2012 IEEE International Conference on Imaging Systems and Techniques Proceedings最新文献_第7页

Establishing low dimensional manifolds for 3D object pose estimation 建立用于三维目标姿态估计的低维流形

2012 IEEE International Conference on Imaging Systems and Techniques Proceedings Pub Date : 2012-07-16 DOI: 10.1109/IST.2012.6295483

R. Kouskouridas, A. Gasteratos

{"title":"Establishing low dimensional manifolds for 3D object pose estimation","authors":"R. Kouskouridas, A. Gasteratos","doi":"10.1109/IST.2012.6295483","DOIUrl":"https://doi.org/10.1109/IST.2012.6295483","url":null,"abstract":"We propose a novel solution to the problem of 3D object pose estimation problem that is based on an efficient representation and feature extraction technique. We build a part-based architecture that takes into account both appearance-based characteristics of targets along with their geometrical attributes. This bunch-based structure encompasses an image feature extraction procedure accompanied by a clustering scheme over the abstracted key-points. In a follow-up step, these clusters are considered to establish representative manifolds capable of distinguishing similar poses of different objects into the corresponding classes. We form low dimensional manifolds by incorporating sophisticated operations over the members (clusters) of the extracted part-based architecture. An accurate estimation of the pose of a target is provided by a neural network-based solution that entails a novel input-output space targeting method. The performance of our method is comparatively studied against other related works that provide solution to the 3D object pose estimation and that are based on a) manifold modeling, b) object part-based representation and c) conventional dimensionality reduction frameworks. Experimental results justify our theoretical claims and provide evidence of low generalization error when estimating the 3D pose of objects, with the best performance achieved when employing the Radial Basis Functions kernel.","PeriodicalId":213330,"journal":{"name":"2012 IEEE International Conference on Imaging Systems and Techniques Proceedings","volume":"412 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122860727","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Super-resolution imaging method based on random radiation radar array 基于随机辐射雷达阵列的超分辨率成像方法

2012 IEEE International Conference on Imaging Systems and Techniques Proceedings Pub Date : 2012-07-16 DOI: 10.1109/IST.2012.6403797

Yuanyue Guo, Dongjin Wang, Xuezhi He, Bo Liu

{"title":"Super-resolution imaging method based on random radiation radar array","authors":"Yuanyue Guo, Dongjin Wang, Xuezhi He, Bo Liu","doi":"10.1109/IST.2012.6403797","DOIUrl":"https://doi.org/10.1109/IST.2012.6403797","url":null,"abstract":"For the purpose of obtaining high-resolution staring image of ground targets by high-altitude imaging platforms, this paper proposes a super-resolution imaging approach based on random radiation radar array by combining random signal radiation and correlated imaging. Firstly, this super-resolution imaging principles are analyzed, and the definition of temporal-spatial stochastic characteristics of the radiating electromagnetic field on the target space are presented, and on this basis, the super-resolution imaging potentiality of random radiation radar array is demonstrated theoretically beyond the limitation of antenna aperture. Then the imaging model of stochastic radiation radar array is founded. The influences of random signals and the spatial configuration of the radar array (number of array elements and array aperture) on stochastic characteristics of the radiation field are discussed in detail. Finally, the imaging simulations are performed and the results show that random radiation radar array can improve its resolution by more than 20 times compared with a real aperture radar array with the same size.","PeriodicalId":213330,"journal":{"name":"2012 IEEE International Conference on Imaging Systems and Techniques Proceedings","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129456398","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 9

A GPGPU accelerated compressed sensing with tight wavelet frame transform technique for MR imaging reconstruction 基于紧凑小波帧变换的GPGPU加速压缩感知磁共振成像重建技术

2012 IEEE International Conference on Imaging Systems and Techniques Proceedings Pub Date : 2012-07-16 DOI: 10.1109/IST.2012.6295566

B. Hu, X. Ma, M. Joyce, P. Glover, B. Naleem

{"title":"A GPGPU accelerated compressed sensing with tight wavelet frame transform technique for MR imaging reconstruction","authors":"B. Hu, X. Ma, M. Joyce, P. Glover, B. Naleem","doi":"10.1109/IST.2012.6295566","DOIUrl":"https://doi.org/10.1109/IST.2012.6295566","url":null,"abstract":"High resolution Magnetic Resonance Imaging (MRI) requires long acquisition time to obtain the fully sampled k-space data for image reconstruction. Compressed Sensing (CS) theory has recently been utilized to accelerate the image reconstruction speed by sparsely sampling the k-space. In this work, the CS framework was combined with the Tight Wavelet Frame (TWF) transform to further enhance edges/boundaries of MR images and reduce their noise levels. Because the TWF coefficients at finer scale correspond to important image boundary features, the proposed algorithm is able to effectively enhance the signal to noise ratio of MR images without blurring their edges or create artifacts. The resulting constrained minimization problem is then solved iteratively and requires extensive computational resources. To accelerate the reconstruction for real-time medical image processing purpose, the algorithm is implemented on the General Purpose Graphic Processing Units (GPGPU). The effects of various factors, including the register counts and block size, on the GPU occupancy have been investigated to tune the hardware for the optimum performance. The proposed algorithm demonstrates great potential to accelerate the MR imaging acquisition by 8-fold without noticeable artifacts. Comparisons with other two l1 minimization methods with traditional wavelet transforms further confirm the competitiveness of the proposed algorithm. Moreover, a speedup of 45 times was achieved by the GPGPU implementation compared with the CPU version, and therefore making this algorithm suitable for applications in a clinical MRI setting.","PeriodicalId":213330,"journal":{"name":"2012 IEEE International Conference on Imaging Systems and Techniques Proceedings","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127581332","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

