Results 1  10
of
186
Global Minimum for Active Contour Models: A Minimal Path Approach
, 1997
"... A new boundary detection approach for shape modeling is presented. It detects the global minimum of an active contour model’s energy between two end points. Initialization is made easier and the curve is not trapped at a local minimum by spurious edges. We modify the “snake” energy by including the ..."
Abstract

Cited by 238 (70 self)
 Add to MetaCart
(Show Context)
A new boundary detection approach for shape modeling is presented. It detects the global minimum of an active contour model’s energy between two end points. Initialization is made easier and the curve is not trapped at a local minimum by spurious edges. We modify the “snake” energy by including the internal regularization term in the external potential term. Our method is based on finding a path of minimal length in a Riemannian metric. We then make use of a new efficient numerical method to find this shortest path. It is shown that the proposed energy, though based only on a potential integrated along the curve, imposes a regularization effect like snakes. We explore the relation between the maximum curvature along the resulting contour and the potential generated from the image. The method is capable to close contours, given only one point on the objects’ boundary by using a topologybased saddle search routine. We show examples of our method applied to real aerial and medical images.
An Unbiased Detector of Curvilinear Structures
, 1996
"... The extraction of curvilinear structures is an important lowlevel operation in computer vision that has many applications. Most existing operators use a simple model for the line that is to be extracted, i.e., they do not take into account the surroundings of a line. This leads to the undesired con ..."
Abstract

Cited by 209 (11 self)
 Add to MetaCart
The extraction of curvilinear structures is an important lowlevel operation in computer vision that has many applications. Most existing operators use a simple model for the line that is to be extracted, i.e., they do not take into account the surroundings of a line. This leads to the undesired consequence that the line will be extracted in the wrong position whenever a line with different lateral contrast is extracted. In contrast, the algorithm proposed in this paper uses an explicit model for lines and their surroundings. By analyzing the scalespace behaviour of a model line profile, it is shown how the bias that is induced by asymmetrical lines can be removed. Furthermore, the algorithm not only returns the precise subpixel line position, but also the width of the line for each line point, also with subpixel accuracy.
Finding deformable shapes using loopy belief propogation.
 In European Conference on Computer Vision,
, 2002
"... ..."
(Show Context)
A survey of video processing techniques for traffic applications
 Image and Vision Computing
, 2003
"... Video sensors become particularly important in traffic applications mainly due to their fast response, easy installation, operation and maintenance, and their ability to monitor wide areas. Research in several fields of traffic applications has resulted in a wealth of video processing and analysis m ..."
Abstract

Cited by 97 (0 self)
 Add to MetaCart
Video sensors become particularly important in traffic applications mainly due to their fast response, easy installation, operation and maintenance, and their ability to monitor wide areas. Research in several fields of traffic applications has resulted in a wealth of video processing and analysis methods. Two of the most demanding and widely studied applications relate to traffic monitoring and automatic vehicle guidance. In general, systems developed for these areas must integrate, amongst their other tasks, the analysis of their static environment (automatic lane finding) and the detection of static or moving obstacles (object detection) within their space of interest. In this paper we present an overview of image processing and analysis tools used in these applications and we relate these tools with complete systems developed for specific traffic applications. More specifically, we categorize processing methods based on the intrinsic organization of their input data (featuredriven, areadriven, or modelbased) and the domain of processing (spatial/frame or temporal/video). Furthermore, we discriminate between the cases of static and mobile camera. Based on this categorization of processing tools, we present representative systems that have been deployed for operation. Thus, the purpose of the paper is threefold. First, to classify imageprocessing methods used in traffic applications. Second, to provide the advantages and disadvantages of these algorithms. Third, from this integrated consideration, to attempt an evaluation of shortcomings and general needs in this field of active research.
Detection of Linear Features in SAR Images: Application to Road Network Extraction
, 1998
"... We propose a twostep algorithm for almost unsupervised detection of linear structures, in particular, main axes in road networks, as seen in synthetic aperture radar (SAR) images. The first step is local and is used to extract linear features from the speckle radar image, which are treated as roads ..."
Abstract

