Pub Date : 2014-11-20DOI: 10.1109/ICOT.2014.6954667
Hangqi Yan, Yanning Zhang, Wei Wei, Lei Zhang, Fei Li, Bobo Wang
Unstructured detectors such as KGLRT, ACE and AMF are widely applied for target detection in hyperspectral imagery (HSI). However, conventional global and local approaches construct background model without considering the contamination caused by anomalies and suspected targets. This paper proposes a local ACE algorithm based on the minimum covariance determinant (MCD) estimator. In the proposed algorithm, a spectral angle based clustering method is applied to the whitened hyperspectral data to form several disjoint clusters over the whole image. Then for each cluster, the robust estimations of its background statistics are obtained using the MCD estimator. Finally, the ACE detector is applied to each pixel utilizing the robust background statistics of the cluster. With experimental results on two different real datasets, the superiority of the proposed algorithm is demonstrated.
{"title":"An MCD-based local ACE algorithm for hyperspectral imagery target detection","authors":"Hangqi Yan, Yanning Zhang, Wei Wei, Lei Zhang, Fei Li, Bobo Wang","doi":"10.1109/ICOT.2014.6954667","DOIUrl":"https://doi.org/10.1109/ICOT.2014.6954667","url":null,"abstract":"Unstructured detectors such as KGLRT, ACE and AMF are widely applied for target detection in hyperspectral imagery (HSI). However, conventional global and local approaches construct background model without considering the contamination caused by anomalies and suspected targets. This paper proposes a local ACE algorithm based on the minimum covariance determinant (MCD) estimator. In the proposed algorithm, a spectral angle based clustering method is applied to the whitened hyperspectral data to form several disjoint clusters over the whole image. Then for each cluster, the robust estimations of its background statistics are obtained using the MCD estimator. Finally, the ACE detector is applied to each pixel utilizing the robust background statistics of the cluster. With experimental results on two different real datasets, the superiority of the proposed algorithm is demonstrated.","PeriodicalId":343641,"journal":{"name":"2014 International Conference on Orange Technologies","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130738010","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}
Pub Date : 2014-11-20DOI: 10.1109/ICOT.2014.6954668
Sicong Yue, Qingsong Song, Weidong Qu
This paper proposed a new improved singular value decomposition method to achieve high accuracy and much more number of correct point correspondences between uncalibrated images with large scene variations. The proposed matching method is based on singular value decomposition and Sift feature descriptor. The proximity matrix for decomposition is redefined to improve the performance of robustness and reliability. Firstly the distance of Sift descriptors is introduced in the proximity matrix to replace spatial distance. Furthermore illumination invariant normalized cross correlation, that simultaneously includes scale and dominant orientation of the feature points, is used as similarity measure to strengthen proximity matrix. Thus, the element in proximity matrix is invariant to scale, rotation, and light changes. Experimental results show that the improved method can be used for point correspondence with severe wide baseline variations and provide evidence of better performance with respect to other popular algorithms.
{"title":"Robust point correspondence by improved proximity matrix","authors":"Sicong Yue, Qingsong Song, Weidong Qu","doi":"10.1109/ICOT.2014.6954668","DOIUrl":"https://doi.org/10.1109/ICOT.2014.6954668","url":null,"abstract":"This paper proposed a new improved singular value decomposition method to achieve high accuracy and much more number of correct point correspondences between uncalibrated images with large scene variations. The proposed matching method is based on singular value decomposition and Sift feature descriptor. The proximity matrix for decomposition is redefined to improve the performance of robustness and reliability. Firstly the distance of Sift descriptors is introduced in the proximity matrix to replace spatial distance. Furthermore illumination invariant normalized cross correlation, that simultaneously includes scale and dominant orientation of the feature points, is used as similarity measure to strengthen proximity matrix. Thus, the element in proximity matrix is invariant to scale, rotation, and light changes. Experimental results show that the improved method can be used for point correspondence with severe wide baseline variations and provide evidence of better performance with respect to other popular algorithms.","PeriodicalId":343641,"journal":{"name":"2014 International Conference on Orange Technologies","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132408736","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}
Pub Date : 2014-11-20DOI: 10.1109/ICOT.2014.6954664
Jie Hu, Hailiang Li, Ying Li
This paper proposes an efficient and structure-based image/video (interframe independent) super resolution (SR) scheme. Image/video SR is currently a very active area of research because it is used in various applications. The basic idea of the proposed scheme is based on the concepts of pattern redundancy and parallel computing. Global and local motions of pixels are well estimated by exploiting the repeated and structured patterns existing in the most nature images. The value of a missing pixel in the desired high resolution image is obtained by calculating the weighted average of the selected pixels according to the estimated motions, which is able to preserve the intrinsic geometric structure of the original low resolution image/video stream. After that, the estimated pixels' values will be re-corrected by using iterative back projection (IBP) approach in which auxiliary high frequency information embedded. The proposed scheme is mainly implemented in parallel programming strategy based on Compute Unified Device Architecture (CUDA), to reconstruct desired high resolution image/video steam from its low resolution counterparts. Experimental results show that the proposed method has high performance on both the visual quality and real time processing speed.
