2010 IEEE 39th Applied Imagery Pattern Recognition Workshop (AIPR)最新文献_第2页

Real-time adaptive pixel replacement 实时自适应像素替换

2010 IEEE 39th Applied Imagery Pattern Recognition Workshop (AIPR) Pub Date : 2010-10-01 DOI: 10.1109/AIPR.2010.5759720

M. Pusateri, J. Scott, Muhammad Umar Mushtaq

{"title":"Real-time adaptive pixel replacement","authors":"M. Pusateri, J. Scott, Muhammad Umar Mushtaq","doi":"10.1109/AIPR.2010.5759720","DOIUrl":"https://doi.org/10.1109/AIPR.2010.5759720","url":null,"abstract":"Scintillation noise artifacts are a part of intensified imagery for both analog and digital sensors. The high intensity flashes are similar to classic “salt” noise although they often are multiple pixels in extent; they can prove very distracting when utilizing intensified imagery under stressful conditions. In stereo intensified vision system, the fact that artifacts occur at different locations in the left and right sensor increases their ability to distract. Digital intensified sensors are not immune from this problem; however, digital image processing gives us an opportunity to mitigate the problem. A 3×3 median filter is the classic suggested solution to “salt” noise. However, the multiple pixel extent of scintillation noise requires the median neighborhood to be increased to 5×5 for effective suppression. Unfortunately, median also introduces a low pass effect that smoothes the imagery to an unacceptable degree. To overcome this loss of image clarity, we have developed and implemented an adaptive algorithm that is designed to identify scintillation noise. Scintillated pixels are replaced using the 5×5 median while unaffected pixels are left unchanged. The algorithm was tested on a Xilinx XC6SLX150–3 and is capable of operating at a pixel clock of over 220 MHz. With a pixel clock of 140 MHz and a 60 Hz frame rate, the module latency is under 26 µs. We discuss the identification of scintillated pixels and will comparing frames from the raw video, the 5×5 median video and the adaptively replaced 5×5 median.","PeriodicalId":128378,"journal":{"name":"2010 IEEE 39th Applied Imagery Pattern Recognition Workshop (AIPR)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133022454","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

Comparing one-class and two-class SVM classifiers for normal mammogram detection 一类与二类SVM分类器在正常乳房x光检测中的比较

2010 IEEE 39th Applied Imagery Pattern Recognition Workshop (AIPR) Pub Date : 2010-10-01 DOI: 10.1109/AIPR.2010.5759708

M. Elshinawy, Abdel-Hameed A. Badawy, Wael W. Abdelmageed, M. Chouikha

{"title":"Comparing one-class and two-class SVM classifiers for normal mammogram detection","authors":"M. Elshinawy, Abdel-Hameed A. Badawy, Wael W. Abdelmageed, M. Chouikha","doi":"10.1109/AIPR.2010.5759708","DOIUrl":"https://doi.org/10.1109/AIPR.2010.5759708","url":null,"abstract":"X-ray mammograms are one of the most common techniques used by radiologists for breast cancer detection and diagnosis. Early detection is important, which raised the importance of developing Computer-Aided Detection and Diag-nosis(CAD) systems. Although most(CAD)systems were designed to help radiologists in their diagnosis by providing useful insight, the accuracy of CAD systems remains below the level that would lead to an improvement in the overall radiologists' performance. Unlike other CAD systems who aim to detect abnormal mammograms, we are designing a pre-CAD system that aims to detect normal mammograms instead of abnormal ones. The pre-CAD system works as a \"first look\" and screens-out normal mammograms, leaving the radiologists and other conventional CAD systems to focus on the suspicious cases. Support Vector Machine classifiers are used to detect normal mammograms. We are comparing the effect of using 1-class and 2-class SVMs when normal mammogram, instead of abnormal, is detected. Results showed that our pre-CAD system performance for 1-class outperformed 2-class SVM classifiers almost always. Using our set of features, 1-class SVM achieved a specificity of (99.2%), while the two-class SVM achieved (86.71%) respectively.","PeriodicalId":128378,"journal":{"name":"2010 IEEE 39th Applied Imagery Pattern Recognition Workshop (AIPR)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117276513","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 8

Automated cross-sensor registration, orthorectification and geopositioning using LIDAR digital elevation models 使用激光雷达数字高程模型进行自动交叉传感器配准、正校正和地理定位

2010 IEEE 39th Applied Imagery Pattern Recognition Workshop (AIPR) Pub Date : 2010-10-01 DOI: 10.1109/AIPR.2010.5759694

M. D. Pritt, Michael Gribbons, Kevin J. LaTourette

{"title":"Automated cross-sensor registration, orthorectification and geopositioning using LIDAR digital elevation models","authors":"M. D. Pritt, Michael Gribbons, Kevin J. LaTourette","doi":"10.1109/AIPR.2010.5759694","DOIUrl":"https://doi.org/10.1109/AIPR.2010.5759694","url":null,"abstract":"Cross-sensor image registration, orthorectification, and geopositioning of imagery are well-known problems whose solutions are difficult, if not impossible, to automate. Registration of radar to optical imagery typically requires a manual solution, as does the registration of imagery over rugged terrain or urban areas, where foreshortening and layover present formidable obstacles to successful automation. We have developed an automated solution that is based on the registration of imagery to high-precision digital elevation models (DEMs) derived from Lidar data. The key idea is the generation of a simulated image using Lidar data, the image camera model and the illumination conditions. The simulated image is then registered to the actual image with normalized cross-correlation methods. The result is an effective and completely automated technique for registering imagery to DEMs. It has been shown to work with BuckEye Lidar, ALIRT Lidar, commercial satellite imagery and commercial synthetic aperture radar imagery over diverse terrain types, including mountains, cities, and forests. It provides an automated solution to many difficult geospatial problems, including cross-sensor registration of radar and optical imagery, image registration over rugged terrain, geopositioning of imagery and orthorectification. Its use of Lidar enables it to handle three-dimensional features that are foreshortened or laid over in different directions. Its use of simulated imagery enables it to bypass the problem of disparate features in cross-sensor registration. Statistical analyses of the registration accuracy are presented along with results on commercial satellite imagery and Lidar data over Iraq, Afghanistan, Haiti and the U.S.","PeriodicalId":128378,"journal":{"name":"2010 IEEE 39th Applied Imagery Pattern Recognition Workshop (AIPR)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114989322","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: 12

