发布求助
文献互助 智能选刊 最新文献

2017 IEEE International Conference on Imaging Systems and Techniques (IST)最新文献

筛选
英文 中文
Visual saliency-based vehicle manufacturer recognition using autoencoder pre-training deep neural networks 基于视觉显著性的自编码器预训练深度神经网络汽车厂商识别
2017 IEEE International Conference on Imaging Systems and Techniques (IST) Pub Date : 2017-10-01 DOI: 10.1109/IST.2017.8261506
Jiang Zhang, Yao Zhao, Fuqiang Zhou, Ming Chi
{"title":"Visual saliency-based vehicle manufacturer recognition using autoencoder pre-training deep neural networks","authors":"Jiang Zhang, Yao Zhao, Fuqiang Zhou, Ming Chi","doi":"10.1109/IST.2017.8261506","DOIUrl":"https://doi.org/10.1109/IST.2017.8261506","url":null,"abstract":"Vehicle manufacturer recognition (VMR), consisting of vehicle logo detection (VLD) and vehicle logo recognition (VLR), is now a crucial part of intelligent transportation system (ITS). A novel VMR method combining visual saliency detection and autoencoder pre-training deep neural network (AP-DNN) is proposed in this paper. An automatic VLD method based on visual saliency detection is used to build a vehicle logo dataset. This dataset contains 10000 training samples and 1500 testing samples for ten types of vehicle manufacturers. In the experiment stage, using AP-DNN, a VLR rate of 99.20% with a training time of 40 min is obtained, which shows higher accuracy than scale-invariant feature transform (SIFT) or AdaBoost-based methods and less training time than methods using a convolutional neural network (CNN). Further, with 2000 vehicle images for ten different types of manufacturers, a VMR rate of 97.95% is obtained automatically and demonstrates the robustness and efficiency of our method.","PeriodicalId":187213,"journal":{"name":"2017 IEEE International Conference on Imaging Systems and Techniques (IST)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129233913","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
Improved dictionary learning algorithm with mappings for single image super-resolution 基于映射的单幅超分辨率改进字典学习算法
2017 IEEE International Conference on Imaging Systems and Techniques (IST) Pub Date : 2017-10-01 DOI: 10.1109/IST.2017.8261522
Fayaz Ali Dharejo, Zongbo Hao, Anam Bhatti, M. N. Bhatti, Junaid Ahmed, M. A. Jatoi
{"title":"Improved dictionary learning algorithm with mappings for single image super-resolution","authors":"Fayaz Ali Dharejo, Zongbo Hao, Anam Bhatti, M. N. Bhatti, Junaid Ahmed, M. A. Jatoi","doi":"10.1109/IST.2017.8261522","DOIUrl":"https://doi.org/10.1109/IST.2017.8261522","url":null,"abstract":"In this paper a coupled dictionary and mapping function learning algorithm is proposed for the task of single image super-resolution. The proposed algorithm consists of dictionary learning part and image reconstruction part. In the dictionary training stage we propose a coupled dictionary and mapping function learning using the K-singular value decomposition. Using this approach we try to enforce the similarity between the high resolution and low resolution sparse coefficients. The idea is to enforce the sparse coefficients of the low resolution image along with its dictionary to well reconstruct the high resolution image using high resolution dictionary. Here we propose to use a mapping function learning which can learn the linear mappings between two resolution levels. For the dictionary update stage the best low rank approximation of singular value decomposition is used. In the image reconstruction stage low resolution images are up-scaled to the high resolution by using the invariance of the sparse coefficients of two resolution levels. First sparse coefficients of low resolution are calculated using the low resolution dictionary and mappings and then they are converted to high resolution by using the high resolution dictionary and mappings. The proposed algorithm is compared with current leading super-resolution algorithms and provides state-of-the-art results.","PeriodicalId":187213,"journal":{"name":"2017 IEEE International Conference on Imaging Systems and Techniques (IST)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124807807","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
Stereo matching and depth map collection algorithm based on deep learning 基于深度学习的立体匹配与深度图采集算法
