Sensors that measure their motion with respect to the surrounding environment (ego-motion sensors) can be broadly classified into two categories. First is inertial sensors such as accelerometers. In order to estimate position and velocity, these sensors integrate the measured acceleration, which often results in accumulation of large errors over time. Second, camera-based approaches such as SLAM that can measure position directly, but their performance depends on the surrounding scene's properties. These approaches cannot function reliably if the scene has low frequency textures or small depth variations. We present a novel ego-motion sensor called SpeDo that addresses these fundamental limitations. SpeDo is based on using coherent light sources and cameras with large defocus. Coherent light, on interacting with a scene, creates a high frequency interferometric pattern in the captured images, called speckle. We develop a theoretical model for speckle flow (motion of speckle as a function of sensor motion), and show that it is quasi-invariant to surrounding scene's properties. As a result, SpeDo can measure ego-motion (not derivative of motion) simply by estimating optical flow at a few image locations. We have built a low-cost and compact hardware prototype of SpeDo and demonstrated high precision 6 DOF ego-motion estimation for complex trajectories in scenarios where the scene properties are challenging (e.g., repeating or no texture) as well as unknown.
{"title":"SpeDo: 6 DOF Ego-Motion Sensor Using Speckle Defocus Imaging","authors":"Kensei Jo, Mohit Gupta, S. Nayar","doi":"10.1109/ICCV.2015.491","DOIUrl":"https://doi.org/10.1109/ICCV.2015.491","url":null,"abstract":"Sensors that measure their motion with respect to the surrounding environment (ego-motion sensors) can be broadly classified into two categories. First is inertial sensors such as accelerometers. In order to estimate position and velocity, these sensors integrate the measured acceleration, which often results in accumulation of large errors over time. Second, camera-based approaches such as SLAM that can measure position directly, but their performance depends on the surrounding scene's properties. These approaches cannot function reliably if the scene has low frequency textures or small depth variations. We present a novel ego-motion sensor called SpeDo that addresses these fundamental limitations. SpeDo is based on using coherent light sources and cameras with large defocus. Coherent light, on interacting with a scene, creates a high frequency interferometric pattern in the captured images, called speckle. We develop a theoretical model for speckle flow (motion of speckle as a function of sensor motion), and show that it is quasi-invariant to surrounding scene's properties. As a result, SpeDo can measure ego-motion (not derivative of motion) simply by estimating optical flow at a few image locations. We have built a low-cost and compact hardware prototype of SpeDo and demonstrated high precision 6 DOF ego-motion estimation for complex trajectories in scenarios where the scene properties are challenging (e.g., repeating or no texture) as well as unknown.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"22 1","pages":"4319-4327"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89830418","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}
Christos Sagonas, Yannis Panagakis, S. Zafeiriou, M. Pantic
Recently, it has been shown that excellent results can be achieved in both facial landmark localization and pose-invariant face recognition. These breakthroughs are attributed to the efforts of the community to manually annotate facial images in many different poses and to collect 3D facial data. In this paper, we propose a novel method for joint frontal view reconstruction and landmark localization using a small set of frontal images only. By observing that the frontal facial image is the one having the minimum rank of all different poses, an appropriate model which is able to jointly recover the frontalized version of the face as well as the facial landmarks is devised. To this end, a suitable optimization problem, involving the minimization of the nuclear norm and the matrix l1 norm is solved. The proposed method is assessed in frontal face reconstruction, face landmark localization, pose-invariant face recognition, and face verification in unconstrained conditions. The relevant experiments have been conducted on 8 databases. The experimental results demonstrate the effectiveness of the proposed method in comparison to the state-of-the-art methods for the target problems.
