We present RaveGrid, a software that efficiently converts a raster image to a scalable vector image comprised of polygons whose boundaries conform to the edges in the image. The resulting vector image has good visual quality and fidelity and can be displayed at various sizes and on various display screen resolutions. The software can render vector images in the SVG (scalable vector graphics) format or in EPS (Encapsulated Postscript). The ubiquity of image data in graphics, on the Web, and in communications, as well as the wide range of devices, from big screen TVs to hand-held cellular phones that support image display, calls for a scalable and more manipulable representation of imagery. Moreover, with the growing need for automating image-based search, object recognition, and image understanding, it is desirable to represent image content at a semantically higher level by means of tokens that support computer vision tasks.
{"title":"Rapid Automated Polygonal Image Decomposition","authors":"S. Swaminarayan, Lakshman Prasad","doi":"10.1109/AIPR.2006.30","DOIUrl":"https://doi.org/10.1109/AIPR.2006.30","url":null,"abstract":"We present RaveGrid, a software that efficiently converts a raster image to a scalable vector image comprised of polygons whose boundaries conform to the edges in the image. The resulting vector image has good visual quality and fidelity and can be displayed at various sizes and on various display screen resolutions. The software can render vector images in the SVG (scalable vector graphics) format or in EPS (Encapsulated Postscript). The ubiquity of image data in graphics, on the Web, and in communications, as well as the wide range of devices, from big screen TVs to hand-held cellular phones that support image display, calls for a scalable and more manipulable representation of imagery. Moreover, with the growing need for automating image-based search, object recognition, and image understanding, it is desirable to represent image content at a semantically higher level by means of tokens that support computer vision tasks.","PeriodicalId":375571,"journal":{"name":"35th IEEE Applied Imagery and Pattern Recognition Workshop (AIPR'06)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115632313","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}
The Performance Metrics for Intelligent Systems (PerMIS 2006) workshop was held during August 21-23, 2006 at the National Institute of Standards and Technology (NIST) in Gaithersburg, Maryland, USA. The PerMIS series (the current workshop is the sixth) is targeted at defining measures and methodologies of evaluating performance of intelligent systems. PerMIS 2006 focused on applications of performance measures to practical problems in commercial, industrial, homeland security, and military applications. An important element of overall performance evaluation is that of assessing the technical maturity of a given technology or system. One approach for accomplishing this is known as technology readiness level (TRL) assesment. TRL evaluations have been the focus of past PerMIS workshops and continue to be a foundational theme. This paper will provide an overview of the workshop and various topics that are closely related to the theme of the AIPR workshop.
{"title":"Performance Metrics for Intelligent Systems (PerMIS) 2006Workshop: Summary and Review","authors":"R. Madhavan, E. Messina","doi":"10.1109/AIPR.2006.29","DOIUrl":"https://doi.org/10.1109/AIPR.2006.29","url":null,"abstract":"The Performance Metrics for Intelligent Systems (PerMIS 2006) workshop was held during August 21-23, 2006 at the National Institute of Standards and Technology (NIST) in Gaithersburg, Maryland, USA. The PerMIS series (the current workshop is the sixth) is targeted at defining measures and methodologies of evaluating performance of intelligent systems. PerMIS 2006 focused on applications of performance measures to practical problems in commercial, industrial, homeland security, and military applications. An important element of overall performance evaluation is that of assessing the technical maturity of a given technology or system. One approach for accomplishing this is known as technology readiness level (TRL) assesment. TRL evaluations have been the focus of past PerMIS workshops and continue to be a foundational theme. This paper will provide an overview of the workshop and various topics that are closely related to the theme of the AIPR workshop.","PeriodicalId":375571,"journal":{"name":"35th IEEE Applied Imagery and Pattern Recognition Workshop (AIPR'06)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126617035","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}
Operational real time hyperspectral reconnaissance systems adaptively estimate multivariate background statistics. Parameter values derived from these estimates feed autonomous onboard detection systems. However, inadequate adaptation occurs whenever an airborne sensor encounters a physical boundary between spectrally distinct regions. The transition area generates excessive false alarms, because standard detection algorithms rely on quasi- stationary models of background statistics. Here we describe a two-mode stochastic mixture model aimed at solving the boundary problem. It exploits deployed signal processing modules to solve a generalized eigenvalue problem, making a threshold test for targets computationally feasible.
