中国科学院机构知识库网格系统: 检索

浏览/检索结果: 共7条，第1-7条

帮助

条数/页：排序方式：
	RaHFF-Net: Recall-Adjustable Hierarchical Feature Fusion Network for Remote Sensing Image Change Detection 期刊论文 OAI收割 IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2025, 卷号: 18, 页码: 176-190 作者: Wang, Bin; Zhao, Kang; Xiao, Tong; Qin, Pinle; Zeng, Jianchao \| 收藏 \| 浏览/下载：4/0 \| 提交时间：2025/03/18 Feature extraction Transformers Semantics Lighting Data mining Tensors Correlation Noise Indexes Adaptation models Change detection (CD) hyperexpectation push pull (HEPP) loss multiscale feature fusion transformer
	FCDM: A Methodology Based on Sensor Pattern Noise Fingerprinting for Fast Confidence Detection to Adversarial Attacks 期刊论文 OAI收割 IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2020, 卷号: 39, 期号: 12, 页码: 4791-4804 作者: Lan, Yazhu; Nixon, Kent W.; Guo, Qingli; Zhang, Guohe; Xu, Yuanchao \| 收藏 \| 浏览/下载：70/0 \| 提交时间：2021/12/01 Perturbation methods Computational modeling Data integrity Detectors Optimization Field programmable gate arrays Hardware Adversarial attacks confidence detection deep neural networks (DNNs) FPGA-based hardware architecture sensor pattern noise (SPN)
	A new method for noise data detection based on DBSCAN and SVDD 会议论文 OAI收割 2015 IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems (CYBER), Shenyang, China, June 8-12, 2015 作者: Hao SX(郝胜轩); Zhou XF(周晓锋); Song H(宋宏) 收藏 \| 浏览/下载：43/0 \| 提交时间：2015/12/16 SVDD DBSCAN noise data detection
	A new approach for noise data detection based on cluster and information entropy 会议论文 OAI收割 2015 IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems (CYBER), Shenyang, China, June 8-12, 2015 作者: Zhou XF(周晓锋); Zhang YL(章永来); Hao SX(郝胜轩); Li S(李帅) 收藏 \| 浏览/下载：33/0 \| 提交时间：2015/12/16 fast search and find of density peaks information entropy noise data detection
	The Research of real time auto-recognition of the moire fringe (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 Wang M.-J.; Wu Z.-G. 收藏 \| 浏览/下载：18/0 \| 提交时间：2013/03/25 Measuring the movement of raster by the method of moire fringe has the advantage of high sensitivity high resolution and non-contacted measurement. The characteristic of moire fringe is that the image is white alternate with black the angle of the stripes is uniform the width of the stripes is uniform the terminators of the stripes aren't clear. A fast method that can figure out the width and angle of the moire fringe precisely is put forward in this paper. It calculates the angle the stripes firstly. According to the principle of the minimum mean squared error (MMSE) the closer a series of data is the smaller the value of the MMSE will be. The method is described as follows: It takes the image's center as the origin 180 beelines pass through the origin with the same angle interval. it calculates the value of the minimum mean squared error of the 180 beelines and find out the least one among those then the angle of the moire fringe comes out primarily. In order to improving the calculating precision of moire fringe 60 equal angles are divided in the neighborhood of the angle then a precise angle of moire fringe is calculated according to the principle of the MMSE. After getting out the angle of the moire fringe we begin to calculate the width of moire fringe. A line vertical with the moire fringe is drawn and we can get the width of the moire fringe by the vertical line. In order to get over the influence of the noise an effective area with the shape of diamond is selected in the image. The data of area is accumulated and projected according to the direction of moire fringe and a sine curve come out. The width of moire fringe can be obtained by getting the position of the first wave crest the position of the last wave crest and the number of wave crest. Experiments prove that the precision of the method put forward in this paper is enhanced in comparison with the traditional frequency method the precision of width calculation achieves to 99.6% according to the evaluation indicators of width detection error. The computing speed is boosted largely compared with traditional method and it can achieve with 15 ms that satisfying the demand of real time. 2011 SPIE.
	Research on tracking approach to low-flying weak small target near the sea (EI CONFERENCE) 会议论文 OAI收割 ICO20: Optical Information Processing, August 21, 2005 - August 26, 2005, Changchun, China 作者: Xue X.-C. 收藏 \| 浏览/下载：32/0 \| 提交时间：2013/03/25 Automatic target detection is very difficult in complicate background of sea and sky because of the clutter caused by waves and clouds nearby the sea-level line. In this paper in view of the low-flying target near the sea is always above the sea-level line we can first locate the sea-level line and neglect the image data beneath the sea-level line. Thus the noise under the sea-level line can be suppressed and the executive time of target segmentation is also much reduced. A new method is proposed which first uses neighborhood averaging method to suppress background and enhance targets so as to increase SNR and then uses the multi-point multi-layer vertical Sobel operator combined with linear least squares fitting to locate the sea-level line lastly uses the centroid tracking algorithm to detect and track the target. In the experiment high frame rate and high-resolution digital CCD camera and high performance DSP are applied. Experimental results show that this method can efficiently locate the sea-level line on various conditions of lower contrast and eliminate the negative impact of the clutter caused by waves and clouds and capture and track target real-timely and accurately.
	Reduction of edge effects in spatial information extraction from regional geochemical data: A case study based on multifractal filtering technique EI期刊论文 OAI收割 2005 作者: Ge Yong 收藏 \| 浏览/下载：23/0 \| 提交时间：2012/06/11 Data reduction Edge detection Fourier transforms Fractals Frequency domain analysis Image analysis Signal to noise ratio