Results 1 - 10
of
39
Image Segmentation Evaluation: A Survey of Unsupervised Methods
, 2008
"... Image segmentation is an important processing step in many image, video and computer vision applications. Extensive research has been done in creating many different approaches and algorithms for image segmentation, but it is still difficult to assess whether one algorithm produces more accurate seg ..."
Abstract
-
Cited by 81 (0 self)
- Add to MetaCart
Image segmentation is an important processing step in many image, video and computer vision applications. Extensive research has been done in creating many different approaches and algorithms for image segmentation, but it is still difficult to assess whether one algorithm produces more accurate segmentations than another, whether it be for a particular image or set of images, or more generally, for a whole class of images. To date, the most common method for evaluating the effectiveness of a segmentation method is subjective evaluation, in which a human visually compares the image segmentation results for separate segmentation algorithms, which is a tedious process and inherently limits the depth of evaluation to a relatively small number of segmentation comparisons over a predetermined set of images. Another common evaluation alternative is supervised evaluation, in which a segmented image is compared against a manually-segmented or pre-processed reference image. Evaluation methods that require user assistance, such as subjective evaluation and supervised evaluation, are infeasible in many vision applications, so unsupervised methods are necessary. Unsupervised evaluation enables the objective comparison of both different segmentation methods and different parameterizations of a single method, without requiring human visual comparisons or comparison with a manually-segmented or pre-processed reference image. Additionally, unsupervised methods generate results for individual images and images whose characteristics
Moving object detection in spatial domain using background removal techniques -- State-of-art
- COMPUTER. SCI
, 2008
"... Identifying moving objects is a critical task for many computer vision applications; it provides a classification of the pixels into either foreground or background. A common approach used to achieve such classification is background removal. Even though there exist numerous of background removal a ..."
Abstract
-
Cited by 45 (0 self)
- Add to MetaCart
(Show Context)
Identifying moving objects is a critical task for many computer vision applications; it provides a classification of the pixels into either foreground or background. A common approach used to achieve such classification is background removal. Even though there exist numerous of background removal algorithms in the literature, most of them follow a simple flow diagram, passing through four major steps, which are pre-processing, background modelling, foreground detection and data validation. In this paper, we survey many existing schemes in the literature of background removal, surveying the common pre-processing algorithms used in different situations, presenting different background models, and the most commonly used ways to update such models and how they can be initialized. We also survey how to measure the performance of any moving object detection algorithm, whether the ground truth data is available or not, presenting performance metrics commonly used in both cases.
A co-evaluation framework for improving segmentation evaluation
- Proc. SPIESignal Processing, Sensor Fusion and Target Recognition
, 2005
"... Object segmentation is an important preprocessing step for many target recognition applications. Many segmentation methods have been studied, but there is still no satisfactory effectiveness measure which makes it hard to compare different segmentation methods, or even different parameterizations of ..."
Abstract
-
Cited by 12 (3 self)
- Add to MetaCart
Object segmentation is an important preprocessing step for many target recognition applications. Many segmentation methods have been studied, but there is still no satisfactory effectiveness measure which makes it hard to compare different segmentation methods, or even different parameterizations of a single method. A good segmentation evaluation method not only would enable different approaches to be compared, but could also be integrated within the target recognition system to adaptively select the appropriate granularity of the segmentation which in turn could improve the recognition accuracy. A few stand-alone effectiveness measures have been proposed, but these measures examine different fundamental criteria of the objects, or examine the same criteria in a different fashion, so they usually work well in some cases, but poorly in the others. We propose a co-evaluation framework, in which different effectiveness measures judge the performance of the segmentation in different ways, and their measures are combined by using a machine learning approach which coalesces the results. Experimental results demonstrate that our method performs better than the existing methods.
Towards perceptually driven segmentation evaluation metrics
- In Proc. of Conference on Computer Vision And Pattern Recognition
, 2004
"... To be reliable, an automatic segmentation evaluation metric has to be validated by subjective tests. In this paper, a formal protocol for subjective tests for segmentation quality assessment is presented. The most common artifacts produced by segmentation algorithms are identified and an extensive a ..."
