The world is full of objects with complex reflectances, situated in complex illumination environments. Past work on full 3D geometry recovery, however, has tried to handle this complexity by framing it into simplistic models of reflectance (Lambetian, mirrored, or diffuse plus specular) or illumination (one or more point light sources). Though there has been some recent progress in directly utilizing such complexities for recovering a single view geometry, it is not clear how such single-view methods can be extended to reconstruct the full geometry. To this end, we derive a probabilistic geometry estimation method that fully exploits the rich signal embedded in complex appearance. Though each observation provides partial and unreliable information, we show how to estimate the reflectance responsible for the diverse appearance, and unite the orientation cues embedded in each observation to reconstruct the underlying geometry. We demonstrate the effectiveness of our method on synthetic and real-world objects. The results show that our method performs accurately across a wide range of real-world environments and reflectances that lies between the extremes that have been the focus of past work.
{"title":"Multiview Shape and Reflectance from Natural Illumination","authors":"Geoffrey Oxholm, K. Nishino","doi":"10.1109/CVPR.2014.277","DOIUrl":"https://doi.org/10.1109/CVPR.2014.277","url":null,"abstract":"The world is full of objects with complex reflectances, situated in complex illumination environments. Past work on full 3D geometry recovery, however, has tried to handle this complexity by framing it into simplistic models of reflectance (Lambetian, mirrored, or diffuse plus specular) or illumination (one or more point light sources). Though there has been some recent progress in directly utilizing such complexities for recovering a single view geometry, it is not clear how such single-view methods can be extended to reconstruct the full geometry. To this end, we derive a probabilistic geometry estimation method that fully exploits the rich signal embedded in complex appearance. Though each observation provides partial and unreliable information, we show how to estimate the reflectance responsible for the diverse appearance, and unite the orientation cues embedded in each observation to reconstruct the underlying geometry. We demonstrate the effectiveness of our method on synthetic and real-world objects. The results show that our method performs accurately across a wide range of real-world environments and reflectances that lies between the extremes that have been the focus of past work.","PeriodicalId":319578,"journal":{"name":"2014 IEEE Conference on Computer Vision and Pattern Recognition","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125093700","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}
Photo-sharing websites have become very popular in the last few years, leading to huge collections of online images. In addition to image data, these websites collect a variety of multimodal metadata about photos including text tags, captions, GPS coordinates, camera metadata, user profiles, etc. However, this metadata is not well constrained and is often noisy, sparse, or missing altogether. In this paper, we propose a framework to model these "loosely organized" multimodal datasets, and show how to perform loosely-supervised learning using a novel latent Conditional Random Field framework. We learn parameters of the LCRF automatically from a small set of validation data, using Information Theoretic Metric Learning (ITML) to learn distance functions and a structural SVM formulation to learn the potential functions. We apply our framework on four datasets of images from Flickr, evaluating both qualitatively and quantitatively against several baselines.
{"title":"Multimodal Learning in Loosely-Organized Web Images","authors":"Kun Duan, David J. Crandall, Dhruv Batra","doi":"10.1109/CVPR.2014.316","DOIUrl":"https://doi.org/10.1109/CVPR.2014.316","url":null,"abstract":"Photo-sharing websites have become very popular in the last few years, leading to huge collections of online images. In addition to image data, these websites collect a variety of multimodal metadata about photos including text tags, captions, GPS coordinates, camera metadata, user profiles, etc. However, this metadata is not well constrained and is often noisy, sparse, or missing altogether. In this paper, we propose a framework to model these \"loosely organized\" multimodal datasets, and show how to perform loosely-supervised learning using a novel latent Conditional Random Field framework. We learn parameters of the LCRF automatically from a small set of validation data, using Information Theoretic Metric Learning (ITML) to learn distance functions and a structural SVM formulation to learn the potential functions. We apply our framework on four datasets of images from Flickr, evaluating both qualitatively and quantitatively against several baselines.","PeriodicalId":319578,"journal":{"name":"2014 IEEE Conference on Computer Vision and Pattern Recognition","volume":"72 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123542418","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}
A. Khosla, Byoungkwon An, Joseph J. Lim, A. Torralba
A common thread that ties together many prior works in scene understanding is their focus on the aspects directly present in a scene such as its categorical classification or the set of objects. In this work, we propose to look beyond the visible elements of a scene; we demonstrate that a scene is not just a collection of objects and their configuration or the labels assigned to its pixels - it is so much more. From a simple observation of a scene, we can tell a lot about the environment surrounding the scene such as the potential establishments near it, the potential crime rate in the area, or even the economic climate. Here, we explore several of these aspects from both the human perception and computer vision perspective. Specifically, we show that it is possible to predict the distance of surrounding establishments such as McDonald's or hospitals even by using scenes located far from them. We go a step further to show that both humans and computers perform well at navigating the environment based only on visual cues from scenes. Lastly, we show that it is possible to predict the crime rates in an area simply by looking at a scene without any real-time criminal activity. Simply put, here, we illustrate that it is possible to look beyond the visible scene.