Cited by 90 (4 self)
 Add to MetaCart
We propose a twostep algorithm for almost unsupervised detection of linear structures, in particular, main axes in road networks, as seen in synthetic aperture radar (SAR) images. The first step is local and is used to extract linear features from the speckle radar image, which are treated as roadsegment candidates. We present two local line detectors as well as a method for fusing information from these detectors. In the second global step, we identify the real roads among the segment candidates by defining a Markov random field (MRF) on a set of segments, which introduces contextual knowledge about the shape of road objects. The influence of the parameters on the road detection is studied and results are presented for various real radar images.
Statistical edge detection: learning and evaluating edge cues
 IEEE Transactions on Pattern Analysis and Machine Intelligence
, 2003
"... We formulate edge detection as statistical inference. This statistical edge detection is data driven, unlike standard methods for edge detection which are model based. For any set of edge detection filters (implementing local edge cues) we use presegmented images to learn the probability distributi ..."
Abstract

Cited by 89 (10 self)
 Add to MetaCart
(Show Context)
We formulate edge detection as statistical inference. This statistical edge detection is data driven, unlike standard methods for edge detection which are model based. For any set of edge detection filters (implementing local edge cues) we use presegmented images to learn the probability distributions of filter responses conditioned on whether they are evaluated on or off an edge. Edge detection is formulated as a discrimination task specified by a likelihood ratio test on the filter responses. This approach emphasizes the necessity of modeling the image background (the offedges). We represent the conditional probability distributions nonparametrically and learn them on two different datasets of 100 (Sowerby) and 50 (South Florida) images. Multiple edges cues, including chrominance and multiplescale, are combined by using their joint distributions. Hence this cue combination is optimal in the statistical sense. We evaluate the effectiveness of different visual cues using the Chernoff information and Receiver Operator Characteristic (ROC) curves. This shows that our approach gives quantitatively better results than the Canny edge detector when the image background contains significant clutter. In addition, it enables us to determine the effectiveness of different edge cues and gives quantitative measures for the advantages of multilevel processing, for the use of chrominance, and for the relative effectiveness of different detectors. Furthermore, we show that we can learn these conditional distributions on one dataset and adapt them to the other with only slight degradation of performance without knowing the ground truth on the second dataset. This shows that our results are not purely domain specific. We apply the same approach to the spatial grouping of edge cues and obtain analogies to nonmaximal suppression and hysteresis.
Segmentation and Interpretation of MR Brain Images: An Improved Active Shape Model
, 1997
"... This paper reports a novel method for fully automated segmentation that is based on description of shape and its variation using Point Distribution Models (PDM). An improvement of the Active Shape procedure introduced by Cootes and Taylor to find new examples of previously learned shapes using PDMs ..."
Abstract

Cited by 76 (7 self)
 Add to MetaCart
This paper reports a novel method for fully automated segmentation that is based on description of shape and its variation using Point Distribution Models (PDM). An improvement of the Active Shape procedure introduced by Cootes and Taylor to find new examples of previously learned shapes using PDMs is presented. The new method for segmentation and interpretation of deep neuroanatomic structures such as thalamus, putamen, ventricular system, etc. incorporates a priori knowledge about shapes of the neuroanatomic structures to provide their robust segmentation and labeling in MR brain images. The method was trained in 8 MR brain images and tested in 19 brain images by comparison to observerdefined independent standards. Neuroanatomic structures in all testing images were successfully identified. Computeridentified and observerdefined neuroanatomic structures agreed well. The average labeling error was 7 \Sigma 3%. Border positioning errors were quite small, with the average border posi...
Learning Image Statistics for Bayesian Tracking
 In IEEE International Conference on Computer Vision
, 2001
"... This paper describes a framework for learning probabilistic models of objects and scenes and for exploiting these models for tracking complex, deformable, or articulated objects in image sequences. We focus on the probabilistic tracking of people and learn models of how they appear and move in image ..."
Abstract