{"title":"Autonomous Hyperspectral Target Detection with Quasi-Stationarity Violation at Background Boundaries","authors":"A. Schaum","doi":"10.1109/AIPR.2006.18","DOIUrl":"https://doi.org/10.1109/AIPR.2006.18","url":null,"abstract":"Operational real time hyperspectral reconnaissance systems adaptively estimate multivariate background statistics. Parameter values derived from these estimates feed autonomous onboard detection systems. However, inadequate adaptation occurs whenever an airborne sensor encounters a physical boundary between spectrally distinct regions. The transition area generates excessive false alarms, because standard detection algorithms rely on quasi- stationary models of background statistics. Here we describe a two-mode stochastic mixture model aimed at solving the boundary problem. It exploits deployed signal processing modules to solve a generalized eigenvalue problem, making a threshold test for targets computationally feasible.","PeriodicalId":375571,"journal":{"name":"35th IEEE Applied Imagery and Pattern Recognition Workshop (AIPR'06)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128000779","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}
The objective of this research is to automatically detect and locate devices-of-interest (DOI) in x-ray images, even if partially obscured by devices of no interest, using a new ALISA Component Module. This preliminary study was performed using a single DOI, a 9mm Colt Beretta, but the solution method can easily accommodate other DOIs. Results obtained in real-time (a few seconds) revealed a robust and accurate classifier that could easily assist security personnel at the defined venue: carry-on luggage x-ray machines in airports. This research project was funded by the defense threat reduction agency (DTRA).
{"title":"Identification of Objects-of-Interest in X-Ray Images","authors":"Carsten K. Oertel, P. Bock","doi":"10.1109/AIPR.2006.25","DOIUrl":"https://doi.org/10.1109/AIPR.2006.25","url":null,"abstract":"The objective of this research is to automatically detect and locate devices-of-interest (DOI) in x-ray images, even if partially obscured by devices of no interest, using a new ALISA Component Module. This preliminary study was performed using a single DOI, a 9mm Colt Beretta, but the solution method can easily accommodate other DOIs. Results obtained in real-time (a few seconds) revealed a robust and accurate classifier that could easily assist security personnel at the defined venue: carry-on luggage x-ray machines in airports. This research project was funded by the defense threat reduction agency (DTRA).","PeriodicalId":375571,"journal":{"name":"35th IEEE Applied Imagery and Pattern Recognition Workshop (AIPR'06)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131875384","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}
A. Perera, A. Hoogs, C. Srinivas, G. Brooksby, Wensheng Hu
As video tracking research matures, the issue of tracker performance evaluation has emerged as a research topic in its own right, as evidenced by a series of workshops devoted solely to this purpose (the workshops on performance evaluation of tracking and surveillance-PETS). However, evaluations such as PETS have been limited to small scenarios with a handful of moving objects. In this paper, we present an evaluation methodology and set of experiments focused on large-scale video tracking problems with hundreds of objects in close proximity. The scale and complexity of this data exposes a number of issues. First, the association of computed tracks to image-truth tracks may have multiple plausible solutions, resulting in a combinatorial grouping problem that must be solved with an approximate solution. Second, computed tracks may be only partially correct, complicating the association problem further and indicating that multiple measures are required to characterize performance. We have created a system that associates computed tracks to manually-generated image-truth tracks, and calculates various measures such as the per-frame probability of detection, false alarm rate, and fragmentation, which is the number of computed tracks associated to a single track. We also normalize fragmentation by track length to reward fewer computed tracks for longer true tracks. The measures were used to compare three tracking methods on an aerial video sequence containing hundreds of objects, long occlusions, and deep shadows.
{"title":"Evaluation of Algorithms for Tracking Multiple Objects in Video","authors":"A. Perera, A. Hoogs, C. Srinivas, G. Brooksby, Wensheng Hu","doi":"10.1109/AIPR.2006.23","DOIUrl":"https://doi.org/10.1109/AIPR.2006.23","url":null,"abstract":"As video tracking research matures, the issue of tracker performance evaluation has emerged as a research topic in its own right, as evidenced by a series of workshops devoted solely to this purpose (the workshops on performance evaluation of tracking and surveillance-PETS). However, evaluations such as PETS have been limited to small scenarios with a handful of moving objects. In this paper, we present an evaluation methodology and set of experiments focused on large-scale video tracking problems with hundreds of objects in close proximity. The scale and complexity of this data exposes a number of issues. First, the association of computed tracks to image-truth tracks may have multiple plausible solutions, resulting in a combinatorial grouping problem that must be solved with an approximate solution. Second, computed tracks may be only partially correct, complicating the association problem further and indicating that multiple measures are required to characterize performance. We have created a system that associates computed tracks to manually-generated image-truth tracks, and calculates various measures such as the per-frame probability of detection, false alarm rate, and fragmentation, which is the number of computed tracks associated to a single track. We also normalize fragmentation by track length to reward fewer computed tracks for longer true tracks. The measures were used to compare three tracking methods on an aerial video sequence containing hundreds of objects, long occlusions, and deep shadows.","PeriodicalId":375571,"journal":{"name":"35th IEEE Applied Imagery and Pattern Recognition Workshop (AIPR'06)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114712279","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}
Conventional RF image formation relies on a fixed waveform set that is based largely on obtaining maximum resolution for a given amount of bandwidth present in a waveform. However, the correlation process for a given waveform set varies widely depending on the cross correlation properties of the waveform and the geometry of the aperture interrogating the object to be imaged. We propose a method that maximizes quality of the imagery being reconstructed based by first using an orthogonal basis to minimize the unwanted correlation response for the waveform. We then shape the frequency and temporal correlation response of the waveform for a given target using a rate distortion criteria and demonstrate the performance of the method.
