2013 IEEE Applied Imagery Pattern Recognition Workshop (AIPR)最新文献_第2页

Detection of Abnormal behavior in Dynamic Crowded Gatherings 动态人群聚集中的异常行为检测

2013 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) Pub Date : 2013-10-01 DOI: 10.1109/AIPR.2013.6749309

Hiba H. Alqaysi, S. Sasi

引用次数: 21

Video-based activity analysis using the L1 tracker on VIRAT data 使用L1跟踪器对VIRAT数据进行基于视频的活动分析

2013 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) Pub Date : 2013-10-01 DOI: 10.1109/AIPR.2013.6749311

E. Blasch, Zhonghai Wang, Haibin Ling, K. Palaniappan, Genshe Chen, D. Shen, Alexander J. Aved, G. Seetharaman

{"title":"Video-based activity analysis using the L1 tracker on VIRAT data","authors":"E. Blasch, Zhonghai Wang, Haibin Ling, K. Palaniappan, Genshe Chen, D. Shen, Alexander J. Aved, G. Seetharaman","doi":"10.1109/AIPR.2013.6749311","DOIUrl":"https://doi.org/10.1109/AIPR.2013.6749311","url":null,"abstract":"Developments in video tracking have addressed various aspects such as target detection, tracking accuracy, algorithm comparison, and implementation methods which are briefly reviewed. However, there are other attributes of full motion video (FMV) tracking that require further investigation for situation awareness of event and activity analysis. Key aspects of activity and behavior analysis include interaction between individuals, groups, and crowds as well as with objects in the environment like vehicles and buildings over a specified time duration as it is typically assumed that the activities of interest include people. In this paper, we explore activity analysis using the L1 tracker over various scenarios in the VIRAT data. Activity analysis extends event detection from tracking accuracy to characterizing number, types, and relationships between actors in analyzing human activities of interest. Relationships include correlation in space and time of actors with other people, objects, vehicles, and facilities (POVF). Event detection is more mature (e.g., based on image exploitation and tracking techniques), while activity analysis (as a higher level fusion function) requires innovative techniques for relationship understanding.","PeriodicalId":435620,"journal":{"name":"2013 IEEE Applied Imagery Pattern Recognition Workshop (AIPR)","volume":"114 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116328480","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: 31

Indoor location with Wi-Fi fingerprinting 室内定位与Wi-Fi指纹识别

2013 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) Pub Date : 2013-10-01 DOI: 10.1109/AIPR.2013.6749334

Noah Pritt

{"title":"Indoor location with Wi-Fi fingerprinting","authors":"Noah Pritt","doi":"10.1109/AIPR.2013.6749334","DOIUrl":"https://doi.org/10.1109/AIPR.2013.6749334","url":null,"abstract":"There are many applications for indoor location determination, from the navigation of hospitals, airports, parking garages and shopping malls, for example, to navigational aids for the blind and visually impaired, targeted advertising, mining, and disaster response. GPS signals are too weak for indoor use, however, making it necessary to investigate other means of navigation. Most approaches such as ultrasound and RFID tags require special hardware to be installed and remain expensive and inconvenient. The solution proposed in this paper makes use of commonly available Wi-Fi networks and runs on ordinary smart phones and tablets without the need to install special hardware. It comprises a calibration stage and a navigation stage. The calibration stage creates a “Wi-Fi fingerprint” for each room of a building. It minimizes the calibration time through the use of waypoints. The navigation stage matches Wi-Fi signals to the fingerprints to determine the user's most likely location. It uses maximum likelihood classification for this matching and takes the building's topology into account through the use of Bayes' Theorem. The system is implemented as a mobile Android app and is easy to use. In testing, it took only an hour to calibrate a home or shopping mall, and the navigation stage yielded the correct location 97.5% of the time in a home and 100% of the time in a mall.","PeriodicalId":435620,"journal":{"name":"2013 IEEE Applied Imagery Pattern Recognition Workshop (AIPR)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127375436","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: 23

Nonlinear dimensionality reduction for structural discovery in image processing 图像处理中结构发现的非线性降维方法

2013 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) Pub Date : 2013-10-01 DOI: 10.1109/AIPR.2013.6749319