An automated ladar polarimetric system for remote characterization of space materials 用于空间材料远程表征的自动雷达极化系统

2012 IEEE International Conference on Imaging Systems and Techniques Proceedings Pub Date : 2012-07-16 DOI: 10.1109/IST.2012.6295598

G. Giakos, R. Picard, W. Inbody, P. Dao, P. Crabtree, P. Mcnicholl, J. Petermann, S. Shrestha, C. Narayan, S. Marotta

引用次数: 2

Visual communication using LED panel and video camera for mobile object 使用LED面板和视频摄像头进行移动对象的视觉交流

2012 IEEE International Conference on Imaging Systems and Techniques Proceedings Pub Date : 2012-07-16 DOI: 10.1109/IST.2012.6295517

H. Ukida, M. Miwa, Y. Tanimoto, T. Sano, Hideki Yamamoto

引用次数: 7

Optimal shutter speed sequences for real-time HDR video 实时HDR视频的最佳快门速度序列

2012 IEEE International Conference on Imaging Systems and Techniques Proceedings Pub Date : 2012-07-16 DOI: 10.1109/IST.2012.6295505

B. Guthier, S. Kopf, W. Effelsberg

引用次数: 22

OCR-based neural network for ANPR 基于ocr的ANPR神经网络

2012 IEEE International Conference on Imaging Systems and Techniques Proceedings Pub Date : 2012-07-16 DOI: 10.1109/IST.2012.6295581

X. Zhai, F. Bensaali, R. Sotudeh

引用次数: 54

In-situ particle measurement with blurred image processing using telecentric lenses 使用远心透镜进行模糊图像处理的原位粒子测量

2012 IEEE International Conference on Imaging Systems and Techniques Proceedings Pub Date : 2012-07-16 DOI: 10.1109/IST.2012.6295547

Xiaozhen Chen, Wu Zhou, Hailong Liu, Xiaoshu Cai, M. Su, L. Cheng

引用次数: 3

3D effect of electrical capacitance and resistance tomography sensors 电容和电阻层析传感器的三维效应

2012 IEEE International Conference on Imaging Systems and Techniques Proceedings Pub Date : 2012-07-16 DOI: 10.1109/IST.2012.6295557

Jiangtao Sun, Wuqiang Yang

{"title":"3D effect of electrical capacitance and resistance tomography sensors","authors":"Jiangtao Sun, Wuqiang Yang","doi":"10.1109/IST.2012.6295557","DOIUrl":"https://doi.org/10.1109/IST.2012.6295557","url":null,"abstract":"In electrical resistance tomography (ERT) sensors, small pin electrodes are commonly used. It is well known that the pin electrodes cause severe field distortions or 3D effect, and the sensing region of such an ERT sensor is not constrained to the pin electrode plane, but spreads to a large volume. This is also true for electrical capacitance tomography (ECT) sensors, even though it is less severe because of larger size electrodes in ECT sensors. However, when the length of electrodes in an ECT sensor is reduced to almost the same dimension as those in ERT sensor, the 3D effect may be equally obvious. To investigate the 3D effect of ERT and ECT sensors, simulation was carried out with different lengths of electrodes and the results are compared with the corresponding 2D simulation. It is concluded that sensors with longer electrodes usually have less 3D effect without guard electrodes. To investigate the effectiveness of grounded guards, 3D simulation was carried out for ECT sensors with grounded guards and the results are compared with the previous results in term of the 3D effect. It is found that the 3D effects of ECT and ERT sensors without guards are similar to each other, and the grounded guards can reduce the 3D effect of ECT sensors to a great extent.","PeriodicalId":213330,"journal":{"name":"2012 IEEE International Conference on Imaging Systems and Techniques Proceedings","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128072991","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 8

Enhancement of color retinal images in poor imaging conditions 在成像条件差的彩色视网膜图像的增强

2012 IEEE International Conference on Imaging Systems and Techniques Proceedings Pub Date : 2012-07-16 DOI: 10.1109/IST.2012.6295584

G. Russell, N. Mcloughlin, Vincent Nourrit, J. Oakley

引用次数: 2