Pub Date : 2014-03-24DOI: 10.1109/WACV.2014.6836052
Vlad I. Morariu, Ejaz Ahmed, Venkataraman Santhanam, David Harwood, L. Davis
We propose a linear dimensionality reduction method, Composite Discriminant Factor (CDF) analysis, which searches for a discriminative but compact feature subspace that can be used as input to classifiers that suffer from problems such as multi-collinearity or the curse of dimensionality. The subspace selected by CDF maximizes the performance of the entire classification pipeline, and is chosen from a set of candidate subspaces that are each discriminative. Our method is based on Partial Least Squares (PLS) analysis, and can be viewed as a generalization of the PLS1 algorithm, designed to increase discrimination in classification tasks. We demonstrate our approach on the UCF50 action recognition dataset, two object detection datasets (INRIA pedestrians and vehicles from aerial imagery), and machine learning datasets from the UCI Machine Learning repository. Experimental results show that the proposed approach improves significantly in terms of accuracy over linear SVM, and also over PLS in terms of compactness and efficiency, while maintaining or improving accuracy.
{"title":"Composite Discriminant Factor analysis","authors":"Vlad I. Morariu, Ejaz Ahmed, Venkataraman Santhanam, David Harwood, L. Davis","doi":"10.1109/WACV.2014.6836052","DOIUrl":"https://doi.org/10.1109/WACV.2014.6836052","url":null,"abstract":"We propose a linear dimensionality reduction method, Composite Discriminant Factor (CDF) analysis, which searches for a discriminative but compact feature subspace that can be used as input to classifiers that suffer from problems such as multi-collinearity or the curse of dimensionality. The subspace selected by CDF maximizes the performance of the entire classification pipeline, and is chosen from a set of candidate subspaces that are each discriminative. Our method is based on Partial Least Squares (PLS) analysis, and can be viewed as a generalization of the PLS1 algorithm, designed to increase discrimination in classification tasks. We demonstrate our approach on the UCF50 action recognition dataset, two object detection datasets (INRIA pedestrians and vehicles from aerial imagery), and machine learning datasets from the UCI Machine Learning repository. Experimental results show that the proposed approach improves significantly in terms of accuracy over linear SVM, and also over PLS in terms of compactness and efficiency, while maintaining or improving accuracy.","PeriodicalId":73325,"journal":{"name":"IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision","volume":"1 1","pages":"564-571"},"PeriodicalIF":0.0,"publicationDate":"2014-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90376019","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 : 2014-03-24DOI: 10.1109/WACV.2014.6835990
Cha Zhang, Zhengyou Zhang
Multiview face detection is a challenging problem due to dramatic appearance changes under various pose, illumination and expression conditions. In this paper, we present a multi-task deep learning scheme to enhance the detection performance. More specifically, we build a deep convolutional neural network that can simultaneously learn the face/nonface decision, the face pose estimation problem, and the facial landmark localization problem. We show that such a multi-task learning scheme can further improve the classifier's accuracy. On the challenging FDDB data set, our detector achieves over 3% improvement in detection rate at the same false positive rate compared with other state-of-the-art methods.
{"title":"Improving multiview face detection with multi-task deep convolutional neural networks","authors":"Cha Zhang, Zhengyou Zhang","doi":"10.1109/WACV.2014.6835990","DOIUrl":"https://doi.org/10.1109/WACV.2014.6835990","url":null,"abstract":"Multiview face detection is a challenging problem due to dramatic appearance changes under various pose, illumination and expression conditions. In this paper, we present a multi-task deep learning scheme to enhance the detection performance. More specifically, we build a deep convolutional neural network that can simultaneously learn the face/nonface decision, the face pose estimation problem, and the facial landmark localization problem. We show that such a multi-task learning scheme can further improve the classifier's accuracy. On the challenging FDDB data set, our detector achieves over 3% improvement in detection rate at the same false positive rate compared with other state-of-the-art methods.","PeriodicalId":73325,"journal":{"name":"IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision","volume":"15 1","pages":"1036-1041"},"PeriodicalIF":0.0,"publicationDate":"2014-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73431647","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 : 2014-03-24DOI: 10.1109/WACV.2014.6835983
M. Khademi, Louis-Philippe Morency
This paper presents a subject-independent facial action unit (AU) detection method by introducing the concept of relative AU detection, for scenarios where the neutral face is not provided. We propose a new classification objective function which analyzes the temporal neighborhood of the current frame to decide if the expression recently increased, decreased or showed no change. This approach is a significant change from the conventional absolute method which decides about AU classification using the current frame, without an explicit comparison with its neighboring frames. Our proposed method improves robustness to individual differences such as face scale and shape, age-related wrinkles, and transitions among expressions (e.g., lower intensity of expressions). Our experiments on three publicly available datasets (Extended Cohn-Kanade (CK+), Bosphorus, and DISFA databases) show significant improvement of our approach over conventional absolute techniques.