{"title":"Robust Statistical Face Frontalization","authors":"Christos Sagonas, Yannis Panagakis, S. Zafeiriou, M. Pantic","doi":"10.1109/ICCV.2015.441","DOIUrl":"https://doi.org/10.1109/ICCV.2015.441","url":null,"abstract":"Recently, it has been shown that excellent results can be achieved in both facial landmark localization and pose-invariant face recognition. These breakthroughs are attributed to the efforts of the community to manually annotate facial images in many different poses and to collect 3D facial data. In this paper, we propose a novel method for joint frontal view reconstruction and landmark localization using a small set of frontal images only. By observing that the frontal facial image is the one having the minimum rank of all different poses, an appropriate model which is able to jointly recover the frontalized version of the face as well as the facial landmarks is devised. To this end, a suitable optimization problem, involving the minimization of the nuclear norm and the matrix l1 norm is solved. The proposed method is assessed in frontal face reconstruction, face landmark localization, pose-invariant face recognition, and face verification in unconstrained conditions. The relevant experiments have been conducted on 8 databases. The experimental results demonstrate the effectiveness of the proposed method in comparison to the state-of-the-art methods for the target problems.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"20 1","pages":"3871-3879"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91533973","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}
Markov random fields are widely used to model many computer vision problems that can be cast in an energy minimization framework composed of unary and pairwise potentials. While computationally tractable discrete optimizers such as Graph Cuts and belief propagation (BP) exist for multi-label discrete problems, they still face prohibitively high computational challenges when the labels reside in a huge or very densely sampled space. Integrating key ideas from PatchMatch of effective particle propagation and resampling, PatchMatch belief propagation (PMBP) has been demonstrated to have good performance in addressing continuous labeling problems and runs orders of magnitude faster than Particle BP (PBP). However, the quality of the PMBP solution is tightly coupled with the local window size, over which the raw data cost is aggregated to mitigate ambiguity in the data constraint. This dependency heavily influences the overall complexity, increasing linearly with the window size. This paper proposes a novel algorithm called sped-up PMBP (SPM-BP) to tackle this critical computational bottleneck and speeds up PMBP by 50-100 times. The crux of SPM-BP is on unifying efficient filter-based cost aggregation and message passing with PatchMatch-based particle generation in a highly effective way. Though simple in its formulation, SPM-BP achieves superior performance for sub-pixel accurate stereo and optical-flow on benchmark datasets when compared with more complex and task-specific approaches.
{"title":"SPM-BP: Sped-Up PatchMatch Belief Propagation for Continuous MRFs","authors":"Yu Li, Dongbo Min, M. S. Brown, M. Do, Jiangbo Lu","doi":"10.1109/ICCV.2015.456","DOIUrl":"https://doi.org/10.1109/ICCV.2015.456","url":null,"abstract":"Markov random fields are widely used to model many computer vision problems that can be cast in an energy minimization framework composed of unary and pairwise potentials. While computationally tractable discrete optimizers such as Graph Cuts and belief propagation (BP) exist for multi-label discrete problems, they still face prohibitively high computational challenges when the labels reside in a huge or very densely sampled space. Integrating key ideas from PatchMatch of effective particle propagation and resampling, PatchMatch belief propagation (PMBP) has been demonstrated to have good performance in addressing continuous labeling problems and runs orders of magnitude faster than Particle BP (PBP). However, the quality of the PMBP solution is tightly coupled with the local window size, over which the raw data cost is aggregated to mitigate ambiguity in the data constraint. This dependency heavily influences the overall complexity, increasing linearly with the window size. This paper proposes a novel algorithm called sped-up PMBP (SPM-BP) to tackle this critical computational bottleneck and speeds up PMBP by 50-100 times. The crux of SPM-BP is on unifying efficient filter-based cost aggregation and message passing with PatchMatch-based particle generation in a highly effective way. Though simple in its formulation, SPM-BP achieves superior performance for sub-pixel accurate stereo and optical-flow on benchmark datasets when compared with more complex and task-specific approaches.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"40 1","pages":"4006-4014"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87904923","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}
Defocus blur usually causes performance degradation in establishing the visual correspondence between stereo images. We propose a blur-aware disparity estimation method that is robust to the mismatch of focus in stereo images. The relative blur resulting from the mismatch of focus between stereo images is approximated as the difference of the square diameters of the blur kernels. Based on the defocus and stereo model, we propose the relative blur versus disparity (RBD) model that characterizes the relative blur as a second-order polynomial function of disparity. Our method alternates between RBD model update and disparity update in each iteration. The RBD model in return refines the disparity estimation by updating the matching cost and aggregation weight to compensate the mismatch of focus. Experiments using both synthesized and real datasets demonstrate the effectiveness of our proposed algorithm.