{"title":"Looking Beyond the Visible Scene","authors":"A. Khosla, Byoungkwon An, Joseph J. Lim, A. Torralba","doi":"10.1109/CVPR.2014.474","DOIUrl":"https://doi.org/10.1109/CVPR.2014.474","url":null,"abstract":"A common thread that ties together many prior works in scene understanding is their focus on the aspects directly present in a scene such as its categorical classification or the set of objects. In this work, we propose to look beyond the visible elements of a scene; we demonstrate that a scene is not just a collection of objects and their configuration or the labels assigned to its pixels - it is so much more. From a simple observation of a scene, we can tell a lot about the environment surrounding the scene such as the potential establishments near it, the potential crime rate in the area, or even the economic climate. Here, we explore several of these aspects from both the human perception and computer vision perspective. Specifically, we show that it is possible to predict the distance of surrounding establishments such as McDonald's or hospitals even by using scenes located far from them. We go a step further to show that both humans and computers perform well at navigating the environment based only on visual cues from scenes. Lastly, we show that it is possible to predict the crime rates in an area simply by looking at a scene without any real-time criminal activity. Simply put, here, we illustrate that it is possible to look beyond the visible scene.","PeriodicalId":319578,"journal":{"name":"2014 IEEE Conference on Computer Vision and Pattern Recognition","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123794460","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}
Pablo Garrido, Levi Valgaerts, Ole Rehmsen, Thorsten Thormählen, P. Pérez, C. Theobalt
We propose an image-based, facial reenactment system that replaces the face of an actor in an existing target video with the face of a user from a source video, while preserving the original target performance. Our system is fully automatic and does not require a database of source expressions. Instead, it is able to produce convincing reenactment results from a short source video captured with an off-the-shelf camera, such as a webcam, where the user performs arbitrary facial gestures. Our reenactment pipeline is conceived as part image retrieval and part face transfer: The image retrieval is based on temporal clustering of target frames and a novel image matching metric that combines appearance and motion to select candidate frames from the source video, while the face transfer uses a 2D warping strategy that preserves the user's identity. Our system excels in simplicity as it does not rely on a 3D face model, it is robust under head motion and does not require the source and target performance to be similar. We show convincing reenactment results for videos that we recorded ourselves and for low-quality footage taken from the Internet.
{"title":"Automatic Face Reenactment","authors":"Pablo Garrido, Levi Valgaerts, Ole Rehmsen, Thorsten Thormählen, P. Pérez, C. Theobalt","doi":"10.1109/CVPR.2014.537","DOIUrl":"https://doi.org/10.1109/CVPR.2014.537","url":null,"abstract":"We propose an image-based, facial reenactment system that replaces the face of an actor in an existing target video with the face of a user from a source video, while preserving the original target performance. Our system is fully automatic and does not require a database of source expressions. Instead, it is able to produce convincing reenactment results from a short source video captured with an off-the-shelf camera, such as a webcam, where the user performs arbitrary facial gestures. Our reenactment pipeline is conceived as part image retrieval and part face transfer: The image retrieval is based on temporal clustering of target frames and a novel image matching metric that combines appearance and motion to select candidate frames from the source video, while the face transfer uses a 2D warping strategy that preserves the user's identity. Our system excels in simplicity as it does not rely on a 3D face model, it is robust under head motion and does not require the source and target performance to be similar. We show convincing reenactment results for videos that we recorded ourselves and for low-quality footage taken from the Internet.","PeriodicalId":319578,"journal":{"name":"2014 IEEE Conference on Computer Vision and Pattern Recognition","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125569146","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}
A method for identifying shape features of local nature on the shape's boundary, in a way that is facilitated by the presence of noise is presented. The boundary is seen as a real function. A study of a certain distance function reveals, almost counter-intuitively, that vertices can be defined and localized better in the presence of noise, thus the concept of noising, as opposed to smoothing, is conceived and presented. The method works on both smooth and noisy shapes, the presence of noise having an effect of improving on the results of the smoothed version. Experiments with noise and a comparison to state of the art validate the method.