{"title":"Relative facial action unit detection","authors":"M. Khademi, Louis-Philippe Morency","doi":"10.1109/WACV.2014.6835983","DOIUrl":"https://doi.org/10.1109/WACV.2014.6835983","url":null,"abstract":"This paper presents a subject-independent facial action unit (AU) detection method by introducing the concept of relative AU detection, for scenarios where the neutral face is not provided. We propose a new classification objective function which analyzes the temporal neighborhood of the current frame to decide if the expression recently increased, decreased or showed no change. This approach is a significant change from the conventional absolute method which decides about AU classification using the current frame, without an explicit comparison with its neighboring frames. Our proposed method improves robustness to individual differences such as face scale and shape, age-related wrinkles, and transitions among expressions (e.g., lower intensity of expressions). Our experiments on three publicly available datasets (Extended Cohn-Kanade (CK+), Bosphorus, and DISFA databases) show significant improvement of our approach over conventional absolute techniques.","PeriodicalId":73325,"journal":{"name":"IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision","volume":"18 1","pages":"1090-1095"},"PeriodicalIF":0.0,"publicationDate":"2014-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84428784","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 : 2014-03-24DOI: 10.1109/WACV.2014.6836108
Shohei Noguchi, M. Yamada, Yoshihiro Watanabe, M. Ishikawa
In this paper, we propose a new book digitization system that can obtain high-resolution document images while flipping the pages automatically. The distinctive feature of our system is the adaptive capturing that has a crucial role in achieving high speed and high resolution. This adaptive capturing requires observing the state of the flipped pages at high speed and with high accuracy. In order to meet this requirement, we newly propose a method of obtaining the 3D shape of the book, tracking each page, and evaluating the state. In addition, we explain the details of the proposed high-speed book digitization system. We also report some experiments conducted to verify the performance of the developed system.
{"title":"Real-time 3D page tracking and book status recognition for high-speed book digitization based on adaptive capturing","authors":"Shohei Noguchi, M. Yamada, Yoshihiro Watanabe, M. Ishikawa","doi":"10.1109/WACV.2014.6836108","DOIUrl":"https://doi.org/10.1109/WACV.2014.6836108","url":null,"abstract":"In this paper, we propose a new book digitization system that can obtain high-resolution document images while flipping the pages automatically. The distinctive feature of our system is the adaptive capturing that has a crucial role in achieving high speed and high resolution. This adaptive capturing requires observing the state of the flipped pages at high speed and with high accuracy. In order to meet this requirement, we newly propose a method of obtaining the 3D shape of the book, tracking each page, and evaluating the state. In addition, we explain the details of the proposed high-speed book digitization system. We also report some experiments conducted to verify the performance of the developed system.","PeriodicalId":73325,"journal":{"name":"IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision","volume":"41 1","pages":"137-144"},"PeriodicalIF":0.0,"publicationDate":"2014-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85222491","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 : 2014-03-24DOI: 10.1109/WACV.2014.6836116
A. Rehan, Aamer Zaheer, Ijaz Akhter, Arfah Saeed, M. Usmani, Bilal Mahmood, Sohaib Khan
In this paper we show that typical nonrigid structure can often be approximated well as locally rigid sub-structures in time and space. Specifically, we assume that: 1) the structure can be approximated as rigid in a short local time window and 2) some point- pairs stay relatively rigid in space, maintaining a fixed distance between them during the sequence. First, we use the triangulation constraints in rigid SfM over a sliding time window to get an initial estimate of the nonrigid 3D structure. Then we automatically identify relatively rigid point-pairs in this structure, and use their length-constancy simultaneously with triangulation constraints to refine the structure estimate. Local factorization inherently handles small camera motion, short sequences and significant natural occlusions gracefully, performing better than nonrigid factorization methods. We show more stable and accurate results as compared to the state-of-the art on even short sequences starting from 15 frames only, containing camera rotations as small as 2° and up to 50% contiguous missing data.
