Pub Date : 2008-12-01DOI: 10.1109/PRRS.2008.4783173
S. Aksoy, B. Ozdemir, S. Eckert, F. Kayitakire, M. Pesarasi, O. Aytekin, C. Borel, J. Čech, E. Christophe, S. Duzgun, A. Erener, K. Ertugay, Elima Hussain, J. Inglada, S. Lefèvre, O. Ok, D. K. San, R. Sára, J. Shan, J. Soman, I. Ulusoy, R. Witz
This paper presents the initial results of the algorithm performance contest that was organized as part of the 5th IAPR Workshop on Pattern Recognition in Remote Sensing (PRRS 2008). The focus of the 2008 contest was automatic building detection and digital surface model (DSM) extraction. A QuickBird data set with manual ground truth was used for building detection evaluation, and a stereo Ikonos data set with a highly accurate reference DSM was used for DSM extraction evaluation. Nine submissions were received for the building detection task, and three submissions were received for the DSM extraction task. We provide an overview of the data sets, the summaries of the methods used for the submissions, the details of the evaluation criteria, and the results of the initial evaluation.
{"title":"Performance evaluation of building detection and digital surface model extraction algorithms: Outcomes of the PRRS 2008 Algorithm Performance Contest","authors":"S. Aksoy, B. Ozdemir, S. Eckert, F. Kayitakire, M. Pesarasi, O. Aytekin, C. Borel, J. Čech, E. Christophe, S. Duzgun, A. Erener, K. Ertugay, Elima Hussain, J. Inglada, S. Lefèvre, O. Ok, D. K. San, R. Sára, J. Shan, J. Soman, I. Ulusoy, R. Witz","doi":"10.1109/PRRS.2008.4783173","DOIUrl":"https://doi.org/10.1109/PRRS.2008.4783173","url":null,"abstract":"This paper presents the initial results of the algorithm performance contest that was organized as part of the 5th IAPR Workshop on Pattern Recognition in Remote Sensing (PRRS 2008). The focus of the 2008 contest was automatic building detection and digital surface model (DSM) extraction. A QuickBird data set with manual ground truth was used for building detection evaluation, and a stereo Ikonos data set with a highly accurate reference DSM was used for DSM extraction evaluation. Nine submissions were received for the building detection task, and three submissions were received for the DSM extraction task. We provide an overview of the data sets, the summaries of the methods used for the submissions, the details of the evaluation criteria, and the results of the initial evaluation.","PeriodicalId":315798,"journal":{"name":"2008 IAPR Workshop on Pattern Recognition in Remote Sensing (PRRS 2008)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121266703","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 : 2008-12-01DOI: 10.1109/PRRS.2008.4783168
Q. Du, N. Younan
In this paper, we present a strategy to improve the performance of Fisher's linear discriminant analysis (FLDA) in dimensionality reduction for hyperspectral image classification. The practical difficulty of applying FLDA to hyperspectral imagery includes the unavailability of enough training samples and unknown information for all the classes including background. The original FLDA has been modified to avoid the requirements of training samples and complete class knowledge, which needs the desired class signatures only. The modified FLDA (MFLDA) can better preserve class information in the low-dimensional space. However, for an image scene with p known classes, the data dimensionality after FLDA and MFLDA transform is p-1. The class-separability performance of FLDA and MFLDA may be significantly improved if the transformed data dimensionality is p instead of p-1. An approach is proposed for this purpose and experimental results demonstrate its advantage.