{"title":"Blur-Aware Disparity Estimation from Defocus Stereo Images","authors":"Ching-Hui Chen, Hui Zhou, T. Ahonen","doi":"10.1109/ICCV.2015.104","DOIUrl":"https://doi.org/10.1109/ICCV.2015.104","url":null,"abstract":"Defocus blur usually causes performance degradation in establishing the visual correspondence between stereo images. We propose a blur-aware disparity estimation method that is robust to the mismatch of focus in stereo images. The relative blur resulting from the mismatch of focus between stereo images is approximated as the difference of the square diameters of the blur kernels. Based on the defocus and stereo model, we propose the relative blur versus disparity (RBD) model that characterizes the relative blur as a second-order polynomial function of disparity. Our method alternates between RBD model update and disparity update in each iteration. The RBD model in return refines the disparity estimation by updating the matching cost and aggregation weight to compensate the mismatch of focus. Experiments using both synthesized and real datasets demonstrate the effectiveness of our proposed algorithm.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"14 1","pages":"855-863"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86859526","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}
Attributes are mid-level semantic properties of objects. Recent research has shown that visual attributes can benefit many traditional learning problems in computer vision community. However, attribute learning is still a challenging problem as the attributes may not always be predictable directly from input images and the variation of visual attributes is sometimes large across categories. In this paper, we propose a unified multiplicative framework for attribute learning, which tackles the key problems. Specifically, images and category information are jointly projected into a shared feature space, where the latent factors are disentangled and multiplied for attribute prediction. The resulting attribute classifier is category-specific instead of being shared by all categories. Moreover, our method can leverage auxiliary data to enhance the predictive ability of attribute classifiers, reducing the effort of instance-level attribute annotation to some extent. Experimental results show that our method achieves superior performance on both instance-level and category-level attribute prediction. For zero-shot learning based on attributes, our method significantly improves the state-of-the-art performance on AwA dataset and achieves comparable performance on CUB dataset.
{"title":"A Unified Multiplicative Framework for Attribute Learning","authors":"K. Liang, Hong-Yi Chang, S. Shan, Xilin Chen","doi":"10.1109/ICCV.2015.288","DOIUrl":"https://doi.org/10.1109/ICCV.2015.288","url":null,"abstract":"Attributes are mid-level semantic properties of objects. Recent research has shown that visual attributes can benefit many traditional learning problems in computer vision community. However, attribute learning is still a challenging problem as the attributes may not always be predictable directly from input images and the variation of visual attributes is sometimes large across categories. In this paper, we propose a unified multiplicative framework for attribute learning, which tackles the key problems. Specifically, images and category information are jointly projected into a shared feature space, where the latent factors are disentangled and multiplied for attribute prediction. The resulting attribute classifier is category-specific instead of being shared by all categories. Moreover, our method can leverage auxiliary data to enhance the predictive ability of attribute classifiers, reducing the effort of instance-level attribute annotation to some extent. Experimental results show that our method achieves superior performance on both instance-level and category-level attribute prediction. For zero-shot learning based on attributes, our method significantly improves the state-of-the-art performance on AwA dataset and achieves comparable performance on CUB dataset.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"1 1","pages":"2506-2514"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89017803","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}
In this paper we tackle the problem of capturing the dense, detailed 3D geometry of generic, complex non-rigid meshes using a single RGB-only commodity video camera and a direct approach. While robust and even real-time solutions exist to this problem if the observed scene is static, for non-rigid dense shape capture current systems are typically restricted to the use of complex multi-camera rigs, take advantage of the additional depth channel available in RGB-D cameras, or deal with specific shapes such as faces or planar surfaces. In contrast, our method makes use of a single RGB video as input, it can capture the deformations of generic shapes, and the depth estimation is dense, per-pixel and direct. We first compute a dense 3D template of the shape of the object, using a short rigid sequence, and subsequently perform online reconstruction of the non-rigid mesh as it evolves over time. Our energy optimization approach minimizes a robust photometric cost that simultaneously estimates the temporal correspondences and 3D deformations with respect to the template mesh. In our experimental evaluation we show a range of qualitative results on novel datasets, we compare against an existing method that requires multi-frame optical flow, and perform a quantitative evaluation against other template-based approaches on a ground truth dataset.