{"title":"NRSfM using local rigidity","authors":"A. Rehan, Aamer Zaheer, Ijaz Akhter, Arfah Saeed, M. Usmani, Bilal Mahmood, Sohaib Khan","doi":"10.1109/WACV.2014.6836116","DOIUrl":"https://doi.org/10.1109/WACV.2014.6836116","url":null,"abstract":"In this paper we show that typical nonrigid structure can often be approximated well as locally rigid sub-structures in time and space. Specifically, we assume that: 1) the structure can be approximated as rigid in a short local time window and 2) some point- pairs stay relatively rigid in space, maintaining a fixed distance between them during the sequence. First, we use the triangulation constraints in rigid SfM over a sliding time window to get an initial estimate of the nonrigid 3D structure. Then we automatically identify relatively rigid point-pairs in this structure, and use their length-constancy simultaneously with triangulation constraints to refine the structure estimate. Local factorization inherently handles small camera motion, short sequences and significant natural occlusions gracefully, performing better than nonrigid factorization methods. We show more stable and accurate results as compared to the state-of-the art on even short sequences starting from 15 frames only, containing camera rotations as small as 2° and up to 50% contiguous missing data.","PeriodicalId":73325,"journal":{"name":"IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision","volume":"14 1","pages":"69-74"},"PeriodicalIF":0.0,"publicationDate":"2014-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81993638","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 : 2014-03-24DOI: 10.1109/WACV.2014.6836050
H. Nguyen, Vishal M. Patel
We introduce a novel classifier, called max residual classifier (MRC), for learning a sparse representation jointly with a discriminative decision function. MRC seeks to maximize the differences between the residual errors of the wrong classes and the right one. This effectively leads to a more discriminative sparse representation and better classification accuracy. The optimization procedure is simple and efficient. Its objective function is closely related to the decision function of the residual classification strategy. Unlike existing methods for learning discriminative sparse representation that are restricted to a linear model, our approach is able to work with a non-linear model via the use of Mercer kernel. Experimental results show that MRC is able to capture meaningful and compact structures of data. Its performances compare favourably with the current state of the art on challenging benchmarks including rotated MNIST, Caltech-101, Caltech-256, and SHREC'11 non-rigid 3D shapes.
{"title":"Max residual classifier","authors":"H. Nguyen, Vishal M. Patel","doi":"10.1109/WACV.2014.6836050","DOIUrl":"https://doi.org/10.1109/WACV.2014.6836050","url":null,"abstract":"We introduce a novel classifier, called max residual classifier (MRC), for learning a sparse representation jointly with a discriminative decision function. MRC seeks to maximize the differences between the residual errors of the wrong classes and the right one. This effectively leads to a more discriminative sparse representation and better classification accuracy. The optimization procedure is simple and efficient. Its objective function is closely related to the decision function of the residual classification strategy. Unlike existing methods for learning discriminative sparse representation that are restricted to a linear model, our approach is able to work with a non-linear model via the use of Mercer kernel. Experimental results show that MRC is able to capture meaningful and compact structures of data. Its performances compare favourably with the current state of the art on challenging benchmarks including rotated MNIST, Caltech-101, Caltech-256, and SHREC'11 non-rigid 3D shapes.","PeriodicalId":73325,"journal":{"name":"IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision","volume":"7 1","pages":"580-587"},"PeriodicalIF":0.0,"publicationDate":"2014-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82576513","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 : 2014-03-24DOI: 10.1109/WACV.2014.6836058
M. J. Afridi, Chun Liu, C. Chan, S. Baek, Xiaoming Liu
Researchers in the areas of regenerative medicine and tissue engineering have great interests in understanding the relationship of different sets of culturing conditions and applied mechanical stimuli to the behavior of mesenchymal stem cells (MSCs). However, it is challenging to design a tool to perform automatic cell image analysis due to the diverse morphologies of MSCs. Therefore, as a primary step towards developing the tool, we propose a novel approach for accurate cell image segmentation. We collected three MSC datasets cultured on different surfaces and exposed to diverse mechanical stimuli. By analyzing existing approaches on our data, we choose to substantially extend binarization-based extraction of alignment score (BEAS) approach by extracting novel discriminating features and developing an adaptive threshold estimation model. Experimental results on our data shows our approach is superior to seven conventional techniques. We also define three quantitative measures to analyze the characteristics of images in our datasets. To the best of our knowledge, this is the first study that applied automatic segmentation to live MSC cultured on different surfaces with applied stimuli.