{"title":"A Rate Distortion Method for Beamforming in RF Image Formation","authors":"R. Bonneau","doi":"10.1109/AIPR.2006.7","DOIUrl":"https://doi.org/10.1109/AIPR.2006.7","url":null,"abstract":"Conventional RF image formation relies on a fixed waveform set that is based largely on obtaining maximum resolution for a given amount of bandwidth present in a waveform. However, the correlation process for a given waveform set varies widely depending on the cross correlation properties of the waveform and the geometry of the aperture interrogating the object to be imaged. We propose a method that maximizes quality of the imagery being reconstructed based by first using an orthogonal basis to minimize the unwanted correlation response for the waveform. We then shape the frequency and temporal correlation response of the waveform for a given target using a rate distortion criteria and demonstrate the performance of the method.","PeriodicalId":375571,"journal":{"name":"35th IEEE Applied Imagery and Pattern Recognition Workshop (AIPR'06)","volume":"1 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120844714","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}
Remotely sensed images from satellite sensors such as MODIS Aqua and Terra provide high temporal resolution and wide area coverage. Unfortunately, these images frequently include undesired cloud and water cover. Areas of cloud or water cover preclude analysis and interpretation of terrestrial land cover, vegetation vigor, and/or analysis of change. Cross platform multi-temporal image compositing techniques may be employed to create daily synthetic cloud free images using fused images from Aqua and Terra MODIS satellite images, and then creating a composite that includes representative values derived from a set of possibly cloudy satellite images collected during a given longer time period of interest. Spatio-temporal analytical processing methods that utilize moderate spatial resolution satellite imagery with high temporal resolution to create multi-temporal composites are data intensive and computationally intensive. Therefore, a study of the strategies using high performance parallel solutions is required. This research focuses on analyzing the fusion, de-noising, filtering, and compositing strategies for vegetation indices using parallel temporal map algebra. The report provides objective findings on methods and the relative benefits observed from various analysis methods and parallelization strategies.
{"title":"Data Fusion, De-noising, and Filtering to Produce Cloud-Free High Quality Temporal Composites Employing Parallel Temporal Map Algebra","authors":"B. Shrestha, C. O'Hara, P. Mali","doi":"10.1109/AIPR.2006.20","DOIUrl":"https://doi.org/10.1109/AIPR.2006.20","url":null,"abstract":"Remotely sensed images from satellite sensors such as MODIS Aqua and Terra provide high temporal resolution and wide area coverage. Unfortunately, these images frequently include undesired cloud and water cover. Areas of cloud or water cover preclude analysis and interpretation of terrestrial land cover, vegetation vigor, and/or analysis of change. Cross platform multi-temporal image compositing techniques may be employed to create daily synthetic cloud free images using fused images from Aqua and Terra MODIS satellite images, and then creating a composite that includes representative values derived from a set of possibly cloudy satellite images collected during a given longer time period of interest. Spatio-temporal analytical processing methods that utilize moderate spatial resolution satellite imagery with high temporal resolution to create multi-temporal composites are data intensive and computationally intensive. Therefore, a study of the strategies using high performance parallel solutions is required. This research focuses on analyzing the fusion, de-noising, filtering, and compositing strategies for vegetation indices using parallel temporal map algebra. The report provides objective findings on methods and the relative benefits observed from various analysis methods and parallelization strategies.","PeriodicalId":375571,"journal":{"name":"35th IEEE Applied Imagery and Pattern Recognition Workshop (AIPR'06)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133626963","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}
An adaptive thresholding method used to distinguish cell boundaries in a given image is presented in this paper. A preprocessing step involves low pass filtering of the image to remove high frequency noise seen in the image. This image is now adaptively thresholded to create a binary image. The bright regions are further analyzed based on their geometrical descriptors such as area and form factor to classify them as cell or non-cell regions. Two sets of images, pulsed and non-pulsed, are available, which can be compared to determine the efficiency of the pulsing. Results for automatic segmentation are compared with those of manually obtained values to determine its efficiency.
