中国科学院机构知识库网格系统: 检索

浏览/检索结果: 共6条，第1-6条

帮助

条数/页：排序方式：
	Multi-Component Fusion Network for Small Object Detection in Remote Sensing Images 期刊论文 OAI收割 IEEE ACCESS, 2019, 卷号: 7, 页码: 128339-128352 作者: Liu, Jing; Yang, Shuojin; Tian, Liang; Guo, Wei; Zhou, Bingyin \| 收藏 \| 浏览/下载：54/0 \| 提交时间：2019/12/10 Small object remote sensing multi-component dual pyramid fusion occlusion complex scene
	Scene matching based on directional keylines and polar transform (EI CONFERENCE) 会议论文 OAI收割 2010 IEEE 10th International Conference on Signal Processing, ICSP2010, October 24, 2010 - October 28, 2010, Beijing, China 作者: Wang Y.; Wang Y.; Wang Y.; Wang Y.; Wang Y. 收藏 \| 浏览/下载：23/0 \| 提交时间：2013/03/25 Scene matching under complex background is a priority and difficulty in the field of computer vision it has the characteristics of rotation and scaling invariance commonly used in matching real-time collected images and photos for navigation. Scene matching techniques are faced with complex natural scenes anti-light and anti-slight-distortion the image distortion exist applicable for complex scene matching. The project has a new idea: combining the keylines with the vectors description based on polar image translation such as light and utilize the rotation-scale-invariance vectors to describe the extracted keylines change of gray levels this method includes three steps: keylines extraction perspective description and matching. Preliminary experiments show that this keylines-based scene matching algorithm is applicable for image matching under complex background. 2010 IEEE. scaling and other differences which cause matching difficult. This paper aims to find a scene matching algorithm
	Non-uniformity correction in multi-CCD imaging system (EI CONFERENCE) 会议论文 OAI收割 2010 2nd International Conference on Mechanical and Electronics Engineering, ICMEE 2010, August 1, 2010 - August 3, 2010, Kyoto, Japan Tao M.; Ren J. 收藏 \| 浏览/下载：25/0 \| 提交时间：2013/03/25 The non-uniformity phenomenon exists in each channel of multi-CCD imaging systems. The factors which lead to the problem are complex. The conventional calibrating algorithms can not consider all of these factors and have poor effects. According to the characters of multi-CCD imaging systems a non-uniformity correction method based on the scene was proposed by adopting the traditional two-point correction theories. The correction coefficient of each channel image can be calculated via the linear relation between the two neighboring pixel lines in the two-channel images. Compared with the conventional two-point calibration and multi-point calibration methods contrastive calibrating results were obtained. This method does not need any standard lighted image as reference source which provides a real time way for calibrating the multi-CCD imaging systems in practical applications. 2010 IEEE.
	复杂背景下的目标实时分割与检测学位论文 OAI收割工学博士, 中国科学院自动化研究所: 中国科学院研究生院, 2009 作者: 吴晓雨收藏 \| 浏览/下载：104/0 \| 提交时间：2015/09/02 交互式分割实时目标分割实时目标检测背景建模图切复杂背景 interactive segmentation real-time object segmentation real-time object detection background modeling graph cut complex scene
	A MLP-PNN neural network for CCD image super-resolution in wavelet packet domain (EI CONFERENCE) 会议论文 OAI收割 2008 International Conference on Wireless Communications, Networking and Mobile Computing, WiCOM 2008, October 12, 2008 - October 14, 2008, Dalian, China Zhao X.; Fu D.; Zhai L. 收藏 \| 浏览/下载：68/0 \| 提交时间：2013/03/25 Image super-resolution methods process an input image sequence of a scene to obtain a still image with increased resolution. Classical approaches to this problem involve complex iterative minimization procedures typically with high computational costs. In this paper is proposed a novel algorithm for super-resolution that enables a substantial decrease in computer load. First decompose and reconstruct the image by wavelet packet. Before constructing the image use neural network in place of other rebuilding method to reconstruct the coefficients in the wavelet packet domain. Second probabilistic neural network architecture is used to perform a scattered-point interpolation of the image sequence data in the wavelet packet domain. The network kernel function is optimally determined for this problem by a MLP-PNN (Multi Layer Perceptron - Probabilistic Neural Network) trained on synthetic data. Network parameters dependent on the sequence noise level. This super-sampled image is spatially Altered to correct finite pixel size effects to yield the final high-resolution estimate. This method can decrease the calculation cost and get perfect PSNR. Results are presented showing the quality of the proposed method. 2008 IEEE.
	corridor-scene classification for mobile robot using spiking neurons 会议论文 OAI收割 4th International Conference on Natural Computation (ICNC 2008), Jian, PEOPLES R CHINA, OCT 18-20, Wang Xiuqing; Hou Zeng-Guang; Tan Min; Wang Yongji; Wang Xinian \| 收藏 \| 浏览/下载：14/0 \| 提交时间：2011/06/13 cognition complex environment corridor-scene classification corridor-scene-classifier integrate-and-fire model mobile robot real autonomous robot spiking neural networks spiking neurons winner-take-all rule mobile robots neural nets pattern clas