{"title":"Image segmentation of mesenchymal stem cells in diverse culturing conditions","authors":"M. J. Afridi, Chun Liu, C. Chan, S. Baek, Xiaoming Liu","doi":"10.1109/WACV.2014.6836058","DOIUrl":"https://doi.org/10.1109/WACV.2014.6836058","url":null,"abstract":"Researchers in the areas of regenerative medicine and tissue engineering have great interests in understanding the relationship of different sets of culturing conditions and applied mechanical stimuli to the behavior of mesenchymal stem cells (MSCs). However, it is challenging to design a tool to perform automatic cell image analysis due to the diverse morphologies of MSCs. Therefore, as a primary step towards developing the tool, we propose a novel approach for accurate cell image segmentation. We collected three MSC datasets cultured on different surfaces and exposed to diverse mechanical stimuli. By analyzing existing approaches on our data, we choose to substantially extend binarization-based extraction of alignment score (BEAS) approach by extracting novel discriminating features and developing an adaptive threshold estimation model. Experimental results on our data shows our approach is superior to seven conventional techniques. We also define three quantitative measures to analyze the characteristics of images in our datasets. To the best of our knowledge, this is the first study that applied automatic segmentation to live MSC cultured on different surfaces with applied stimuli.","PeriodicalId":73325,"journal":{"name":"IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision","volume":"55 1","pages":"516-523"},"PeriodicalIF":0.0,"publicationDate":"2014-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89194629","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 : 2014-03-24DOI: 10.1109/WACV.2014.6836017
M. Yang, B. Rosenhahn
Unsupervised video object segmentation is a challenging problem because it involves a large amount of data and object appearance may significantly change over time. In this paper, we propose a bottom-up approach for the combination of object segmentation and motion segmentation using a novel graphical model, which is formulated as inference in a conditional random field (CRF) model. This model combines object labeling and trajectory clustering in a unified probabilistic framework. The CRF contains binary variables representing the class labels of image pixels as well as binary variables indicating the correctness of trajectory clustering, which integrates dense local interaction and sparse global constraint. An optimization scheme based on a coordinate ascent style procedure is proposed to solve the inference problem. We evaluate our proposed framework by comparing it to other video and motion segmentation algorithms. Our method achieves improved performance on state-of-the-art benchmark datasets.
{"title":"Video segmentation with joint object and trajectory labeling","authors":"M. Yang, B. Rosenhahn","doi":"10.1109/WACV.2014.6836017","DOIUrl":"https://doi.org/10.1109/WACV.2014.6836017","url":null,"abstract":"Unsupervised video object segmentation is a challenging problem because it involves a large amount of data and object appearance may significantly change over time. In this paper, we propose a bottom-up approach for the combination of object segmentation and motion segmentation using a novel graphical model, which is formulated as inference in a conditional random field (CRF) model. This model combines object labeling and trajectory clustering in a unified probabilistic framework. The CRF contains binary variables representing the class labels of image pixels as well as binary variables indicating the correctness of trajectory clustering, which integrates dense local interaction and sparse global constraint. An optimization scheme based on a coordinate ascent style procedure is proposed to solve the inference problem. We evaluate our proposed framework by comparing it to other video and motion segmentation algorithms. Our method achieves improved performance on state-of-the-art benchmark datasets.","PeriodicalId":73325,"journal":{"name":"IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision","volume":"11 1","pages":"831-838"},"PeriodicalIF":0.0,"publicationDate":"2014-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89947162","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 : 2014-03-24DOI: 10.1109/WACV.2014.6836013
G. Nebehay, R. Pflugfelder
We propose a novel keypoint-based method for long-term model-free object tracking in a combined matching-and-tracking framework. In order to localise the object in every frame, each keypoint casts votes for the object center. As erroneous keypoints are hard to avoid, we employ a novel consensus-based scheme for outlier detection in the voting behaviour. To make this approach computationally feasible, we propose not to employ an accumulator space for votes, but rather to cluster votes directly in the image space. By transforming votes based on the current keypoint constellation, we account for changes of the object in scale and rotation. In contrast to competing approaches, we refrain from updating the appearance information, thus avoiding the danger of making errors. The use of fast keypoint detectors and binary descriptors allows for our implementation to run in real-time. We demonstrate experimentally on a diverse dataset that is as large as 60 sequences that our method outperforms the state-of-the-art when high accuracy is required and visualise these results by employing a variant of success plots.