2017 IEEE International Conference on Imaging Systems and Techniques (IST) Pub Date : 2017-10-01 DOI: 10.1109/IST.2017.8261504
Hao Xu
{"title":"Stereo matching and depth map collection algorithm based on deep learning","authors":"Hao Xu","doi":"10.1109/IST.2017.8261504","DOIUrl":"https://doi.org/10.1109/IST.2017.8261504","url":null,"abstract":"This paper elaborates the research on stereo matching and depth map collection algorithm based on deep learning, use the Torch deep learning framework based on Linux platform to build neural network. The neural network refers to open source algorithm to achieve the use of convolution neural network instead of the traditional algorithm to calculate the matching cost function. This paper also improves the structure of the convolution neural network by using different activation function and adding the batch normalization layer and other methods, reducing the error matching rate, and then get the disparity map and depth map by the post-processing algorithm which includes the matching cost aggregation, disparity computation, disparity refinement. Then the paper verified the effect of the algorithm by experiment and analyzed the experiment results, and used the Middlebury stereo algorithm evaluation platform to evaluate the algorithm. And finally the porposed algorithm gets better stereo matching effect than before.","PeriodicalId":187213,"journal":{"name":"2017 IEEE International Conference on Imaging Systems and Techniques (IST)","volume":"122 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124514267","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
Land cover classification from ICESat/GLAS waveform data 基于ICESat/GLAS波形数据的土地覆盖分类
2017 IEEE International Conference on Imaging Systems and Techniques (IST) Pub Date : 2017-10-01 DOI: 10.1109/IST.2017.8261451
Qunchong Zhao, Xiaolu Li, Lijun Xu
{"title":"Land cover classification from ICESat/GLAS waveform data","authors":"Qunchong Zhao, Xiaolu Li, Lijun Xu","doi":"10.1109/IST.2017.8261451","DOIUrl":"https://doi.org/10.1109/IST.2017.8261451","url":null,"abstract":"Lidar waveform attributes extracted from the Ice, Cloud, and land Elevation Satellite/Geoscience Laser Altimeter System (ICESat/GLAS) were used to distinguish land cover types for GLAS footprints over Jakobshavn Glacier, West Greenland. The waveform derived attributes (reflectivity and kurtosis) and self-computed waveform attributes (waveform width and waveform beginning location) were extracted as features, while true labels were generated from the LANDSAT 7 image as ground truth through gap-filling, three-band combination and supervised maximum likelihood classification. A Gaussian Process (GP) classifier was used to train classification model for classifying the land cover types into three different categories: snow, bare bedrock and sea water. Over this test site, the algorithm achieved an overall accuracy (OA) of 92.22%.","PeriodicalId":187213,"journal":{"name":"2017 IEEE International Conference on Imaging Systems and Techniques (IST)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122454276","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
A BeiDou weak signal acquisition method with INS-aiding 基于ins辅助的北斗微弱信号采集方法
2017 IEEE International Conference on Imaging Systems and Techniques (IST) Pub Date : 2017-10-01 DOI: 10.1109/IST.2017.8261488
Falin Wu, Shan Xu, Yong Fu, Tahir Jan, Jiemin Chen
{"title":"A BeiDou weak signal acquisition method with INS-aiding","authors":"Falin Wu, Shan Xu, Yong Fu, Tahir Jan, Jiemin Chen","doi":"10.1109/IST.2017.8261488","DOIUrl":"https://doi.org/10.1109/IST.2017.8261488","url":null,"abstract":"China plans to implement the navigation services of BeiDou Satellite Navigation System on a global scale in 2020. To ensure the acquisition in BeiDou-challenged environments, this paper proposed a two-step acquisition method to eliminate influence of bit sign transitions. To reduce the Doppler estimation time, the INS information is integrated to detect the receiver's speed. As satellite ephemeris information is downloaded by the assisted receiver, with the aid of INS, the relative speed of receiver and satellite can be obtained, and the Doppler shift searching range can be reduced within ±300 Hz from ±5 KHz.","PeriodicalId":187213,"journal":{"name":"2017 IEEE International Conference on Imaging Systems and Techniques (IST)","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117344865","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