Supervised semantic classification for nuclear proliferation monitoring 用于核扩散监测的监督语义分类

2010 IEEE 39th Applied Imagery Pattern Recognition Workshop (AIPR) Pub Date : 2010-10-01 DOI: 10.1109/AIPR.2010.5759712

Ranga Raju Vatsavai, A. Cheriyadat, S. Gleason

引用次数: 7

Evaluation of ISR technologies for counter insurgency warfare 反叛乱战争ISR技术评估

2010 IEEE 39th Applied Imagery Pattern Recognition Workshop (AIPR) Pub Date : 2010-10-01 DOI: 10.1109/AIPR.2010.5759681

S. Israel

引用次数: 2

Standoff video analysis for the detection of security anomalies in vehicles 对峙视频分析，用于检测车辆中的安全异常

2010 IEEE 39th Applied Imagery Pattern Recognition Workshop (AIPR) Pub Date : 2010-10-01 DOI: 10.1109/AIPR.2010.5759685

S. Srivastava, E. Delp

{"title":"Standoff video analysis for the detection of security anomalies in vehicles","authors":"S. Srivastava, E. Delp","doi":"10.1109/AIPR.2010.5759685","DOIUrl":"https://doi.org/10.1109/AIPR.2010.5759685","url":null,"abstract":"Video surveillance systems are commonly used by security personnel to monitor and record activity in buildings, public gatherings, busy roads, and parking lots. These systems allow many cameras to be observed by a small number of trained human operators but suffer from potential operator fatigue and lack of attention due to the large amount of information provided by cameras which can distract the operator from focusing on important events. In this paper, we propose the design of an autonomous video surveillance system which can operate from a standoff range that analyzes approaching vehicles in order to detect security anomalies. Such anomalies, based on dynamic analysis of the vehicle tracks, include unexpected slowing/stopping or sudden acceleration, particularly near check points or critical structures (e.g. government buildings). A human supervisor can be alerted whenever a significant event is detected and can then determine if the vehicle should be further inspected. Besides dynamic analysis, the system also estimates physical information about the vehicles such as make, body type and tire size. We describe low-complexity techniques to obtain the above information from two cameras.","PeriodicalId":128378,"journal":{"name":"2010 IEEE 39th Applied Imagery Pattern Recognition Workshop (AIPR)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121116827","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 9

Histo-pathological image analysis using OS-FCM and level sets 使用OS-FCM和水平集进行组织病理图像分析

2010 IEEE 39th Applied Imagery Pattern Recognition Workshop (AIPR) Pub Date : 2010-10-01 DOI: 10.1109/AIPR.2010.5759688

M. Babu, V. Madasu, M. Hanmandlu, S. Vasikarla

引用次数: 8

Prediction of satellite images using fuzzy rule based Gaussian regression 基于模糊规则的高斯回归卫星图像预测

2010 IEEE 39th Applied Imagery Pattern Recognition Workshop (AIPR) Pub Date : 2010-10-01 DOI: 10.1109/AIPR.2010.5759679

N. Verma, N. Pal

引用次数: 13

An adaptive parameterization method for SIFT based video stabilization 基于SIFT的视频稳像自适应参数化方法

2010 IEEE 39th Applied Imagery Pattern Recognition Workshop (AIPR) Pub Date : 2010-10-01 DOI: 10.1109/AIPR.2010.5759711

V. Santhaseelan, V. Asari

{"title":"An adaptive parameterization method for SIFT based video stabilization","authors":"V. Santhaseelan, V. Asari","doi":"10.1109/AIPR.2010.5759711","DOIUrl":"https://doi.org/10.1109/AIPR.2010.5759711","url":null,"abstract":"Video stabilization is used to eliminate unwanted shakiness in video caused by movement of the camera. This can be achieved by estimating the motion of the camera, filtering out the high frequency components in the motion path and warping the video frames in order to compensate for the motion. In this paper, an adaptive parameterization technique is proposed to define the characteristics of the filter used to eliminate high frequency components in the motion path. Scale Invariant Feature Transform (SIFT) is used to extract the features from each video frame. A string of transformation matrices is used to represent the motion of the camera. For any frame that has to be stabilized, only a few frames in the local neighborhood are considered to calculate the required amount of motion compensation. The high-frequency components in camera motion are eliminated using a zero-mean Gaussian filter. The variance of the Gaussian filter that defines the amount of smoothening is computed automatically from the camera motion path. This is based on the observation that the variation in the individual components in the transformation matrices correlates with the amount of instability in the video. The proposed approach has been found to be effective irrespective of the presence of moving objects in the video.","PeriodicalId":128378,"journal":{"name":"2010 IEEE 39th Applied Imagery Pattern Recognition Workshop (AIPR)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134131005","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 9

Algorithms with attitude 带有姿态的算法

2010 IEEE 39th Applied Imagery Pattern Recognition Workshop (AIPR) Pub Date : 2010-10-01 DOI: 10.1109/AIPR.2010.5759683

A. Schaum

引用次数: 22