{"title":"Direct, Dense, and Deformable: Template-Based Non-rigid 3D Reconstruction from RGB Video","authors":"Rui Yu, Chris Russell, N. Campbell, L. Agapito","doi":"10.1109/ICCV.2015.111","DOIUrl":"https://doi.org/10.1109/ICCV.2015.111","url":null,"abstract":"In this paper we tackle the problem of capturing the dense, detailed 3D geometry of generic, complex non-rigid meshes using a single RGB-only commodity video camera and a direct approach. While robust and even real-time solutions exist to this problem if the observed scene is static, for non-rigid dense shape capture current systems are typically restricted to the use of complex multi-camera rigs, take advantage of the additional depth channel available in RGB-D cameras, or deal with specific shapes such as faces or planar surfaces. In contrast, our method makes use of a single RGB video as input, it can capture the deformations of generic shapes, and the depth estimation is dense, per-pixel and direct. We first compute a dense 3D template of the shape of the object, using a short rigid sequence, and subsequently perform online reconstruction of the non-rigid mesh as it evolves over time. Our energy optimization approach minimizes a robust photometric cost that simultaneously estimates the temporal correspondences and 3D deformations with respect to the template mesh. In our experimental evaluation we show a range of qualitative results on novel datasets, we compare against an existing method that requires multi-frame optical flow, and perform a quantitative evaluation against other template-based approaches on a ground truth dataset.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"39 1","pages":"918-926"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83581168","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}
Recently, exemplar based approaches have been successfully applied for face detection in the wild. Contrary to traditional approaches that model face variations from a large and diverse set of training examples, exemplar-based approaches use a collection of discriminatively trained exemplars for detection. In this paradigm, each exemplar casts a vote using retrieval framework and generalized Hough voting, to locate the faces in the target image. The advantage of this approach is that by having a large database that covers all possible variations, faces in challenging conditions can be detected without having to learn explicit models for different variations. Current schemes, however, make an assumption of independence between the visual words, ignoring their relations in the process. They also ignore the spatial consistency of the visual words. Consequently, every exemplar word contributes equally during voting regardless of its location. In this paper, we propose a novel approach that incorporates higher order information in the voting process. We discover visual phrases that contain semantically related visual words and exploit them for detection along with the visual words. For spatial consistency, we estimate the spatial distribution of visual words and phrases from the entire database and then weigh their occurrence in exemplars. This ensures that a visual word or a phrase in an exemplar makes a major contribution only if it occurs at its semantic location, thereby suppressing the noise significantly. We perform extensive experiments on standard FDDB, AFW and G-album datasets and show significant improvement over previous exemplar approaches.