{"title":"Real time super resolution reconstruction for video stream based on GPU","authors":"Jie Hu, Hailiang Li, Ying Li","doi":"10.1109/ICOT.2014.6954664","DOIUrl":"https://doi.org/10.1109/ICOT.2014.6954664","url":null,"abstract":"This paper proposes an efficient and structure-based image/video (interframe independent) super resolution (SR) scheme. Image/video SR is currently a very active area of research because it is used in various applications. The basic idea of the proposed scheme is based on the concepts of pattern redundancy and parallel computing. Global and local motions of pixels are well estimated by exploiting the repeated and structured patterns existing in the most nature images. The value of a missing pixel in the desired high resolution image is obtained by calculating the weighted average of the selected pixels according to the estimated motions, which is able to preserve the intrinsic geometric structure of the original low resolution image/video stream. After that, the estimated pixels' values will be re-corrected by using iterative back projection (IBP) approach in which auxiliary high frequency information embedded. The proposed scheme is mainly implemented in parallel programming strategy based on Compute Unified Device Architecture (CUDA), to reconstruct desired high resolution image/video steam from its low resolution counterparts. Experimental results show that the proposed method has high performance on both the visual quality and real time processing speed.","PeriodicalId":343641,"journal":{"name":"2014 International Conference on Orange Technologies","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131293959","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}
Pub Date : 2014-11-20DOI: 10.1109/ICOT.2014.6956640
Huashan Feng, Wenhao Dong, N. Chai
A bionic micro sucker was designed in this study based on the analyses of the structure and behavior of leech suckers. This sucker helps micro medical robot to adhere to the inner wall of the gastrointestinal tract and perform long-term test of the peristalsis. It is actuated by petaloid ionic-polymer metal composite (IPMC), and wrapped by innocuous silicone rubber, which makes it like a foveate plate and fit closely on the inner wall of the gastrointestinal tract. The silicone elastomer structure bends when 3-5V direct voltage is applied to the IPMC, and forms a negative pressure by closely contact with the gastrointestinal tract, thus realizing the initiative adsorption that imitates leech suckers. The preliminary experiment showed that this micro sucker is able to bear a load of 200g successfully when it sucks on a glass surface.
{"title":"A bionic micro sucker actuated by IPMC","authors":"Huashan Feng, Wenhao Dong, N. Chai","doi":"10.1109/ICOT.2014.6956640","DOIUrl":"https://doi.org/10.1109/ICOT.2014.6956640","url":null,"abstract":"A bionic micro sucker was designed in this study based on the analyses of the structure and behavior of leech suckers. This sucker helps micro medical robot to adhere to the inner wall of the gastrointestinal tract and perform long-term test of the peristalsis. It is actuated by petaloid ionic-polymer metal composite (IPMC), and wrapped by innocuous silicone rubber, which makes it like a foveate plate and fit closely on the inner wall of the gastrointestinal tract. The silicone elastomer structure bends when 3-5V direct voltage is applied to the IPMC, and forms a negative pressure by closely contact with the gastrointestinal tract, thus realizing the initiative adsorption that imitates leech suckers. The preliminary experiment showed that this micro sucker is able to bear a load of 200g successfully when it sucks on a glass surface.","PeriodicalId":343641,"journal":{"name":"2014 International Conference on Orange Technologies","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116308368","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}
Pub Date : 2014-11-20DOI: 10.1109/ICOT.2014.6956601
Tsung-Han Hsieh, H. Huang
In this paper we advocate that improving teaching quality through better course design should be at least the same important as the other components of current Orange Technology. In order to attain this idea, we present a course design which have applied the concept of gamification and practised with role playing. Gamification is applied to a group role playing game to intensified the material students are expected to learn in the course. Comparing the student participating rate of the role playing game over 3 years, this study finds that gamification should be able to increase the willing of students to participate voluntarily in the activities of a course. An informal query upon students who have participated in the gamified course show that gamification can be an efficient tool to deliver strong impressions in student's mindset.
