2015 IEEE Applied Imagery Pattern Recognition Workshop (AIPR)最新文献_第3页

Parallel photon mapping computations to enable fast approximate solutions to the art gallery and watchman route problems 并行光子映射计算，使快速近似解决艺术画廊和守望者路线问题

2015 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) Pub Date : 2015-10-01 DOI: 10.1109/AIPR.2015.7444524

B. A. Johnson, Vatana An, J. Isaacs

{"title":"Parallel photon mapping computations to enable fast approximate solutions to the art gallery and watchman route problems","authors":"B. A. Johnson, Vatana An, J. Isaacs","doi":"10.1109/AIPR.2015.7444524","DOIUrl":"https://doi.org/10.1109/AIPR.2015.7444524","url":null,"abstract":"The art gallery and watchman route problems (AGP and WRP) are NP-hard constrained optimization problems concerned with providing static and dynamic sensing, respectively, to environments such that the maximum amount of information is sensed at a minimal cost. What being an NP-hard problem means, practically, is that when an AGP or WRP solution is calculated for a particular time step t, any small change in the environment requires that an entirely new solution must be computed. Extending 3D AGP- and WRP-solving computations into 4D (i.e. considering time's effects on the solutions generated) means that a large number of computational resources would be consumed if the updates to the AGP and WRP solutions are performed serially - since each time step's solution would be computed sequentially. Our particular AGP- and WRP-solving algorithms are built upon the photon mapping algorithm in order to model the information obtainable in the sensed environment. The photon mapping algorithm models the propagation of multispectral photons through an environment and stores the result of the photons' interaction with their environment in a k-d tree data structure called a photon map. Since each virtual photon can operate independently of every other virtual photon, a photon map generated at a particular time step t can be generated independently of every other photon map populated at every other time step using a graphics processing unit (GPU). Thus given an n-sized time sequence, a photon map can be populated by each member of an n-core GPU. Once the photon map is updated, our AGP/WRP-solving algorithms can be executed in parallel over the time sequence using the particular core assigned to a photon map's population. We present the results of our computations and compare both serial- and GPU-based performance.","PeriodicalId":440673,"journal":{"name":"2015 IEEE Applied Imagery Pattern Recognition Workshop (AIPR)","volume":"358 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122812687","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

ROC curve analysis for validating objective image fusion metrics ROC曲线分析验证客观图像融合指标

2015 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) Pub Date : 2015-10-01 DOI: 10.1109/AIPR.2015.7444531

Neal Messer, Soundararajan Ezekiel, M. Ferris, E. Blasch, M. Alford, Maria Scalzo-Cornacchia, A. Bubalo

{"title":"ROC curve analysis for validating objective image fusion metrics","authors":"Neal Messer, Soundararajan Ezekiel, M. Ferris, E. Blasch, M. Alford, Maria Scalzo-Cornacchia, A. Bubalo","doi":"10.1109/AIPR.2015.7444531","DOIUrl":"https://doi.org/10.1109/AIPR.2015.7444531","url":null,"abstract":"Image fusion is a process that allows for the synthesis of information from multiple source images into a single image. There are many applications for image fusion including night vision, medical imaging, and remote sensing. Over the many applications, numerous image fusion algorithms have been explored from averaging pixel intensities to fusion through multi-resolution decomposition transforms such as the wavelet or contourlet. Objective evaluation of a given image fusion method is still a major challenge especially when there exists no reference image. Existing no-reference objective fusion metrics include information theory based metrics, image feature based metrics, and structural similarity metrics. However there has been very little work done in validating which objective metric best evaluates a given image fusion algorithm. Receiver operating characteristic (ROC) curves and the area under the curve (AUC) provide a viable validation method for metric selection. This study focuses on validating objective fusion metrics over mutual information, spatial frequency, and structural similarity Index Measure (SSIM) used to evaluate fusion algorithms for denoising applications.","PeriodicalId":440673,"journal":{"name":"2015 IEEE Applied Imagery Pattern Recognition Workshop (AIPR)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125453153","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Indexing open imagery to create tools to fight sex trafficking 索引公开图像，创建打击性交易的工具