{"title":"On the performance improvement for linear discriminant analysis-based hyperspectral image classification","authors":"Q. Du, N. Younan","doi":"10.1109/PRRS.2008.4783168","DOIUrl":"https://doi.org/10.1109/PRRS.2008.4783168","url":null,"abstract":"In this paper, we present a strategy to improve the performance of Fisher's linear discriminant analysis (FLDA) in dimensionality reduction for hyperspectral image classification. The practical difficulty of applying FLDA to hyperspectral imagery includes the unavailability of enough training samples and unknown information for all the classes including background. The original FLDA has been modified to avoid the requirements of training samples and complete class knowledge, which needs the desired class signatures only. The modified FLDA (MFLDA) can better preserve class information in the low-dimensional space. However, for an image scene with p known classes, the data dimensionality after FLDA and MFLDA transform is p-1. The class-separability performance of FLDA and MFLDA may be significantly improved if the transformed data dimensionality is p instead of p-1. An approach is proposed for this purpose and experimental results demonstrate its advantage.","PeriodicalId":315798,"journal":{"name":"2008 IAPR Workshop on Pattern Recognition in Remote Sensing (PRRS 2008)","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124397396","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 : 2008-12-01DOI: 10.1109/PRRS.2008.4783171
M. Thomas, C. Geiger, P. Kannan, C. Kambhamettu
Non-rigid motion has to sometimes contend with the presence of discontinuous structures when it is estimated under a non-topology preserving deformation. In this paper, we propose an algorithm that estimates large scale non-rigid motion in the presence of these discontinuous structures. We have developed a streamline regularization framework that uses particle streamlines to compute a plausible flow at discontinuities, thereby enabling us to predict the motion more accurately. To quantitatively validate the accuracy of our results, we applied the Wilcoxon Signed Rank Test, which shows an improvement in estimation accuracy using our proposed scheme.
当非刚性运动在非拓扑保持变形下估计时，有时不得不与不连续结构的存在作斗争。在本文中，我们提出了一种算法来估计在这些不连续结构存在下的大规模非刚性运动。我们已经开发了一个流线正则化框架，使用粒子流线来计算不连续处的合理流动，从而使我们能够更准确地预测运动。为了定量验证我们结果的准确性，我们应用了Wilcoxon Signed Rank检验，结果表明使用我们提出的方案可以提高估计精度。
{"title":"Streamline regularization for large discontinuous motion of sea ice","authors":"M. Thomas, C. Geiger, P. Kannan, C. Kambhamettu","doi":"10.1109/PRRS.2008.4783171","DOIUrl":"https://doi.org/10.1109/PRRS.2008.4783171","url":null,"abstract":"Non-rigid motion has to sometimes contend with the presence of discontinuous structures when it is estimated under a non-topology preserving deformation. In this paper, we propose an algorithm that estimates large scale non-rigid motion in the presence of these discontinuous structures. We have developed a streamline regularization framework that uses particle streamlines to compute a plausible flow at discontinuities, thereby enabling us to predict the motion more accurately. To quantitatively validate the accuracy of our results, we applied the Wilcoxon Signed Rank Test, which shows an improvement in estimation accuracy using our proposed scheme.","PeriodicalId":315798,"journal":{"name":"2008 IAPR Workshop on Pattern Recognition in Remote Sensing (PRRS 2008)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133799270","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 : 2008-12-01DOI: 10.1109/PRRS.2008.4783170
P. Yu, David A Clausi, R. de Abreu, T. Agnew
The benefits of augmenting AMSR-E image data with QuikSCAT image data for supervised sea ice classification in the Western Arctic region are investigated. Experiments compared the performance of a maximum likelihood classifier when used with the AMSR-E only data set against the combined data and examined the preferred number of features to use as well as the reliability of training data over time. Adding QuikSCAT often improves classifier accuracy in a statistically significant manner and never decreased it significantly when enough features are used. Combining these data sets is beneficial for sea ice mapping. Using all available features is recommended and training data from a specific date remains reliable within 30 days.
{"title":"Combining AMSR-E and QuikSCAT image data to improve sea ice classification","authors":"P. Yu, David A Clausi, R. de Abreu, T. Agnew","doi":"10.1109/PRRS.2008.4783170","DOIUrl":"https://doi.org/10.1109/PRRS.2008.4783170","url":null,"abstract":"The benefits of augmenting AMSR-E image data with QuikSCAT image data for supervised sea ice classification in the Western Arctic region are investigated. Experiments compared the performance of a maximum likelihood classifier when used with the AMSR-E only data set against the combined data and examined the preferred number of features to use as well as the reliability of training data over time. Adding QuikSCAT often improves classifier accuracy in a statistically significant manner and never decreased it significantly when enough features are used. Combining these data sets is beneficial for sea ice mapping. Using all available features is recommended and training data from a specific date remains reliable within 30 days.","PeriodicalId":315798,"journal":{"name":"2008 IAPR Workshop on Pattern Recognition in Remote Sensing (PRRS 2008)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130556724","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 : 2008-12-01DOI: 10.1109/PRRS.2008.4783167
W. Yao, S. Hinz, Uwe Stilla
In this paper, we address issues in traffic monitoring of urban areas using airborne LiDAR data. Our aim in this paper is to extract individual vehicles from common LiDAR data of urban areas, based on which the dynamical status of vehicles and other traffic-related parameters can be derived. A context-guiding bottom-up processing strategy is developed to accomplish the task. Ground level separation is first used to exclude the irrelevant objects and provide the ldquoRegion of Interestrdquo. The marker-controlled watershed transformation assisted by morphological reconstruction is then performed on the gridded and filled raster of ground level points to delineate the single vehicles. The evaluation of experimental results has shown that most vehicles can be correctly detected, whose delineated contours are accurate.