{"title":"Happy studying by gamificational role playing","authors":"Tsung-Han Hsieh, H. Huang","doi":"10.1109/ICOT.2014.6956601","DOIUrl":"https://doi.org/10.1109/ICOT.2014.6956601","url":null,"abstract":"In this paper we advocate that improving teaching quality through better course design should be at least the same important as the other components of current Orange Technology. In order to attain this idea, we present a course design which have applied the concept of gamification and practised with role playing. Gamification is applied to a group role playing game to intensified the material students are expected to learn in the course. Comparing the student participating rate of the role playing game over 3 years, this study finds that gamification should be able to increase the willing of students to participate voluntarily in the activities of a course. An informal query upon students who have participated in the gamified course show that gamification can be an efficient tool to deliver strong impressions in student's mindset.","PeriodicalId":343641,"journal":{"name":"2014 International Conference on Orange Technologies","volume":"60 36","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120930437","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}
Pub Date : 2014-11-20DOI: 10.1109/ICOT.2014.6956616
Bo Wang, Yingjun Sun, Cheng-Chung Tang, Yang Liu
The propagation and influence is an important problem for online social network. In this paper, we develop a visualization toolkit for online social network propagation and influence analysis and predication which can not only present the main trend of the propagation and influence, but also can present them in multiple views e.g., time and location distribution. Considering the existing works mostly analysis the propagation and influence with the structure of the social network and the features of the individuals, in this paper, we also try to introduce the features of the information content to the problems. The main technologies and implementation results of the toolkit are introduced in this paper.
{"title":"A visualization toolkit for online social network propagation and influence analysis with content features","authors":"Bo Wang, Yingjun Sun, Cheng-Chung Tang, Yang Liu","doi":"10.1109/ICOT.2014.6956616","DOIUrl":"https://doi.org/10.1109/ICOT.2014.6956616","url":null,"abstract":"The propagation and influence is an important problem for online social network. In this paper, we develop a visualization toolkit for online social network propagation and influence analysis and predication which can not only present the main trend of the propagation and influence, but also can present them in multiple views e.g., time and location distribution. Considering the existing works mostly analysis the propagation and influence with the structure of the social network and the features of the individuals, in this paper, we also try to introduce the features of the information content to the problems. The main technologies and implementation results of the toolkit are introduced in this paper.","PeriodicalId":343641,"journal":{"name":"2014 International Conference on Orange Technologies","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124630386","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}
Pub Date : 2014-11-20DOI: 10.1109/ICOT.2014.6954671
Mohib A. Shah, Jinman Kim, M. Khadra, D. Feng
Recent years have witnessed rapid development of Telehealth applications and the integration of portable devices to facilitate services such as Voice-over-IP (VoIP), Video-over-IP and distribution of other data types e.g., medical images and health sensor data. In line with Telehelath, Home Area Network (HAN) has also seen broad deployments and has expanded conventional households to support latest electronic devices that are equipped with network connectivity. Telehealth applications are starting to be designed to take advantages of the HAN environment and are providing healthcare at the patients home, i.e., facilitates hospital at home via video-consultation-call (VCC). However, some of these Telehealth applications are highly delay sensitive and require higher bandwidth priority and a network load-balancing system in order to produce best quality of service (QoS). We observed that typical HAN is established without bandwidth priority and network-load-balancing systems. This lack of management causes HAN to produce unacceptable QoS for Telehealth applications. In this scenario, we propose a scheme to enhance HAN while providing better quality of VCC to support Telehealth services. Our scheme controls the Internet traffic within the HAN network infrastructure environment. In our experimental setting, we implemented a real network test-bed based on HAN where two-way Skype VCC was established and the quality of packet-loss was measured. Skype was chosen for its wide availability and support on all types of computing devices (PC, mobile, laptop etc.). Our results indicate that packet-loss fluctuates between ~5-16% when user datagram protocol (UDP) traffic is utilised concurrently by other devices in HAN. It also demonstrated that our scheme could enhance HAN performance for VCC as it reduced packet-loss down to ~0.3 %.
