Pub Date : 2011-01-01DOI: 10.1109/WACV.2011.5711494
Nathan Jacobs, Kylia Miskell, Robert Pless
We consider the problem of geo-locating static cameras from long-term time-lapse imagery. This problem has received significant attention recently, with most methods making strong assumptions on the geometric structure of the scene. We explore a simple, robust cue that relates overall image intensity to the zenith angle of the sun (which need not be visible). We characterize the accuracy of geolocation based on this cue as a function of different models of the zenith-intensity relationship and the amount of imagery available. We evaluate our algorithm on a dataset of more than 60 million images captured from outdoor webcams located around the globe. We find that using our algorithm with images sampled every 30 minutes, yields localization errors of less than 100 km for the majority of cameras.
{"title":"Webcam geo-localization using aggregate light levels","authors":"Nathan Jacobs, Kylia Miskell, Robert Pless","doi":"10.1109/WACV.2011.5711494","DOIUrl":"https://doi.org/10.1109/WACV.2011.5711494","url":null,"abstract":"We consider the problem of geo-locating static cameras from long-term time-lapse imagery. This problem has received significant attention recently, with most methods making strong assumptions on the geometric structure of the scene. We explore a simple, robust cue that relates overall image intensity to the zenith angle of the sun (which need not be visible). We characterize the accuracy of geolocation based on this cue as a function of different models of the zenith-intensity relationship and the amount of imagery available. We evaluate our algorithm on a dataset of more than 60 million images captured from outdoor webcams located around the globe. We find that using our algorithm with images sampled every 30 minutes, yields localization errors of less than 100 km for the majority of cameras.","PeriodicalId":424724,"journal":{"name":"2011 IEEE Workshop on Applications of Computer Vision (WACV)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124463006","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 : 2011-01-01DOI: 10.1109/WACV.2011.5711534
M. Aly, Mario E. Munich, P. Perona
Indexing quickly and accurately in a large collection of images has become an important problem with many applications. Given a query image, the goal is to retrieve matching images in the collection. We compare the structure and properties of seven different methods based on the two leading approaches: voting from matching of local descriptors vs. matching histograms of visual words, including some new methods. We derive theoretical estimates of how the memory and computational cost scale with the number of images in the database. We evaluate these properties empirically on four real-world datasets with different statistics. We discuss the pros and cons of the different methods and suggest promising directions for future research.
{"title":"Indexing in large scale image collections: Scaling properties and benchmark","authors":"M. Aly, Mario E. Munich, P. Perona","doi":"10.1109/WACV.2011.5711534","DOIUrl":"https://doi.org/10.1109/WACV.2011.5711534","url":null,"abstract":"Indexing quickly and accurately in a large collection of images has become an important problem with many applications. Given a query image, the goal is to retrieve matching images in the collection. We compare the structure and properties of seven different methods based on the two leading approaches: voting from matching of local descriptors vs. matching histograms of visual words, including some new methods. We derive theoretical estimates of how the memory and computational cost scale with the number of images in the database. We evaluate these properties empirically on four real-world datasets with different statistics. We discuss the pros and cons of the different methods and suggest promising directions for future research.","PeriodicalId":424724,"journal":{"name":"2011 IEEE Workshop on Applications of Computer Vision (WACV)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126268486","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 : 2011-01-01DOI: 10.1109/WACV.2011.5711519
Oliver A. Nina, B. Morse, W. Barrett
The use of digital images of scanned handwritten historical documents has increased in recent years, especially with the online availability of large document collections. However, the sheer number of images in some of these collections makes them cumbersome to manually read and process, making the need for automated processing of increased importance. A key step in the recognition and retrieval of such documents is binarization, the separation of document text from the page's background. Binarization of images of historical documents that have been affected by degradation or are otherwise of poor image quality is difficult and continues to be a topic of research in the field of image processing. This paper presents a novel approach to this problem, including two primary variations. One combines a recursive extension of Otsu thresholding and selective bilateral filtering to allow automatic binarization and segmentation of handwritten text images. The other also builds on the recursive Otsu method and adds improved background normalization and a post-processing step to the algorithm to make it more robust and to perform adequately even for images that present bleed-through artifacts. Our results show that these techniques segment the text in historical documents comparable to and in some cases better than many state-of-the-art approaches based on their performance as evaluated using the dataset from the recent ICDAR 2009 Document Image Binarization Contest.
{"title":"A recursive Otsu thresholding method for scanned document binarization","authors":"Oliver A. Nina, B. Morse, W. Barrett","doi":"10.1109/WACV.2011.5711519","DOIUrl":"https://doi.org/10.1109/WACV.2011.5711519","url":null,"abstract":"The use of digital images of scanned handwritten historical documents has increased in recent years, especially with the online availability of large document collections. However, the sheer number of images in some of these collections makes them cumbersome to manually read and process, making the need for automated processing of increased importance. A key step in the recognition and retrieval of such documents is binarization, the separation of document text from the page's background. Binarization of images of historical documents that have been affected by degradation or are otherwise of poor image quality is difficult and continues to be a topic of research in the field of image processing. This paper presents a novel approach to this problem, including two primary variations. One combines a recursive extension of Otsu thresholding and selective bilateral filtering to allow automatic binarization and segmentation of handwritten text images. The other also builds on the recursive Otsu method and adds improved background normalization and a post-processing step to the algorithm to make it more robust and to perform adequately even for images that present bleed-through artifacts. Our results show that these techniques segment the text in historical documents comparable to and in some cases better than many state-of-the-art approaches based on their performance as evaluated using the dataset from the recent ICDAR 2009 Document Image Binarization Contest.","PeriodicalId":424724,"journal":{"name":"2011 IEEE Workshop on Applications of Computer Vision (WACV)","volume":"642 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117100650","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 : 2010-09-01DOI: 10.1109/ICIP.2010.5649575
Jun Yang, Yang Wang, A. Sowmya, Zhidong Li
In this paper, we address the problem of vehicle detection and tracking with low-angle cameras by combining windshield detection and feature points clustering, effectively fusing several primitive image features such as color, edge and interest point. By exploring various heterogenous features and multiple vehicle models, we achieve at least two improvements over the existing methods: higher detection accuracy and the ability to distinguish different vehicle types. Our experiments on real-world traffic video sequences demonstrate the benefits of feature fusion and the improved performance.
{"title":"Feature fusion for vehicle detection and tracking with low-angle cameras","authors":"Jun Yang, Yang Wang, A. Sowmya, Zhidong Li","doi":"10.1109/ICIP.2010.5649575","DOIUrl":"https://doi.org/10.1109/ICIP.2010.5649575","url":null,"abstract":"In this paper, we address the problem of vehicle detection and tracking with low-angle cameras by combining windshield detection and feature points clustering, effectively fusing several primitive image features such as color, edge and interest point. By exploring various heterogenous features and multiple vehicle models, we achieve at least two improvements over the existing methods: higher detection accuracy and the ability to distinguish different vehicle types. Our experiments on real-world traffic video sequences demonstrate the benefits of feature fusion and the improved performance.","PeriodicalId":424724,"journal":{"name":"2011 IEEE Workshop on Applications of Computer Vision (WACV)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128388867","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：