中国科学院机构知识库网格系统: 检索

Which Matters More in Incidental Category Learning: Edge-Based Versus Surface-Based Features 期刊论文 OAI收割
FRONTIERS IN PSYCHOLOGY, 2019, 卷号: 10, 页码: 12
作者: Zhou, Xiaoyan; Fu, Qiufang; Rose, Michael; Sun, Yuqi

|

收藏 | 浏览/下载：68/0 | 提交时间：2019/03/11

category learning incidental category learning the prototype distortion task edge-based features surface-based features

Road Extraction from VHR Remote-Sensing Imagery via Object Segmentation Constrained by Gabor Features 期刊论文 OAI收割
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION, 2018, 卷号: 7, 期号: 9, 页码: 21
作者: Chen, Li; Zhu, Qing; Xie, Xiao; Hu, Han; Zeng, Haowei

|

收藏 | 浏览/下载：34/0 | 提交时间：2019/06/04

edge constraints Gabor features object segmentation region growing road extraction shape features

Application of a sea surface temperature front composite algorithm in the Bohai, Yellow, and East China Seas SCI/SSCI论文 OAI收割
2016
作者: Ping B.; Su, F. Z.; Meng, Y. S.; Du, Y. Y.; Fang, S. H.

|

收藏 | 浏览/下载：25/0 | 提交时间：2017/11/09

oceanic fronts Sobel algorithm frontal frequency frontal average gradient edge-detection sst images oceanic fronts satellite wintertime features

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：77/0 | 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.

Automatic bridge extraction for optical images (EI CONFERENCE) 会议论文 OAI收割
6th International Conference on Image and Graphics, ICIG 2011, August 12, 2011 - August 15, 2011, Hefei, Anhui, China
Gu D.-Y.; Zhu C.-F.; Shen H.; Hu J.-Z.; Chang H.-X.

收藏 | 浏览/下载：32/0 | 提交时间：2013/03/25

This paper describes a novel hierarchy algorithm for extracting bridges over water in optical images. To reduce the omission of bridges by searching the edge we extract the river regions which the bridges are included in. Firstly we segment the optical image to get the coarse water bodies using iterative threshold eliminate the noise regions and add the missing regions based on k-means clustering with texture information and spatial coherence. Then the blanks are connected based on shape features and candidate bridge regions are segmented from river regions. Finally the bridges are verified by geometric information and the ubiety between bridges and river. The results show that this approach is efficient and effective for extracting bridges in satellite image from Google Earth and in aerial optical images acquired by unmanned aerial vehicle. 2011 IEEE.

An improved algorithm to generate high quality progressive animation models (EI CONFERENCE) 会议论文 OAI收割
2010 International Conference on Biomedical Engineering and Computer Science, ICBECS 2010, April 23, 2010 - April 25, 2010, Wuhan, China
作者: Zhao J.; Zhang S.

收藏 | 浏览/下载：25/0 | 提交时间：2013/03/25

In computer graphics investigation has been made in many years in progressive models generation to alleviate the workload of visualization processing. However most of the existing algorithms only focus on static meshes and very little works are to deal with animation models. In this paper we propose an improved method for generating progressive multiresolution animation models. By the method we first use a normal deviation parameter to improve the famous QEM method as our basic edge contraction metric to generate a base hierarchy. The sequence of the simplified models is generated progressively from the first frame to the last one. Based on the edge contraction sequence in the previous frame the contraction order in the current frame is adjusted according to the deformation degree. We demonstrate that our method works efficiently and can generate better approximations with well-preserved features than previous methods. 2010 IEEE.

Optimal multiresolution dynamic models generation based on triangle importance (EI CONFERENCE) 会议论文 OAI收割
2nd International Conference on Image Analysis and Signal Processing, IASP'2010, April 12, 2010 - April 14, 2010, Xiamen, China
作者: Zhao J.; Zhang S.

收藏 | 浏览/下载：20/0 | 提交时间：2013/03/25

In this paper we propose an efficient method to generate optimal multiresolution dynamic models. By the method we define the triangle importance degree as a weight parameter to be embedded to the edge contraction cost so the new metric can not only measure distance error but also reflect geometric variation of local areas. A deformation degree weight is appended to the aggregated edge contraction cost for the whole animation thus sharp features on areas with large deformation can be preserved. In addition a process of mesh optimization and validity check can further alleviate the geometric distortion of the approximations. Our approach is efficient in operation easy for implementation and as a result high quality of dynamic approximations with well-preserved fine details can be generated at any given frame. 2010 IEEE.

A new algorithm to approximate deforming models based on torsion detection (EI CONFERENCE) 会议论文 OAI收割
2010 6th International Conference on Wireless Communications, Networking and Mobile Computing, WiCOM 2010, September 23, 2010 - September 25, 2010, Chengdu, China
作者: Zhang S.; Wang G.

收藏 | 浏览/下载：26/0 | 提交时间：2013/03/25

In this paper we propose a new method to approximate deforming models based on torsion detection. We propose the use of surface torsion to represent local features on the original model and consider it as an additional weight factor when calculating the edge contraction cost during the simplification process. The approximations of the original deforming models are generated progressively from the first frame to the last one. Based on the edge contraction sequence in the previous frame the contraction order in the current frame is adjusted according to the deformation degree. Our approach is fast easy to implement and as a result good quality approximations with well-preserved fine details can be generated at any given frame. 2010 IEEE.

SAR AND OPTICAL IMAGES REGISTRATION USING SHAPE CONTEXT 会议论文 OAI收割
2010 Ieee International Geoscience and Remote Sensing Symposium, New York
Huang, Lei; Li, Zhen; Zhang, Rui

收藏 | 浏览/下载：23/0 | 提交时间：2014/12/07

Image registration edge features feature dilation shape context airborne

Multiresolution animated models generation based on deformation distance analysis (EI CONFERENCE) 会议论文 OAI收割
2009 International Conference on Computer Modeling and Simulation, ICCMS 2009, February 20, 2009 - February 22, 2009, Macau, China
Shixue Z.; Enhua W.

收藏 | 浏览/下载：61/0 | 提交时间：2013/03/25

In computer graphics animated models have been widely used to represent time-varying data. Reducing the models complexly is a common way to overcome the rendering limitations. In this paper 2009 IEEE. we propose an efficient method for generating multiresolution animated models based on deformation distance analysis. Our method obtains different LOD models by performing iterative edge contraction operations. We use deformation distance to analysis the deformation degree of the triangle planes during the whole animation and define a deformation weight to be added to the aggregated edge contraction cost. Thus features in areas with large deformation can be preserved well. Besides we propose a mesh optimization method for dynamic model sequence which can efficiently improve the temporal coherence and reduce visual artifacts between adjacent frames. The results show our approach is efficient easy to implement and good quality animated approximations with well-preserved fine details can be generated at any given frame. copy