{"title":"Enhancing home area networks to facilitate telehealth services: Test-bed scenario with video-consultation-calls (VCC)","authors":"Mohib A. Shah, Jinman Kim, M. Khadra, D. Feng","doi":"10.1109/ICOT.2014.6954671","DOIUrl":"https://doi.org/10.1109/ICOT.2014.6954671","url":null,"abstract":"Recent years have witnessed rapid development of Telehealth applications and the integration of portable devices to facilitate services such as Voice-over-IP (VoIP), Video-over-IP and distribution of other data types e.g., medical images and health sensor data. In line with Telehelath, Home Area Network (HAN) has also seen broad deployments and has expanded conventional households to support latest electronic devices that are equipped with network connectivity. Telehealth applications are starting to be designed to take advantages of the HAN environment and are providing healthcare at the patients home, i.e., facilitates hospital at home via video-consultation-call (VCC). However, some of these Telehealth applications are highly delay sensitive and require higher bandwidth priority and a network load-balancing system in order to produce best quality of service (QoS). We observed that typical HAN is established without bandwidth priority and network-load-balancing systems. This lack of management causes HAN to produce unacceptable QoS for Telehealth applications. In this scenario, we propose a scheme to enhance HAN while providing better quality of VCC to support Telehealth services. Our scheme controls the Internet traffic within the HAN network infrastructure environment. In our experimental setting, we implemented a real network test-bed based on HAN where two-way Skype VCC was established and the quality of packet-loss was measured. Skype was chosen for its wide availability and support on all types of computing devices (PC, mobile, laptop etc.). Our results indicate that packet-loss fluctuates between ~5-16% when user datagram protocol (UDP) traffic is utilised concurrently by other devices in HAN. It also demonstrated that our scheme could enhance HAN performance for VCC as it reduced packet-loss down to ~0.3 %.","PeriodicalId":343641,"journal":{"name":"2014 International Conference on Orange Technologies","volume":"160 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120936552","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}
Pub Date : 2014-11-20DOI: 10.1109/ICOT.2014.6956613
Hua Cao, Jiazhong Chen, Jiayi Cao
320 Slice Dynamic Volume CT provides intracranial aneurysm patients with 4D digital subtraction angiography (DSA) imaging and the Key technology of which are the wide detection platform and ConeXact Cone-beam reconstruction algorithm. In this thesis, some familiar cone-beam scan reconstruction algorithms are analyzed and compared, especially those algorithms currently developed such as Feldkamp-type, Grangeant, Katsevich and ConeXact cone-beam reconstruction algorithm. In clinical applications, thirty-four aneurysm patients have through the dynamic volume scan with wide detection platform by TOSHIBA 320 Slice CT and obtained fine single-pass imaging results all of which had no phase artifacts. The quality of scanning images were evaluated and compared with computed tomography angiography (CTA) and convention cerebral vascular DSA angiography. Comparative analysis shows that the 320 slice CT has great advantages in dynamic volume function imaging compared to CTA and it is of a great value to screen out patients with susceptible intracranial aneurysm from the following re-examination after the surgery for the patients with aneurysm.
{"title":"Development and evaluated for intracranial aneurysm imaging reconstruction algorithms by 320 Slice Dynamic Volume CT","authors":"Hua Cao, Jiazhong Chen, Jiayi Cao","doi":"10.1109/ICOT.2014.6956613","DOIUrl":"https://doi.org/10.1109/ICOT.2014.6956613","url":null,"abstract":"320 Slice Dynamic Volume CT provides intracranial aneurysm patients with 4D digital subtraction angiography (DSA) imaging and the Key technology of which are the wide detection platform and ConeXact Cone-beam reconstruction algorithm. In this thesis, some familiar cone-beam scan reconstruction algorithms are analyzed and compared, especially those algorithms currently developed such as Feldkamp-type, Grangeant, Katsevich and ConeXact cone-beam reconstruction algorithm. In clinical applications, thirty-four aneurysm patients have through the dynamic volume scan with wide detection platform by TOSHIBA 320 Slice CT and obtained fine single-pass imaging results all of which had no phase artifacts. The quality of scanning images were evaluated and compared with computed tomography angiography (CTA) and convention cerebral vascular DSA angiography. Comparative analysis shows that the 320 slice CT has great advantages in dynamic volume function imaging compared to CTA and it is of a great value to screen out patients with susceptible intracranial aneurysm from the following re-examination after the surgery for the patients with aneurysm.","PeriodicalId":343641,"journal":{"name":"2014 International Conference on Orange Technologies","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116997925","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}
Pub Date : 2014-11-20DOI: 10.1109/ICOT.2014.6956608
Hongwu Yang, Xiaochun An, Dong Pei, Yitong Liu
This paper realizes a gesture-to-speech conversion system to solve the communication problem between healthy people and speech disorders. An improved speeded up robust features (SURF) algorithm is adopted for static gesture recognition by combining Kinect sensor. Meanwhile, a Hidden Markov Model (HMM) based Mandarin-Tibetan bilingual speech synthesis system is developed by using speaker adaptive training. A set of semantic rules is designed for the static gestures. Chinese or Tibetan context-dependent labels of recognized static gestures are generated according to the semantic rules. The recognized gestures are finally converted to the Mandarin or Tibetan by using the Mandarin-Tibetan bilingual speech synthesis system with the context-dependent labels. Tests show that the static gesture recognition rate of the designed system achieves 97.1%. Subjective evaluation demonstrates that synthesized speech can get 4.0 of the mean opinion score (MOS) on synthesized speech.