{"title":"Automatic vehicle extraction from airborne LiDAR data of urban areas using morphological reconstruction","authors":"W. Yao, S. Hinz, Uwe Stilla","doi":"10.1109/PRRS.2008.4783167","DOIUrl":"https://doi.org/10.1109/PRRS.2008.4783167","url":null,"abstract":"In this paper, we address issues in traffic monitoring of urban areas using airborne LiDAR data. Our aim in this paper is to extract individual vehicles from common LiDAR data of urban areas, based on which the dynamical status of vehicles and other traffic-related parameters can be derived. A context-guiding bottom-up processing strategy is developed to accomplish the task. Ground level separation is first used to exclude the irrelevant objects and provide the ldquoRegion of Interestrdquo. The marker-controlled watershed transformation assisted by morphological reconstruction is then performed on the gridded and filled raster of ground level points to delineate the single vehicles. The evaluation of experimental results has shown that most vehicles can be correctly detected, whose delineated contours are accurate.","PeriodicalId":315798,"journal":{"name":"2008 IAPR Workshop on Pattern Recognition in Remote Sensing (PRRS 2008)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122084797","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 : 2008-12-01DOI: 10.1109/PRRS.2008.4783172
David A Clausi, A. K. Qin, M. S. Chowdhury, P. Yu, P. Maillard
A map-guided ice classification (MAGIC) system that aims at effectively interpreting SAR sea ice images using the associated ice charts in an operational environment is presented. As an ongoing project, MAGIC version 1.0 has been developed using operational SAR image data from the Canadian ice service (CIS). MAGIC is intended to not only be used for SAR sea ice classification research and development, but also used for classification research of generic digital imagery using the available fundamental and advanced algorithms. At some point, we hope to make the system freely available.
{"title":"MAGIC: MAp-Guided Ice Classification system for operational analysis","authors":"David A Clausi, A. K. Qin, M. S. Chowdhury, P. Yu, P. Maillard","doi":"10.1109/PRRS.2008.4783172","DOIUrl":"https://doi.org/10.1109/PRRS.2008.4783172","url":null,"abstract":"A map-guided ice classification (MAGIC) system that aims at effectively interpreting SAR sea ice images using the associated ice charts in an operational environment is presented. As an ongoing project, MAGIC version 1.0 has been developed using operational SAR image data from the Canadian ice service (CIS). MAGIC is intended to not only be used for SAR sea ice classification research and development, but also used for classification research of generic digital imagery using the available fundamental and advanced algorithms. At some point, we hope to make the system freely available.","PeriodicalId":315798,"journal":{"name":"2008 IAPR Workshop on Pattern Recognition in Remote Sensing (PRRS 2008)","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124763016","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 : 2008-12-01DOI: 10.1109/PRRS.2008.4783166
Yang Cao, Hong Wei, Huijie Zhao
In this paper, a fuzzy Markov random field (FMRF) model is used to segment land-objects into tree, grass, building, and road regions by fusing remotely sensed LIDAR data and co-registered color bands, i.e. scanned aerial color (RGB) photo and near infra-red (NIR) photo. An FMRF model is defined as a Markov random field (MRF) model in a fuzzy domain. Three optimization algorithms in the FMRF model, i.e. Lagrange multiplier (LM), iterated conditional mode (ICM), and simulated annealing (SA), are compared with respect to the computational cost and segmentation accuracy. The results have shown that the FMRF model-based ICM algorithm balances the computational cost and segmentation accuracy in land-cover segmentation from LIDAR data and co-registered bands.