2015 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) Pub Date : 2015-10-01 DOI: 10.1109/AIPR.2015.7444535

Abby Stylianou, Abigail Norling-Ruggles, Richard Souvenir, Robert Pless

引用次数: 7

Seeing the Earth in the Cloud: Processing one petabyte of satellite imagery in one day 从云端看地球:一天处理1拍字节的卫星图像

2015 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) Pub Date : 2015-10-01 DOI: 10.1109/AIPR.2015.7444536

Michael S. Warren, S. Brumby, S. Skillman, T. Kelton, B. Wohlberg, M. Mathis, R. Chartrand, R. Keisler, M. Johnson

{"title":"Seeing the Earth in the Cloud: Processing one petabyte of satellite imagery in one day","authors":"Michael S. Warren, S. Brumby, S. Skillman, T. Kelton, B. Wohlberg, M. Mathis, R. Chartrand, R. Keisler, M. Johnson","doi":"10.1109/AIPR.2015.7444536","DOIUrl":"https://doi.org/10.1109/AIPR.2015.7444536","url":null,"abstract":"The proliferation of transistors has increased the performance of computing systems by over a factor of a million in the past 30 years, and is also dramatically increasing the amount of data in existence, driving improvements in sensor, communication and storage technology. Multi-decadal Earth and planetary remote sensing global datasets at the petabyte (8×1015 bits) scale are now available in commercial clouds (e.g., Google Earth Engine and Amazon NASA NEX), and new commercial satellite constellations are planning to generate petabytes of images per year, providing daily global coverage at a few meters per pixel. Cloud storage with adjacent high-bandwidth compute, combined with recent advances in machine learning for computer vision, is enabling understanding of the world at a scale and at a level of granularity never before feasible. We report here on a computation processing over a petabyte of compressed raw data from 2.8 quadrillion pixels (2.8 petapixels) acquired by the US Landsat and MODIS programs over the past 40 years. Using commodity cloud computing resources, we convert the imagery to a calibrated, georeferenced, multiresolution tiled format suited for machine-learning analysis. We believe ours is the first application to process, in less than a day, on generally available resources, over a petabyte of scientific image data. We report on work using this reprocessed dataset for experiments demonstrating country-scale food production monitoring, an indicator for famine early warning. We apply remote sensing science and machine learning algorithms to detect and classify agricultural crops and then estimate crop yields.","PeriodicalId":440673,"journal":{"name":"2015 IEEE Applied Imagery Pattern Recognition Workshop (AIPR)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128038866","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: 21

Efficient dense reconstruction using geometry and image consistency constraints 使用几何和图像一致性约束的高效密集重建

2015 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) Pub Date : 2015-10-01 DOI: 10.1109/AIPR.2015.7444539

Mikhail M. Shashkov, J. Mak, S. Recker, Connie S. Nguyen, John Douglas Owens, K. Joy

引用次数: 1

Spectral ship surveillance from space 来自太空的光谱船监视

2015 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) Pub Date : 2015-10-01 DOI: 10.1109/AIPR.2015.7444548

A. Schaum, E. Allman, R. Leathers

引用次数: 4

The role of imaging in the detection, identification, and treatment of cancer 影像学在癌症的检测、鉴定和治疗中的作用

2015 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) Pub Date : 2015-10-01 DOI: 10.1109/AIPR.2015.7444525