{"title":"Consensus-based matching and tracking of keypoints for object tracking","authors":"G. Nebehay, R. Pflugfelder","doi":"10.1109/WACV.2014.6836013","DOIUrl":"https://doi.org/10.1109/WACV.2014.6836013","url":null,"abstract":"We propose a novel keypoint-based method for long-term model-free object tracking in a combined matching-and-tracking framework. In order to localise the object in every frame, each keypoint casts votes for the object center. As erroneous keypoints are hard to avoid, we employ a novel consensus-based scheme for outlier detection in the voting behaviour. To make this approach computationally feasible, we propose not to employ an accumulator space for votes, but rather to cluster votes directly in the image space. By transforming votes based on the current keypoint constellation, we account for changes of the object in scale and rotation. In contrast to competing approaches, we refrain from updating the appearance information, thus avoiding the danger of making errors. The use of fast keypoint detectors and binary descriptors allows for our implementation to run in real-time. We demonstrate experimentally on a diverse dataset that is as large as 60 sequences that our method outperforms the state-of-the-art when high accuracy is required and visualise these results by employing a variant of success plots.","PeriodicalId":73325,"journal":{"name":"IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision","volume":"2 1","pages":"862-869"},"PeriodicalIF":0.0,"publicationDate":"2014-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88963142","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 : 2014-03-24DOI: 10.1109/WACV.2014.6836109
L. Hazelhoff, Ivo M. Creusen, P. D. With
Accurate and up-to-date inventories of lighting poles are of interest to energy companies, beneficial for the transition to energy-efficient lighting and may contribute to a more adequate lighting of streets. This potentially improves social security and reduces crime and vandalism during nighttime. This paper describes a system for automated surveying of lighting poles from street-level panoramic images. The system consists of two independent detectors, focusing at the detection of the pole itself and at the detection of a specific lighting fixture type. Both follow the same approach, and start with detection of the feature of interest (pole or fixture) within the individual images, followed by a multi-view analysis to retrieve the real-world coordinates of the poles. Afterwards, the detection output of both algorithms is merged. Large-scale validations, covering about 135 km of road, show that over 91% of the lighting poles is found, while the precision remains above 50%. When applying this system in a semi-automated fashion, high-quality inventories can be created up to 5 times more efficiently compared to manually surveying all poles from the images.
{"title":"System for semi-automated surveying of street-lighting poles from street-level panoramic images","authors":"L. Hazelhoff, Ivo M. Creusen, P. D. With","doi":"10.1109/WACV.2014.6836109","DOIUrl":"https://doi.org/10.1109/WACV.2014.6836109","url":null,"abstract":"Accurate and up-to-date inventories of lighting poles are of interest to energy companies, beneficial for the transition to energy-efficient lighting and may contribute to a more adequate lighting of streets. This potentially improves social security and reduces crime and vandalism during nighttime. This paper describes a system for automated surveying of lighting poles from street-level panoramic images. The system consists of two independent detectors, focusing at the detection of the pole itself and at the detection of a specific lighting fixture type. Both follow the same approach, and start with detection of the feature of interest (pole or fixture) within the individual images, followed by a multi-view analysis to retrieve the real-world coordinates of the poles. Afterwards, the detection output of both algorithms is merged. Large-scale validations, covering about 135 km of road, show that over 91% of the lighting poles is found, while the precision remains above 50%. When applying this system in a semi-automated fashion, high-quality inventories can be created up to 5 times more efficiently compared to manually surveying all poles from the images.","PeriodicalId":73325,"journal":{"name":"IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision","volume":"120 1","pages":"129-136"},"PeriodicalIF":0.0,"publicationDate":"2014-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86167045","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：