Analysis of gas/solid two-phase flow imaging system based on ECT technology 基于ECT技术的气固两相流成像系统分析
2017 IEEE International Conference on Imaging Systems and Techniques (IST) Pub Date : 2017-10-01 DOI: 10.1109/IST.2017.8261464
Ma Min, Yan Chao-qi
{"title":"Analysis of gas/solid two-phase flow imaging system based on ECT technology","authors":"Ma Min, Yan Chao-qi","doi":"10.1109/IST.2017.8261464","DOIUrl":"https://doi.org/10.1109/IST.2017.8261464","url":null,"abstract":"Electrical imaging technology is a new detecting method developed in the electromagnetic field theory. Aiming at the problems of accuracy and speed limits of flow pattern identification in gas/solid two-phase flow detection, a 16 electrode electrical capacitance tomography (ECT) system based on Xilinx Spartan-3E series FPGA chip is designed. This system is used to implement high-speed data transmission by DDR2 storage technology and USB bus technology, and adopt the digital quadrature demodulation to replace the analog demodulation, which can improve the real-time performance of the system effectively. The simulation results show that the system has stable performance, fast processing speed and high sampling precision. It has a certain reference value in practical industrial application.","PeriodicalId":187213,"journal":{"name":"2017 IEEE International Conference on Imaging Systems and Techniques (IST)","volume":"122 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117317876","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: 0
Spectral-texture approach to hyperspectral image analysis for plant classification with SVMs 基于光谱纹理的支持向量机植物分类高光谱图像分析
2017 IEEE International Conference on Imaging Systems and Techniques (IST) Pub Date : 2017-10-01 DOI: 10.1109/IST.2017.8261496
A. AlSuwaidi, B. Grieve, Hujun Yin
{"title":"Spectral-texture approach to hyperspectral image analysis for plant classification with SVMs","authors":"A. AlSuwaidi, B. Grieve, Hujun Yin","doi":"10.1109/IST.2017.8261496","DOIUrl":"https://doi.org/10.1109/IST.2017.8261496","url":null,"abstract":"Numerous environmental and financial benefits of using hyperspectral imaging have driven much increased applications on plant monitoring and diagnosis. This paper is concerned with analysis of hyperspectral images for plant discrimination by means of their spectral and texture properties. The main contribution of the work lies in the use feature selection and Markov random field model (MRF) to facilitate such spectral-texture analysis to enhance prediction performance, as compared to conventional analysis methods. A hyperspectral dataset on control and stressed Arabidopsis plant leaves captured by a proximal hyperspectral imaging system was used in the experiment. Texture parameters with different orders were estimated from the MRF model and two support vector machine settings were used in the evaluation. Experimental results showed significant improvements in classification performance of the proposed spectral-texture approach over the conventional analysis methods.","PeriodicalId":187213,"journal":{"name":"2017 IEEE International Conference on Imaging Systems and Techniques (IST)","volume":"113 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120995043","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: 4
Investigation of relaxation factor in landweber iterative algorithm for electrical capacitance tomography 电容层析成像landweber迭代算法中的松弛因子研究
2017 IEEE International Conference on Imaging Systems and Techniques (IST) Pub Date : 2017-10-01 DOI: 10.1109/IST.2017.8261455
W. Tian, Mimi Faisyalini Ramli, Wuqiang Yang, Jiangtao Sun