E. Williams

{"title":"The role of imaging in the detection, identification, and treatment of cancer","authors":"E. Williams","doi":"10.1109/AIPR.2015.7444525","DOIUrl":"https://doi.org/10.1109/AIPR.2015.7444525","url":null,"abstract":"In April, 2015, I was diagnosed with Non-Hodgkin Lymphoma which is a blood cancer that attacks the lymph nodes. Having recently purchased a winter home in Clearwater, Florida, in early March, 2015, I did not have a doctor network established in Florida. After having lower abdominal pains for more than a week, I went to the emergency room (ER) at the local hospital. A CT scan was done of the lower abdomen, and I was told that my lymph nodes were enlarged. During the next five days in the hospital, I had three CT scans and a renal scan of the kidneys and urinary track. The third CT scan was used to guide a needle for a biopsy of an enlarged lymph node. Six days later my Oncologist informed me that I had Non-Hodgkin Lymphoma Large B cell rapid growing type of cancer. Over the next six days I had a MUGA Scan of the heart and a PET scan of the whole body. Seventeen days after going to the ER I started my first Chemotherapy treatment. Although I have little or no knowledge about medical imagery, I did spend almost forty years working for the Department of Defense researching imaging systems to detect small targets in a cluttered and noisy environment. I have also been attending the annual AIPR Workshops for more than 30 years. AIPR has been bringing together researchers from the Department of Defense, the medical community, and other application areas of imagery understanding. This paper will address some of the challenges of detecting and identifying cancer in the cluttered environment of the human body and the role of medical imaging systems that improve the survival rate of cancer patients. Imagery from the many scanning systems used to detect, identify, and monitor progress of treatment for my cancer will be shown and discussed. A history of the improving survival rate for Non-Hodgkin Lymphoma from 1960 to present and the role the imaging systems played in this improved survival rate will be discussed.","PeriodicalId":440673,"journal":{"name":"2015 IEEE Applied Imagery Pattern Recognition Workshop (AIPR)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116887730","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Comprehensive review of evolution of satellite sensor specifications against speedup performance of pattern recognition algorithms in remote sensing 遥感中模式识别算法加速性能下卫星传感器规格的演变综述

2015 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) Pub Date : 2015-10-01 DOI: 10.1109/AIPR.2015.7444540

B. Gokaraju, S. Bhushan, V. Anantharaj, A. Turlapaty, D. Doss

引用次数: 1

High Accuracy Optical Flow based future image frame predictor model 基于高精度光流的未来图像帧预测模型

2015 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) Pub Date : 2015-10-01 DOI: 10.1109/AIPR.2015.7444534

N. Verma, Eeshan Gunesh Dhekane, G. S. Rao, Aakansha Mishra

{"title":"High Accuracy Optical Flow based future image frame predictor model","authors":"N. Verma, Eeshan Gunesh Dhekane, G. S. Rao, Aakansha Mishra","doi":"10.1109/AIPR.2015.7444534","DOIUrl":"https://doi.org/10.1109/AIPR.2015.7444534","url":null,"abstract":"In this paper, High Accuracy Optical Flow (HAOF) based future image frames generator model is proposed. The aim of this work is to develop a framework which is capable of predicting the future image frames for any given sequence of images. The requirement is to predict large number of image frames with better clarity and better accuracy. In the first step, the vertical and horizontal components of flow velocities of the intensities at each pixel positions are estimated using High Accuracy Optical Flow (HAOF) algorithm. The estimated flow velocities in all the image frames at all the pixel positions are then modeled using separate Artificial Neural Networks (ANN). The trained models are used to predict the flow velocities of intensities at all the pixel positions in the future image frames. The intensities at all the pixel positions are mapped to new positions by using the velocities predicted by the model. The concept of Bilinear Interpolation is used to obtain predicted images from the new positions of intensities. The quality of the predicted image frames is evaluated by using Canny Edge Detection based Image Comparison Metric (CIM) and Mean Structural Similarity Index Measure (MSSIM). The predictor model is simulated by applying it on the two image sequences-an image sequence of a fighter jet landing over the navy deck, and another image sequence of a train moving on a bridge. The proposed framework is found to give promising results with better clarity and better accuracy.","PeriodicalId":440673,"journal":{"name":"2015 IEEE Applied Imagery Pattern Recognition Workshop (AIPR)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128246511","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

Perceived X-ray image quality for baggage screening 感知x射线图像质量的行李检查

2015 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) Pub Date : 2015-10-01 DOI: 10.1109/AIPR.2015.7444546

J. Irvine, M. Young, Stan German, R. Eaton

引用次数: 3