{"title":"Noising versus Smoothing for Vertex Identification in Unknown Shapes","authors":"Konstantinos A. Raftopoulos, Marin Ferecatu","doi":"10.1109/CVPR.2014.530","DOIUrl":"https://doi.org/10.1109/CVPR.2014.530","url":null,"abstract":"A method for identifying shape features of local nature on the shape's boundary, in a way that is facilitated by the presence of noise is presented. The boundary is seen as a real function. A study of a certain distance function reveals, almost counter-intuitively, that vertices can be defined and localized better in the presence of noise, thus the concept of noising, as opposed to smoothing, is conceived and presented. The method works on both smooth and noisy shapes, the presence of noise having an effect of improving on the results of the smoothed version. Experiments with noise and a comparison to state of the art validate the method.","PeriodicalId":319578,"journal":{"name":"2014 IEEE Conference on Computer Vision and Pattern Recognition","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126856832","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}
Tianzhu Zhang, K. Jia, Changsheng Xu, Yi Ma, N. Ahuja
Part-based visual tracking is advantageous due to its robustness against partial occlusion. However, how to effectively exploit the confidence scores of individual parts to construct a robust tracker is still a challenging problem. In this paper, we address this problem by simultaneously matching parts in each of multiple frames, which is realized by a locality-constrained low-rank sparse learning method that establishes multi-frame part correspondences through optimization of partial permutation matrices. The proposed part matching tracker (PMT) has a number of attractive properties. (1) It exploits the spatial-temporal locality-constrained property for robust part matching. (2) It matches local parts from multiple frames jointly by considering their low-rank and sparse structure information, which can effectively handle part appearance variations due to occlusion or noise. (3) The proposed PMT model has the inbuilt mechanism of leveraging multi-mode target templates, so that the dilemma of template updating when encountering occlusion in tracking can be better handled. This contrasts with existing methods that only do part matching between a pair of frames. We evaluate PMT and compare with 10 popular state-of-the-art methods on challenging benchmarks. Experimental results show that PMT consistently outperform these existing trackers.
{"title":"Partial Occlusion Handling for Visual Tracking via Robust Part Matching","authors":"Tianzhu Zhang, K. Jia, Changsheng Xu, Yi Ma, N. Ahuja","doi":"10.1109/CVPR.2014.164","DOIUrl":"https://doi.org/10.1109/CVPR.2014.164","url":null,"abstract":"Part-based visual tracking is advantageous due to its robustness against partial occlusion. However, how to effectively exploit the confidence scores of individual parts to construct a robust tracker is still a challenging problem. In this paper, we address this problem by simultaneously matching parts in each of multiple frames, which is realized by a locality-constrained low-rank sparse learning method that establishes multi-frame part correspondences through optimization of partial permutation matrices. The proposed part matching tracker (PMT) has a number of attractive properties. (1) It exploits the spatial-temporal locality-constrained property for robust part matching. (2) It matches local parts from multiple frames jointly by considering their low-rank and sparse structure information, which can effectively handle part appearance variations due to occlusion or noise. (3) The proposed PMT model has the inbuilt mechanism of leveraging multi-mode target templates, so that the dilemma of template updating when encountering occlusion in tracking can be better handled. This contrasts with existing methods that only do part matching between a pair of frames. We evaluate PMT and compare with 10 popular state-of-the-art methods on challenging benchmarks. Experimental results show that PMT consistently outperform these existing trackers.","PeriodicalId":319578,"journal":{"name":"2014 IEEE Conference on Computer Vision and Pattern Recognition","volume":"539 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116245469","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}
Camera shake during exposure time often results in spatially variant blur effect of the image. The non-uniform blur effect is not only caused by the camera motion, but also the depth variation of the scene. The objects close to the camera sensors are likely to appear more blurry than those at a distance in such cases. However, recent non-uniform deblurring methods do not explicitly consider the depth factor or assume fronto-parallel scenes with constant depth for simplicity. While single image non-uniform deblurring is a challenging problem, the blurry results in fact contain depth information which can be exploited. We propose to jointly estimate scene depth and remove non-uniform blur caused by camera motion by exploiting their underlying geometric relationships, with only single blurry image as input. To this end, we present a unified layer-based model for depth-involved deblurring. We provide a novel layer-based solution using matting to partition the layers and an expectation-maximization scheme to solve this problem. This approach largely reduces the number of unknowns and makes the problem tractable. Experiments on challenging examples demonstrate that both depth and camera shake removal can be well addressed within the unified framework.