Cited by 73 (6 self)
 Add to MetaCart
This paper describes a framework for learning probabilistic models of objects and scenes and for exploiting these models for tracking complex, deformable, or articulated objects in image sequences. We focus on the probabilistic tracking of people and learn models of how they appear and move in images. In particular, we learn the likelihood of observing various spatial and temporal filter responses corresponding to edges, ridges, and motion differences given a model of the person. Similarly, we learn probability distributions over filter responses for general scenes that define a likelihood of observing the filter responses for arbitrary backgrounds. We then derive a probabilistic model for tracking that exploits the ratio between the likelihood that image pixels corresponding to the foreground (person) were generated by an actual person or by some unknown background. The paper extends previous work on learning image statistics and combines it with Bayesian tracking using particle filtering. By combining multiple image cues, and by using learned likelihood models, we demonstrate improved robustness and accuracy when tracking complex objects such as people in monocular image sequences with cluttered scenes and a moving camera.
Object Localization by Bayesian Correlation
"... Maximisation of crosscorrelation is a commonly used principle for intensitybased object localization that gives a single estimate of location. However, to facilitate sequential inference (eg over time or scale) and to allow the representation of ambiguity, it is desirable to represent an entire pr ..."
Abstract

Cited by 67 (2 self)
 Add to MetaCart
Maximisation of crosscorrelation is a commonly used principle for intensitybased object localization that gives a single estimate of location. However, to facilitate sequential inference (eg over time or scale) and to allow the representation of ambiguity, it is desirable to represent an entire probability distribution for object location. Although the crosscorrelation itself (or some function of it) has sometimes been treated as a probability distribution, this is not generally justifiable. Bayesian correlation achieves a consistent probabilistic treatment by combining several developments. The first is the interpretation of correlation matching functions in probabilistic terms, as observation likelihoods. Second, probability distributions of filterbank responses are learned from training examples. Inescapably, responselearning also demands statistical modelling of background intensities, and there are links here with image coding and Independent Component Analysis. Lastly, multiscale processing is achieved, in a Bayesian context, by means of a new algorithm, layered sampling, for which asymptotic properties are derived.
Learning the Statistics of People in Images and Video
 IJCV
, 2001
"... This paper address the problems of modeling the appearance of humans and distinguishing human appearance from the appearance of general scenes. We seek a model of appearance and motion that is generic in that it accounts for the ways in which people's appearance varies and, at the same time, is ..."
Abstract

Cited by 64 (3 self)
 Add to MetaCart
(Show Context)
This paper address the problems of modeling the appearance of humans and distinguishing human appearance from the appearance of general scenes. We seek a model of appearance and motion that is generic in that it accounts for the ways in which people's appearance varies and, at the same time, is specific enough to be useful for tracking people in natural scenes. Given a 3D model of the person projected into an image we model the likelihood of observing various image cues conditioned on the predicted locations and orientations of the limbs. These cues are taken to be steered filter responses corresponding to edges, ridges, and motioncompensated temporal differences. Motivated by work on the statistics of natural scenes, the statistics of these filter responses for human limbs are learned from training images containing handlabeled limb regions. Similarly, the statistics of the filter responses in general scenes are learned to define a "background" distribution. The likelihood of observing a scene given a predicted pose of a person is computed, for each limb, using the likelihood ratio between the learned foreground (person) and background distributions. Adopting a Bayesian formulation allows cues to be combined in a principled way. Furthermore, the use of learned distributions obviates the need for handtuned image noise models and thresholds. The paper provides a detailed analysis of the statistics of how people appear in scenes and provides a connection between work on natural image statistics and the Bayesian tracking of people.