D. Floyd, R. Cloutier, Teresa Zigh

引用次数: 0

Robust feature vector for efficient human detection 鲁棒特征向量用于高效的人体检测

2013 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) Pub Date : 2013-10-01 DOI: 10.1109/AIPR.2013.6749310

A. Bell

{"title":"Robust feature vector for efficient human detection","authors":"A. Bell","doi":"10.1109/AIPR.2013.6749310","DOIUrl":"https://doi.org/10.1109/AIPR.2013.6749310","url":null,"abstract":"This research presents a method for the automatic detection of a dismounted human at long range from a single, highly compressed image. The histogram of oriented gradients (HOG) method provides the feature vector, a support vector machine performs the classification, and the JPEG2000 standard compresses the image. This work presents an understanding of how HOG for human detection holds up as range and compression increases. The results indicate that HOG remains effective even at long distances: the average miss rate and false alarm rate are both kept to 5% for humans only 12 pixels tall and 4-5 pixels wide in uncompressed images. Next, classification performance for humans at close range (100 pixels tall) is evaluated for compressed and uncompressed versions of the same test images. Using a compression ratio of 32:1 (97% of each image's data is discarded and the image is reconstructed from only the 3% retained), the miss rates for the compressed and uncompressed images are equivalent at 0.5% while the 1.0% false alarm rate for the compressed images is only slightly higher than the 0.5% rate for the uncompressed images. Finally, this work depicts good detection performance for humans at long ranges in highly compressed images. Insights into important design issues-for example, the impact of the amount and type of training data needed to achieve this performance-are also discussed.","PeriodicalId":435620,"journal":{"name":"2013 IEEE Applied Imagery Pattern Recognition Workshop (AIPR)","volume":" 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120933917","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

Image georegistration methods: A framework for application guidelines 图像地理配准方法:应用指南框架

2013 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) Pub Date : 2013-10-01 DOI: 10.1109/AIPR.2013.6749317

Peter Doucette, Jim Antonisse, A. Braun, M. Lenihan, Michelle Brennan

{"title":"Image georegistration methods: A framework for application guidelines","authors":"Peter Doucette, Jim Antonisse, A. Braun, M. Lenihan, Michelle Brennan","doi":"10.1109/AIPR.2013.6749317","DOIUrl":"https://doi.org/10.1109/AIPR.2013.6749317","url":null,"abstract":"With the rapid growth of sensor platforms for imagery collection, from micro-unmanned aerial systems (UAS) to smart phones, an ability to geo-register image data is a fundamental need for many downstream applications. Approaches to georegistration for sensor imagery have deep roots in photogrammetry, and more recently with the integration of computer vision techniques. Georegistration solutions are increasingly sought for inexpensive and non-metric quality sensors and/or those that may lack the metadata needed to support rigorous coordinate transfer with error estimation. This indicates a range of solution quality, with situational awareness at one end, and rigorous accuracy at the other. There are a variety of correspondence and transformation models from which to select, with tradeoffs among simplicity, accuracy, and error estimation. The continually expanding vernacular of terms and methods can lead to confusion of application among the broader community of users. A sorting of representative terminology, processes, and techniques, is proposed as a framework. The goal is to motivate discussion for application guidelines.","PeriodicalId":435620,"journal":{"name":"2013 IEEE Applied Imagery Pattern Recognition Workshop (AIPR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134265284","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: 4

Plenoptic camera range finding 全光学相机测距

2013 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) Pub Date : 2013-10-01 DOI: 10.1109/AIPR.2013.6749336

Robert Raynor, K. Walli

引用次数: 6

Anomaly prediction in seismic signals using neural networks 基于神经网络的地震信号异常预测

2013 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) Pub Date : 2013-10-01 DOI: 10.1109/AIPR.2013.6749340

A. Waibel, A. Alshehri, Soundararajan Ezekiel

引用次数: 2

Feature track summary visualization for sequential multi-view reconstruction 用于顺序多视图重建的特征轨道摘要可视化

2013 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) Pub Date : 2013-10-01 DOI: 10.1109/AIPR.2013.6749337

S. Recker, Mauricio Hess-Flores, K. Joy

引用次数: 0

Face recognition using Elastic bunch graph matching 基于弹性束图匹配的人脸识别

2013 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) Pub Date : 2013-10-01 DOI: 10.1109/AIPR.2013.6749338

M. Hanmandlu, Divya Gupta, S. Vasikarla

引用次数: 17