{"title":"Joint Depth Estimation and Camera Shake Removal from Single Blurry Image","authors":"Zhe Hu, Li Xu, Ming-Hsuan Yang","doi":"10.1109/CVPR.2014.370","DOIUrl":"https://doi.org/10.1109/CVPR.2014.370","url":null,"abstract":"Camera shake during exposure time often results in spatially variant blur effect of the image. The non-uniform blur effect is not only caused by the camera motion, but also the depth variation of the scene. The objects close to the camera sensors are likely to appear more blurry than those at a distance in such cases. However, recent non-uniform deblurring methods do not explicitly consider the depth factor or assume fronto-parallel scenes with constant depth for simplicity. While single image non-uniform deblurring is a challenging problem, the blurry results in fact contain depth information which can be exploited. We propose to jointly estimate scene depth and remove non-uniform blur caused by camera motion by exploiting their underlying geometric relationships, with only single blurry image as input. To this end, we present a unified layer-based model for depth-involved deblurring. We provide a novel layer-based solution using matting to partition the layers and an expectation-maximization scheme to solve this problem. This approach largely reduces the number of unknowns and makes the problem tractable. Experiments on challenging examples demonstrate that both depth and camera shake removal can be well addressed within the unified framework.","PeriodicalId":319578,"journal":{"name":"2014 IEEE Conference on Computer Vision and Pattern Recognition","volume":"219 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122852688","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}
We propose a deep learning framework for image set classification with application to face recognition. An Adaptive Deep Network Template (ADNT) is defined whose parameters are initialized by performing unsupervised pre-training in a layer-wise fashion using Gaussian Restricted Boltzmann Machines (GRBMs). The pre-initialized ADNT is then separately trained for images of each class and class-specific models are learnt. Based on the minimum reconstruction error from the learnt class-specific models, a majority voting strategy is used for classification. The proposed framework is extensively evaluated for the task of image set classification based face recognition on Honda/UCSD, CMU Mobo, YouTube Celebrities and a Kinect dataset. Our experimental results and comparisons with existing state-of-the-art methods show that the proposed method consistently achieves the best performance on all these datasets.
{"title":"Learning Non-linear Reconstruction Models for Image Set Classification","authors":"Munawar Hayat, Bennamoun, S. An","doi":"10.1109/CVPR.2014.246","DOIUrl":"https://doi.org/10.1109/CVPR.2014.246","url":null,"abstract":"We propose a deep learning framework for image set classification with application to face recognition. An Adaptive Deep Network Template (ADNT) is defined whose parameters are initialized by performing unsupervised pre-training in a layer-wise fashion using Gaussian Restricted Boltzmann Machines (GRBMs). The pre-initialized ADNT is then separately trained for images of each class and class-specific models are learnt. Based on the minimum reconstruction error from the learnt class-specific models, a majority voting strategy is used for classification. The proposed framework is extensively evaluated for the task of image set classification based face recognition on Honda/UCSD, CMU Mobo, YouTube Celebrities and a Kinect dataset. Our experimental results and comparisons with existing state-of-the-art methods show that the proposed method consistently achieves the best performance on all these datasets.","PeriodicalId":319578,"journal":{"name":"2014 IEEE Conference on Computer Vision and Pattern Recognition","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116606524","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}
Jaesik Park, Sudipta N. Sinha, Y. Matsushita, Yu-Wing Tai, In-So Kweon
We show that a non-isotropic near point light source rigidly attached to a camera can be calibrated using multiple images of a weakly textured planar scene. We prove that if the radiant intensity distribution (RID) of a light source is radially symmetric with respect to its dominant direction, then the shading observed on a Lambertian scene plane is bilaterally symmetric with respect to a 2D line on the plane. The symmetry axis detected in an image provides a linear constraint for estimating the dominant light axis. The light position and RID parameters can then be estimated using a linear method. Specular highlights if available can also be used for light position estimation. We also extend our method to handle non-Lambertian reflectances which we model using a biquadratic BRDF. We have evaluated our method on synthetic data quantitavely. Our experiments on real scenes show that our method works well in practice and enables light calibration without the need of a specialized hardware.