{"title":"Towards realizing gesture-to-speech conversion with a HMM-based bilingual speech synthesis system","authors":"Hongwu Yang, Xiaochun An, Dong Pei, Yitong Liu","doi":"10.1109/ICOT.2014.6956608","DOIUrl":"https://doi.org/10.1109/ICOT.2014.6956608","url":null,"abstract":"This paper realizes a gesture-to-speech conversion system to solve the communication problem between healthy people and speech disorders. An improved speeded up robust features (SURF) algorithm is adopted for static gesture recognition by combining Kinect sensor. Meanwhile, a Hidden Markov Model (HMM) based Mandarin-Tibetan bilingual speech synthesis system is developed by using speaker adaptive training. A set of semantic rules is designed for the static gestures. Chinese or Tibetan context-dependent labels of recognized static gestures are generated according to the semantic rules. The recognized gestures are finally converted to the Mandarin or Tibetan by using the Mandarin-Tibetan bilingual speech synthesis system with the context-dependent labels. Tests show that the static gesture recognition rate of the designed system achieves 97.1%. Subjective evaluation demonstrates that synthesized speech can get 4.0 of the mean opinion score (MOS) on synthesized speech.","PeriodicalId":343641,"journal":{"name":"2014 International Conference on Orange Technologies","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125750415","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}
Pub Date : 2014-11-20DOI: 10.1109/ICOT.2014.6954672
Bei Fang, Ying Li, Peng Zhang, Bendu Bai
Spectral unmixing is one of the most challenging and fundamental problems in hyperspectral imagery. In this paper, we address a hyperspectral imagery unmixing problem by introducing sparse nonnegative matrix factorization unmixing algorithms into kernel space. Many sparse nonnegative matrix factorization algorithms has been recently applied to solve the hyperspectral unmixing problem because it overcome the difficulty of absence of pure pixels and sufficiently utilize the sparse characteristic of the data. Most existing sparse nonnegative matrix factorization algorithms for unmixing are based on the linear mixing models. In fact, hyperspectral data are more likely to lie on nonlinear model space. Motivated by the fact that kernel trick can capture the nonlinear structure of data during the decomposition, we propose a new hyperspectral imagery unmixing algorithm by introducing sparse nonnegative matrix factorization unmixing algorithms into kernel space in this paper. Experimental results based on synthetic hyperspectral data show the superiority of the proposed algorithm with respect to other state-of-the-art approaches.
{"title":"Kernel sparse NMF for hyperspectral unmixing","authors":"Bei Fang, Ying Li, Peng Zhang, Bendu Bai","doi":"10.1109/ICOT.2014.6954672","DOIUrl":"https://doi.org/10.1109/ICOT.2014.6954672","url":null,"abstract":"Spectral unmixing is one of the most challenging and fundamental problems in hyperspectral imagery. In this paper, we address a hyperspectral imagery unmixing problem by introducing sparse nonnegative matrix factorization unmixing algorithms into kernel space. Many sparse nonnegative matrix factorization algorithms has been recently applied to solve the hyperspectral unmixing problem because it overcome the difficulty of absence of pure pixels and sufficiently utilize the sparse characteristic of the data. Most existing sparse nonnegative matrix factorization algorithms for unmixing are based on the linear mixing models. In fact, hyperspectral data are more likely to lie on nonlinear model space. Motivated by the fact that kernel trick can capture the nonlinear structure of data during the decomposition, we propose a new hyperspectral imagery unmixing algorithm by introducing sparse nonnegative matrix factorization unmixing algorithms into kernel space in this paper. Experimental results based on synthetic hyperspectral data show the superiority of the proposed algorithm with respect to other state-of-the-art approaches.","PeriodicalId":343641,"journal":{"name":"2014 International Conference on Orange Technologies","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127347443","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：