| 浏览/下载：7/0 \| 提交时间：2024/09/19 Remote sensing image applications Satellite image processing Tiny object detection Knowledge distillation
	Study on spectrograph for ionosphere: A broadband imaging instrument prototype for far-ultraviolet (EI CONFERENCE) 会议论文 OAI收割 International Symposium on Photoelectronic Detection and Imaging 2011: Space Exploration Technologies and Applications, May 24, 2011 - May 26, 2011, Beijing, China 作者: Wang S.-R.; Lin G.-Y.; Yu L. 收藏 \| 浏览/下载：36/0 \| 提交时间：2013/03/25 Current research on space-based exploration for the ionosphere needs more advanced technologies. Because the spectral signals in the ionosphere distributing basically in the far-ultraviolet waveband are very weak. Usual spectrometer structures and detectors such as CCD can't receive enough information. Based on this principle of atmospheric sounding the imaging spectrometer prototype for ionosphere detection application was designed to solve the problem. This prototype consists of the telescope and the imaging spectrometer. The simple structure and small number of mirrors can help higher transmission efficiency be achieved and weak signals detection be implemented. The telescope is an off-axis parabolic mirror and the spectrometer is a modified Czerny-Turner spectral imaging system. Modified Czerny-Turner spectrometer contains a spherical mirror a fixed plane grating and a toroidal mirror. By adjusting the incident angle to the collimating mirror and using toroidal mirror coma and astigmatism were corrected well. We also optimize distances between the grating to the focusing mirror and the focusing mirror to the image plane to improve disadvantages of traditional Czerny-Turner structure. Designed results demonstrate that aberrations are substantially corrected and high image quality can be obtained in broad waveband. The photon counting Wedge-Strip-Anode detector with micro-channel planes as the receiving plane is accepted for the instrument prototype. The other photon counting 2-D detector responding well for weak light such as Cross-Delay line detector and MAMA detector can also be used for detection. The calibration and performances testing system is made of a vacuum system a deuterium lamp a monochrometer and the instrument prototype. Results obtained from the experiment show that the spectral resolution is 2.4 nm and the spatial resolution is 80 m. The other calibration experiments are running. The technology of the spectrometer prototype is important for the research and applications of ionosphere remote sensing. 2011 SPIE.
	Multi-focus image fusion algorithm based on adaptive PCNN and wavelet transform (EI CONFERENCE) 会议论文 OAI收割 International Symposium on Photoelectronic Detection and Imaging 2011: Advances in Imaging Detectors and Applications, May 24, 2011 - May 26, 2011, Beijing, China Wu Z.-G.; Wang M.-J.; Han G.-L. 收藏 \| 浏览/下载：78/0 \| 提交时间：2013/03/25 Being an efficient method of information fusion image fusion has been used in many fields such as machine vision medical diagnosis military applications and remote sensing.In this paper Pulse Coupled Neural Network (PCNN) is introduced in this research field for its interesting properties in image processing including segmentation target recognition et al. and a novel algorithm based on PCNN and Wavelet Transform for Multi-focus image fusion is proposed. First the two original images are decomposed by wavelet transform. Then based on the PCNN a fusion rule in the Wavelet domain is given. This algorithm uses the wavelet coefficient in each frequency domain as the linking strength so that its value can be chosen adaptively. Wavelet coefficients map to the range of image gray-scale. The output threshold function attenuates to minimum gray over time. Then all pixels of image get the ignition. So the output of PCNN in each iteration time is ignition wavelet coefficients of threshold strength in different time. At this moment the sequences of ignition of wavelet coefficients represent ignition timing of each neuron. The ignition timing of PCNN in each neuron is mapped to corresponding image gray-scale range which is a picture of ignition timing mapping. Then it can judge the targets in the neuron are obvious features or not obvious. The fusion coefficients are decided by the compare-selection operator with the firing time gradient maps and the fusion image is reconstructed by wavelet inverse transform. Furthermore by this algorithm the threshold adjusting constant is estimated by appointed iteration number. Furthermore In order to sufficient reflect order of the firing time the threshold adjusting constant is estimated by appointed iteration number. So after the iteration achieved each of the wavelet coefficient is activated. In order to verify the effectiveness of proposed rules the experiments upon Multi-focus image are done. Moreover comparative results of evaluating fusion quality are listed. The experimental results show that the method can effectively enhance the edge details and improve the spatial resolution of the image. 2011 SPIE.
	Ship recognition from high resolution remote sensing imagery aided by spatial relationship 会议论文 OAI收割 2011 IEEE International Conference on Spatial Data Mining and Geographical Knowledge Services, ICSDM 2011 - In Conjunction with 8th Beijing International Workshop on Geographical Information Science, BJ-IWGIS 2011, Fuzhou, China, June 29, 2011 - July 1,2011 Wu, Wei; Luo, Jiancheng; Qiao, Cheng; Shen, Zhanfeng 收藏 \| 浏览/下载：28/0 \| 提交时间：2014/12/07 Ships Data mining Geographic information systems Image reconstruction Marine applications Remote sensing
	SIFT based registration of remotely-sensed imagery 会议论文 OAI收割 2011 International Conference on Future Computer Sciences and Application, ICFCSA 2011,, Hong Kong, China, June 18, 2011 - June 19,2011 Wang, Kai; Bo, Cheng 收藏 \| 浏览/下载：12/0 \| 提交时间：2014/12/07 Computer applications Computer science Image reconstruction Remote sensing
	Aerosol retrieval from remote sensing image using artificial neural network 会议论文 OAI收割 2010-10-22 Wang,Houmao; Tang,Jiakui \| 收藏 \| 浏览/下载：15/0 \| 提交时间：2011/07/22 Atmospheric Aerosols Computer Applications Image Reconstruction Interpolation Remote Sensing
	Application of optical remote sensing in the wenchuan earthquake assessment 会议论文 OAI收割 2nd International Conference on Earth Observation for Global Changes, Chengdu, China, May 25, 2009 - May 29,2009 Zhang, Bing; Lei, Liping; Zhang, Li; Liu, Liangyun; Zhu, Boqin; Zuo, Zhengli 收藏 \| 浏览/下载：54/0 \| 提交时间：2014/12/07 Earthquakes Debris Disasters Earth (planet) Erosion Geographic information systems Geometrical optics Image reconstruction Observatories Remote sensing Roads and streets Satellites Societies and institutions Space applications Space optics
	Research on long focal length On-axis TMA system for high-resolution remote sensing (EI CONFERENCE) 会议论文 OAI收割 3rd International Symposium on Advanced Optical Manufacturing and Testing Technologies, AOMATT 2007: Advanced Optical Manufacturing Technologies, July 8, 2007 - July 12, 2007, Chengdu, China 作者: Zhang L.; Zhang L. 收藏 \| 浏览/下载：25/0 \| 提交时间：2013/03/25 TMA (Three Mirror Anastigmatic) is popular to the design of space-based optical system. This paper describes the characteristics of the on-axis TMA optical system. An on-axis TMA system with 13m focal length is designed and analyzed. To solve the initial configuration parameters Cassagrain structure is confirmed firstly and then the tertiary mirror. Based on initial configuration parameters automatic optimization is executed in ZEMAX program and design result with excellent image quality is acquired which shows the procedure we choosed with good advantage of computer processing. As the distortion of the design reaches 1% its influences on TDICCD brushing camera are discussed. The source of distortion is analyzed and correcting methods are considered. Zero focal power corrector is chosen to correct the distortion and the corrected distortion is less than 0.02%. The research on on-axis TMA system in this paper makes a foundation for farther high-resolution remote sensing applications.