{"title":"Visual Phrases for Exemplar Face Detection","authors":"Vijay Kumar, A. Namboodiri, C. V. Jawahar","doi":"10.1109/ICCV.2015.231","DOIUrl":"https://doi.org/10.1109/ICCV.2015.231","url":null,"abstract":"Recently, exemplar based approaches have been successfully applied for face detection in the wild. Contrary to traditional approaches that model face variations from a large and diverse set of training examples, exemplar-based approaches use a collection of discriminatively trained exemplars for detection. In this paradigm, each exemplar casts a vote using retrieval framework and generalized Hough voting, to locate the faces in the target image. The advantage of this approach is that by having a large database that covers all possible variations, faces in challenging conditions can be detected without having to learn explicit models for different variations. Current schemes, however, make an assumption of independence between the visual words, ignoring their relations in the process. They also ignore the spatial consistency of the visual words. Consequently, every exemplar word contributes equally during voting regardless of its location. In this paper, we propose a novel approach that incorporates higher order information in the voting process. We discover visual phrases that contain semantically related visual words and exploit them for detection along with the visual words. For spatial consistency, we estimate the spatial distribution of visual words and phrases from the entire database and then weigh their occurrence in exemplars. This ensures that a visual word or a phrase in an exemplar makes a major contribution only if it occurs at its semantic location, thereby suppressing the noise significantly. We perform extensive experiments on standard FDDB, AFW and G-album datasets and show significant improvement over previous exemplar approaches.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"54 1","pages":"1994-2002"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76195154","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}
Takahiro Hasegawa, Mitsuru Ambai, Kohta Ishikawa, G. Koutaki, Yuji Yamauchi, Takayoshi Yamashita, H. Fujiyoshi
We propose a method for estimating multiple-hypothesis affine regions from a keypoint by using an anisotropic Laplacian-of-Gaussian (LoG) filter. Although conventional affine region detectors, such as Hessian/Harris-Affine, iterate to find an affine region that fits a given image patch, such iterative searching is adversely affected by an initial point. To avoid this problem, we allow multiple detections from a single keypoint. We demonstrate that the responses of all possible anisotropic LoG filters can be efficiently computed by factorizing them in a similar manner to spectral SIFT. A large number of LoG filters that are densely sampled in a parameter space are reconstructed by a weighted combination of a limited number of representative filters, called "eigenfilters", by using singular value decomposition. Also, the reconstructed filter responses of the sampled parameters can be interpolated to a continuous representation by using a series of proper functions. This results in efficient multiple extrema searching in a continuous space. Experiments revealed that our method has higher repeatability than the conventional methods.
{"title":"Multiple-Hypothesis Affine Region Estimation with Anisotropic LoG Filters","authors":"Takahiro Hasegawa, Mitsuru Ambai, Kohta Ishikawa, G. Koutaki, Yuji Yamauchi, Takayoshi Yamashita, H. Fujiyoshi","doi":"10.1109/ICCV.2015.74","DOIUrl":"https://doi.org/10.1109/ICCV.2015.74","url":null,"abstract":"We propose a method for estimating multiple-hypothesis affine regions from a keypoint by using an anisotropic Laplacian-of-Gaussian (LoG) filter. Although conventional affine region detectors, such as Hessian/Harris-Affine, iterate to find an affine region that fits a given image patch, such iterative searching is adversely affected by an initial point. To avoid this problem, we allow multiple detections from a single keypoint. We demonstrate that the responses of all possible anisotropic LoG filters can be efficiently computed by factorizing them in a similar manner to spectral SIFT. A large number of LoG filters that are densely sampled in a parameter space are reconstructed by a weighted combination of a limited number of representative filters, called \"eigenfilters\", by using singular value decomposition. Also, the reconstructed filter responses of the sampled parameters can be interpolated to a continuous representation by using a series of proper functions. This results in efficient multiple extrema searching in a continuous space. Experiments revealed that our method has higher repeatability than the conventional methods.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"389 1","pages":"585-593"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79572711","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}
S. H. Rezatofighi, Anton Milan, Zhen Zhang, Javen Qinfeng Shi, A. Dick, I. Reid
In this paper, we revisit the joint probabilistic data association (JPDA) technique and propose a novel solution based on recent developments in finding the m-best solutions to an integer linear program. The key advantage of this approach is that it makes JPDA computationally tractable in applications with high target and/or clutter density, such as spot tracking in fluorescence microscopy sequences and pedestrian tracking in surveillance footage. We also show that our JPDA algorithm embedded in a simple tracking framework is surprisingly competitive with state-of-the-art global tracking methods in these two applications, while needing considerably less processing time.