{"title":"Adaptive Thresholding Based Cell Segmentation for Cell-Destruction Activity Verification","authors":"P. Sankaran, V. Asari","doi":"10.1109/AIPR.2006.9","DOIUrl":"https://doi.org/10.1109/AIPR.2006.9","url":null,"abstract":"An adaptive thresholding method used to distinguish cell boundaries in a given image is presented in this paper. A preprocessing step involves low pass filtering of the image to remove high frequency noise seen in the image. This image is now adaptively thresholded to create a binary image. The bright regions are further analyzed based on their geometrical descriptors such as area and form factor to classify them as cell or non-cell regions. Two sets of images, pulsed and non-pulsed, are available, which can be compared to determine the efficiency of the pulsing. Results for automatic segmentation are compared with those of manually obtained values to determine its efficiency.","PeriodicalId":375571,"journal":{"name":"35th IEEE Applied Imagery and Pattern Recognition Workshop (AIPR'06)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134074627","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}
The application development framework (ADF) provided developers with a unique environment that supported the rapid integration and testing of image processing algorithms on high performance computers (HPCs). Using object-oriented middleware for the base of the system, along with Web technologies, allowed considerable flexibility in extending the system to a broad range of system development tools and components. The pub/sub system at the core of the ADF was the foundation that provided rapid system integration.
{"title":"Application Development Framework for the Rapid Integration of High Performance Image Processing Algorithms","authors":"S. Spetka, G. Ramseyer, R. Linderman","doi":"10.1109/AIPR.2006.15","DOIUrl":"https://doi.org/10.1109/AIPR.2006.15","url":null,"abstract":"The application development framework (ADF) provided developers with a unique environment that supported the rapid integration and testing of image processing algorithms on high performance computers (HPCs). Using object-oriented middleware for the base of the system, along with Web technologies, allowed considerable flexibility in extending the system to a broad range of system development tools and components. The pub/sub system at the core of the ADF was the foundation that provided rapid system integration.","PeriodicalId":375571,"journal":{"name":"35th IEEE Applied Imagery and Pattern Recognition Workshop (AIPR'06)","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115818151","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}
The National Institute of Standards and Technology is involved in developing standard protocols for the performance evaluation of 3D imaging systems, which include laser scanners and LADARs (laser detection and ranging). A LADAR is an optical device that typically yields voluminous 3D "point clouds" by scanning scenes. In many applications, a model of an object which is present in the scene has been specified, and the task amounts to recovering this object from scan data. Specifically, the recovery of spheres from point clouds will be addressed, aiming at estimating the location of their centers and, if not known beforehand, their radii. This information can be used, for instance, to "register "LADAR data to a specified coordinate frame. Two experiments recovering spheres based on best-fitting data points are reported. Sphere fitting based on orthogonal least squares is compared to a novel approach, minimizing instead the squares of range errors incurred in the direction of the scan.
{"title":"Recovering Spheres from 3D Point Data","authors":"C. Witzgall, G. Cheok, Anthony J. Kearsley","doi":"10.1109/AIPR.2006.33","DOIUrl":"https://doi.org/10.1109/AIPR.2006.33","url":null,"abstract":"The National Institute of Standards and Technology is involved in developing standard protocols for the performance evaluation of 3D imaging systems, which include laser scanners and LADARs (laser detection and ranging). A LADAR is an optical device that typically yields voluminous 3D \"point clouds\" by scanning scenes. In many applications, a model of an object which is present in the scene has been specified, and the task amounts to recovering this object from scan data. Specifically, the recovery of spheres from point clouds will be addressed, aiming at estimating the location of their centers and, if not known beforehand, their radii. This information can be used, for instance, to \"register \"LADAR data to a specified coordinate frame. Two experiments recovering spheres based on best-fitting data points are reported. Sphere fitting based on orthogonal least squares is compared to a novel approach, minimizing instead the squares of range errors incurred in the direction of the scan.","PeriodicalId":375571,"journal":{"name":"35th IEEE Applied Imagery and Pattern Recognition Workshop (AIPR'06)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125878024","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：