{"title":"Calibrating a Non-isotropic Near Point Light Source Using a Plane","authors":"Jaesik Park, Sudipta N. Sinha, Y. Matsushita, Yu-Wing Tai, In-So Kweon","doi":"10.1109/CVPR.2014.290","DOIUrl":"https://doi.org/10.1109/CVPR.2014.290","url":null,"abstract":"We show that a non-isotropic near point light source rigidly attached to a camera can be calibrated using multiple images of a weakly textured planar scene. We prove that if the radiant intensity distribution (RID) of a light source is radially symmetric with respect to its dominant direction, then the shading observed on a Lambertian scene plane is bilaterally symmetric with respect to a 2D line on the plane. The symmetry axis detected in an image provides a linear constraint for estimating the dominant light axis. The light position and RID parameters can then be estimated using a linear method. Specular highlights if available can also be used for light position estimation. We also extend our method to handle non-Lambertian reflectances which we model using a biquadratic BRDF. We have evaluated our method on synthetic data quantitavely. Our experiments on real scenes show that our method works well in practice and enables light calibration without the need of a specialized hardware.","PeriodicalId":319578,"journal":{"name":"2014 IEEE Conference on Computer Vision and Pattern Recognition","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117003511","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}
Xióngbiao Luó, Ying Wan, Xiangjian He, Jie Yang, K. Mori
The paper proposes a diversity-enhanced condensation algorithm to address the particle impoverishment problem which stochastic filtering usually suffers from. The particle diversity plays an important role as it affects the performance of filtering. Although the condensation algorithm is widely used in computer vision, it easily gets trapped in local minima due to the particle degeneracy. We introduce a modified evolutionary computing method, adaptive differential evolution, to resolve the particle impoverishment under a proper size of particle population. We apply our proposed method to endoscope tracking for estimating three-dimensional motion of the endoscopic camera. The experimental results demonstrate that our proposed method offers more robust and accurate tracking than previous methods. The current tracking smoothness and error were significantly reduced from (3.7, 4.8) to (2.3 mm, 3.2 mm), which approximates the clinical requirement of 3.0 mm.
针对随机滤波中存在的粒子贫困化问题，提出了一种多样性增强凝聚算法。粒子多样性是影响过滤性能的重要因素。虽然凝聚算法在计算机视觉中得到了广泛的应用，但由于粒子的简并性，它很容易陷入局部极小值。提出了一种改进的进化计算方法——自适应差分进化，以解决在适当的粒子种群规模下的粒子贫困化问题。我们将该方法应用于内窥镜跟踪，用于估计内窥镜相机的三维运动。实验结果表明，该方法具有较好的鲁棒性和准确性。电流跟踪平滑度和误差从(3.7,4.8)显著降低到(2.3 mm, 3.2 mm)，接近临床要求的3.0 mm。
{"title":"Diversity-Enhanced Condensation Algorithm and Its Application for Robust and Accurate Endoscope Three-Dimensional Motion Tracking","authors":"Xióngbiao Luó, Ying Wan, Xiangjian He, Jie Yang, K. Mori","doi":"10.1109/CVPR.2014.163","DOIUrl":"https://doi.org/10.1109/CVPR.2014.163","url":null,"abstract":"The paper proposes a diversity-enhanced condensation algorithm to address the particle impoverishment problem which stochastic filtering usually suffers from. The particle diversity plays an important role as it affects the performance of filtering. Although the condensation algorithm is widely used in computer vision, it easily gets trapped in local minima due to the particle degeneracy. We introduce a modified evolutionary computing method, adaptive differential evolution, to resolve the particle impoverishment under a proper size of particle population. We apply our proposed method to endoscope tracking for estimating three-dimensional motion of the endoscopic camera. The experimental results demonstrate that our proposed method offers more robust and accurate tracking than previous methods. The current tracking smoothness and error were significantly reduced from (3.7, 4.8) to (2.3 mm, 3.2 mm), which approximates the clinical requirement of 3.0 mm.","PeriodicalId":319578,"journal":{"name":"2014 IEEE Conference on Computer Vision and Pattern Recognition","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129545138","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：