{"title":"Optimization algorithms in FMRF model-based segmentation for LIDAR data and co-registered bands","authors":"Yang Cao, Hong Wei, Huijie Zhao","doi":"10.1109/PRRS.2008.4783166","DOIUrl":"https://doi.org/10.1109/PRRS.2008.4783166","url":null,"abstract":"In this paper, a fuzzy Markov random field (FMRF) model is used to segment land-objects into tree, grass, building, and road regions by fusing remotely sensed LIDAR data and co-registered color bands, i.e. scanned aerial color (RGB) photo and near infra-red (NIR) photo. An FMRF model is defined as a Markov random field (MRF) model in a fuzzy domain. Three optimization algorithms in the FMRF model, i.e. Lagrange multiplier (LM), iterated conditional mode (ICM), and simulated annealing (SA), are compared with respect to the computational cost and segmentation accuracy. The results have shown that the FMRF model-based ICM algorithm balances the computational cost and segmentation accuracy in land-cover segmentation from LIDAR data and co-registered bands.","PeriodicalId":315798,"journal":{"name":"2008 IAPR Workshop on Pattern Recognition in Remote Sensing (PRRS 2008)","volume":"153 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132489226","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 : 2008-12-01DOI: 10.1109/PRRS.2008.4783169
S. Grauer-Gray, C. Kambhamettu, K. Palaniappan
This paper describes an efficient CUDA-based GPU implementation of the belief propagation algorithm that can be used to speed up stereo image processing and motion tracking calculations without loss of accuracy. Preliminary results in using belief propagation to analyze satellite images of hurricane Luis for real-time cloud structure and tracking are promising with speed-ups of nearly a factor of five.
{"title":"GPU implementation of belief propagation using CUDA for cloud tracking and reconstruction","authors":"S. Grauer-Gray, C. Kambhamettu, K. Palaniappan","doi":"10.1109/PRRS.2008.4783169","DOIUrl":"https://doi.org/10.1109/PRRS.2008.4783169","url":null,"abstract":"This paper describes an efficient CUDA-based GPU implementation of the belief propagation algorithm that can be used to speed up stereo image processing and motion tracking calculations without loss of accuracy. Preliminary results in using belief propagation to analyze satellite images of hurricane Luis for real-time cloud structure and tracking are promising with speed-ups of nearly a factor of five.","PeriodicalId":315798,"journal":{"name":"2008 IAPR Workshop on Pattern Recognition in Remote Sensing (PRRS 2008)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125854774","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 : 2008-12-01DOI: 10.1109/PRRS.2008.4783164
A. Wong, David A Clausi
A robust method for registering inter-band and inter-sensor remote sensing images has been designed and implemented. The proposed method introduces noise-resilient and contrast invariant control point detection and control point matching schemes based on robust complex wavelet feature representations. Furthermore, an iterative refinement scheme is introduced for achieving improved control point pair localization and mapping function estimation between the images being registered. The registration accuracy of the proposed method was demonstrated on the registration of multi-spectral optical and synthetic aperture radar (SAR) images. The proposed method achieves better registration accuracy when compared with the state-of-the-art MSSD and ARRSI registration algorithms.
{"title":"Automatic registration of inter-band and inter-sensor images using robust complex wavelet feature representations","authors":"A. Wong, David A Clausi","doi":"10.1109/PRRS.2008.4783164","DOIUrl":"https://doi.org/10.1109/PRRS.2008.4783164","url":null,"abstract":"A robust method for registering inter-band and inter-sensor remote sensing images has been designed and implemented. The proposed method introduces noise-resilient and contrast invariant control point detection and control point matching schemes based on robust complex wavelet feature representations. Furthermore, an iterative refinement scheme is introduced for achieving improved control point pair localization and mapping function estimation between the images being registered. The registration accuracy of the proposed method was demonstrated on the registration of multi-spectral optical and synthetic aperture radar (SAR) images. The proposed method achieves better registration accuracy when compared with the state-of-the-art MSSD and ARRSI registration algorithms.","PeriodicalId":315798,"journal":{"name":"2008 IAPR Workshop on Pattern Recognition in Remote Sensing (PRRS 2008)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114227552","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：