{"title":"Joint Probabilistic Data Association Revisited","authors":"S. H. Rezatofighi, Anton Milan, Zhen Zhang, Javen Qinfeng Shi, A. Dick, I. Reid","doi":"10.1109/ICCV.2015.349","DOIUrl":"https://doi.org/10.1109/ICCV.2015.349","url":null,"abstract":"In this paper, we revisit the joint probabilistic data association (JPDA) technique and propose a novel solution based on recent developments in finding the m-best solutions to an integer linear program. The key advantage of this approach is that it makes JPDA computationally tractable in applications with high target and/or clutter density, such as spot tracking in fluorescence microscopy sequences and pedestrian tracking in surveillance footage. We also show that our JPDA algorithm embedded in a simple tracking framework is surprisingly competitive with state-of-the-art global tracking methods in these two applications, while needing considerably less processing time.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"3 5 1","pages":"3047-3055"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88329349","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}
Statistical shape and appearance models are often based on the accurate identification of one-to-one correspondences in a training data set. At the same time, the determination of these corresponding landmarks is the most challenging part of such methods. Hufnagel etal developed an alternative method using correspondence probabilities for a statistical shape model. We propose the use of probabilistic correspondences for statistical appearance models by incorporating appearance information into the framework. A point-based representation is employed representing the image by a set of vectors assembling position and appearances. Using probabilistic correspondences between these multi-dimensional feature vectors eliminates the need for extensive preprocessing to find corresponding landmarks and reduces the dependence of the generated model on the landmark positions. Then, a maximum a-posteriori approach is used to derive a single global optimization criterion with respect to model parameters and observation dependent parameters, that directly affects shape and appearance information of the considered structures. Model generation and fitting can be expressed by optimizing the same criterion. The developed framework describes the modeling process in a concise and flexible mathematical way and allows for additional constraints as topological regularity in the modeling process. Furthermore, it eliminates the demand for costly correspondence determination. We apply the model for segmentation and landmark identification in hand X-ray images, where segmentation information is modeled as further features in the vectorial image representation. The results demonstrate the feasibility of the model to reconstruct contours and landmarks for unseen test images. Furthermore, we apply the model for tissue classification, where a model is generated for healthy brain tissue using 2D MRI slices. Applying the model to images of stroke patients the probabilistic correspondences are used to classify between healthy and pathological structures. The results demonstrate the ability of the probabilistic model to recognize healthy and pathological tissue automatically.
{"title":"Probabilistic Appearance Models for Segmentation and Classification","authors":"J. Krüger, J. Ehrhardt, H. Handels","doi":"10.1109/ICCV.2015.198","DOIUrl":"https://doi.org/10.1109/ICCV.2015.198","url":null,"abstract":"Statistical shape and appearance models are often based on the accurate identification of one-to-one correspondences in a training data set. At the same time, the determination of these corresponding landmarks is the most challenging part of such methods. Hufnagel etal developed an alternative method using correspondence probabilities for a statistical shape model. We propose the use of probabilistic correspondences for statistical appearance models by incorporating appearance information into the framework. A point-based representation is employed representing the image by a set of vectors assembling position and appearances. Using probabilistic correspondences between these multi-dimensional feature vectors eliminates the need for extensive preprocessing to find corresponding landmarks and reduces the dependence of the generated model on the landmark positions. Then, a maximum a-posteriori approach is used to derive a single global optimization criterion with respect to model parameters and observation dependent parameters, that directly affects shape and appearance information of the considered structures. Model generation and fitting can be expressed by optimizing the same criterion. The developed framework describes the modeling process in a concise and flexible mathematical way and allows for additional constraints as topological regularity in the modeling process. Furthermore, it eliminates the demand for costly correspondence determination. We apply the model for segmentation and landmark identification in hand X-ray images, where segmentation information is modeled as further features in the vectorial image representation. The results demonstrate the feasibility of the model to reconstruct contours and landmarks for unseen test images. Furthermore, we apply the model for tissue classification, where a model is generated for healthy brain tissue using 2D MRI slices. Applying the model to images of stroke patients the probabilistic correspondences are used to classify between healthy and pathological structures. The results demonstrate the ability of the probabilistic model to recognize healthy and pathological tissue automatically.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"59 1","pages":"1698-1706"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88433502","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：