{"title":"Investigation of relaxation factor in landweber iterative algorithm for electrical capacitance tomography","authors":"W. Tian, Mimi Faisyalini Ramli, Wuqiang Yang, Jiangtao Sun","doi":"10.1109/IST.2017.8261455","DOIUrl":"https://doi.org/10.1109/IST.2017.8261455","url":null,"abstract":"It is crucial to select a suitable relaxation factor in iterative image reconstruction algorithms (e.g. Landweber iterative algorithm) for electrical capacitance tomography (ECT) because it affects the convergence. By simulation, it is found notably that the relaxation factor should be selected adaptively according to the sensor structure (e.g. the number of electrodes) and the permittivity distribution in capacitance measurements. With different number of electrodes and four typical permittivity distributions, the relaxation factor and the related convergence are investigated in consideration of the change in relative image error. It is shown that the relaxation factor can be chosen based on the upper boundary of all relaxation factors. The conclusions in this paper can be used for practical industrial processes, regarding the adaptive selection of relaxation factor and the number of iterations needed.","PeriodicalId":187213,"journal":{"name":"2017 IEEE International Conference on Imaging Systems and Techniques (IST)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125796421","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: 3
A coding method for single-channel passive millmeter wave imaging based on cyclic S matrix 基于循环S矩阵的单通道无源毫米波成像编码方法
2017 IEEE International Conference on Imaging Systems and Techniques (IST) Pub Date : 2017-10-01 DOI: 10.1109/IST.2017.8261526
Zelong Xiao, Caoyang Fan, Ruoling Xiao, Yuankai Wang, Xuan Lu
{"title":"A coding method for single-channel passive millmeter wave imaging based on cyclic S matrix","authors":"Zelong Xiao, Caoyang Fan, Ruoling Xiao, Yuankai Wang, Xuan Lu","doi":"10.1109/IST.2017.8261526","DOIUrl":"https://doi.org/10.1109/IST.2017.8261526","url":null,"abstract":"Single-pixel Passive Millimeter Wave (PMMW) imaging system has drawn much attention for its low cost and low complexity. Nowadays, researchers put more effort into the study of the single-pixel PMMW imaging technology as the wide application of Compressive Sensing technology. Previous studies have indicated that the key of the single-pixel imaging technology is the design of coding template. In most studies, a large number of single-templates are applied for coding sampling. These kinds of methods are not suitable for engineering applications due to their low imaging speed. Therefore, a coding method based on quasi cyclic S matrix is proposed, and a novel coding template is designed to improve the imaging speed in this paper. The algorithms of OMP and TVAL3 simulation results in MaTLAB verity the effectiveness of the proposed method.","PeriodicalId":187213,"journal":{"name":"2017 IEEE International Conference on Imaging Systems and Techniques (IST)","volume":"150 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121370478","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: 0
3-D SAR imaging algorithm application in blast furnace stock lines 三维SAR成像算法在高炉炉料线中的应用
2017 IEEE International Conference on Imaging Systems and Techniques (IST) Pub Date : 2017-10-01 DOI: 10.1109/IST.2017.8261561
Jiang-peng Li, Xianzhong Chen, Qingwen Hou, Zhengpeng Wang
{"title":"3-D SAR imaging algorithm application in blast furnace stock lines","authors":"Jiang-peng Li, Xianzhong Chen, Qingwen Hou, Zhengpeng Wang","doi":"10.1109/IST.2017.8261561","DOIUrl":"https://doi.org/10.1109/IST.2017.8261561","url":null,"abstract":"In this paper, the imaging of blast furnace (BF) stock line has been studied. For the first time, the threedimensional (3-D) synthetic aperture radar (SAR) imaging of BF stock line is realized in anechoic chamber, which lays the foundation for the research and development of blast furnace imaging system. Firstly, the range migration algorithm (RMA) is deduced, and the effectiveness of the imaging algorithm is verified by point targets simulation. Then, the imaging experiments of K band and X band is implemented on the typical stock line scaling model, and the 3-D imaging effect of the stock line scaling model composed of steel ball, iron ore and coke in different frequency band are compared. Finally, the imaging error of the steel balls in the K band is analyzed, and the imaging errors of azimuth, range and elevation are±0.01m, ±0.012m and ± 0.002m respectively.","PeriodicalId":187213,"journal":{"name":"2017 IEEE International Conference on Imaging Systems and Techniques (IST)","volume":"47 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113968119","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: 0
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信
小红书