Abstract
-
Cited by 10 (2 self)
- Add to MetaCart
(Show Context)
To be reliable, an automatic segmentation evaluation metric has to be validated by subjective tests. In this paper, a formal protocol for subjective tests for segmentation quality assessment is presented. The most common artifacts produced by segmentation algorithms are identified and an extensive analysis of their effects on the perceived quality is performed. A psychophysical experiment was performed to assess the quality of video with segmentation errors. The results show how an objective segmentation evaluation metric can be defined as a function of various error types. 1.
Meta-Evaluation of Image Segmentation Using Machine Learning
"... Image segmentation is a fundamental step in many computer vision applications. Generally, the choice of a segmentation algorithm, or parameterization of a given algorithm, is selected at the application level and fixed for all images within that application. Our goal is to create a stand-alone metho ..."
Abstract
-
Cited by 8 (2 self)
- Add to MetaCart
(Show Context)
Image segmentation is a fundamental step in many computer vision applications. Generally, the choice of a segmentation algorithm, or parameterization of a given algorithm, is selected at the application level and fixed for all images within that application. Our goal is to create a stand-alone method to evaluate segmentation quality. Stand-alone methods have the advantage that they do not require a manually-segmented reference image for comparison, and can therefore be used for real-time evaluation. Current stand-alone evaluation methods often work well for some types of images, but poorly for others. We propose a meta-evaluation method in which any set of base evaluation methods are combined by a machine learning algorithm that coalesces their evaluations based on a learned weighting function, which depends upon the image to be segmented. The training data used by the machine learning algorithm can be labeled by a human, based on similarity to a human-generated reference segmentation, or based upon system-level performance. Experimental results demonstrate that our method performs better than the existing stand-alone segmentation evaluation methods. 1.
An Iterative SuperResolution Reconstruction of Image Sequences using a Bayesian Approach with BTV Prior and Affine Block-Based Registration
- IEEE CRV2006
, 2006
"... Due to translational registration, traditional super-resolution reconstructions can apply only on the sequences that have simple translation motion. This paper reviews the super-resolution algorithm in these two decades and proposes a novel super-resolution reconstruction that that can apply on real ..."
Abstract
-
Cited by 8 (1 self)
- Add to MetaCart
Due to translational registration, traditional super-resolution reconstructions can apply only on the sequences that have simple translation motion. This paper reviews the super-resolution algorithm in these two decades and proposes a novel super-resolution reconstruction that that can apply on real sequences or complex motion sequences. The proposed super-resolution reconstruction uses a high accuracy registration algorithm, the fast affine blockbased registration [42], in the stochastic regularization technique of Bayesian MAP estimation used to compensate the missing measurement information. The experimental results show that the proposed reconstruction can apply on real sequence such as Suzie, Mobile Calendar and Foreman. 1.
A Framework for Evaluating Video Object Segmentation Algorithms
- Proc. CVPR Workshop
, 2006
"... Segmentation of moving objects in image sequences plays an important role in video processing and analy-sis. Evaluating the quality of segmentation results is nec-essary to allow the appropriate selection of segmentation algorithms and to tune their parameters for optimal per-formance. Many segmenta ..."
Abstract
-
Cited by 7 (1 self)
- Add to MetaCart
(Show Context)
Segmentation of moving objects in image sequences plays an important role in video processing and analy-sis. Evaluating the quality of segmentation results is nec-essary to allow the appropriate selection of segmentation algorithms and to tune their parameters for optimal per-formance. Many segmentation algorithms have been pro-posed along with a number of evaluation criteria. Never-theless, no psychophysical experiments evaluating the qual-ity of different video object segmentation results have been conducted. In this paper, a generic framework for segmen-tation quality evaluation is presented. A perceptually driven automatic method for segmentation evaluation is proposed and compared against an existing approach. Moreover, on the basis of subjective results, perceptual factors are intro-duced into the novel objective metric to meet the specificity of different segmentation applications such as video com-pression. Experimental results confirm the efficiency of the proposed evaluation criteria. 1.
Video segmentation: Propagation, validation and aggregation of a preceding graph
- In CVPR
, 2008
"... In this work, video segmentation is viewed as an efficient intra-frame grouping temporally reinforced by a strong inter-frame coherence. Traditional approaches simply regard pixel motions as another prior in the MRF-MAP framework. Since pixel pre-grouping is inefficiently performed on every frame, t ..."
Abstract
-
Cited by 6 (0 self)
- Add to MetaCart
(Show Context)
In this work, video segmentation is viewed as an efficient intra-frame grouping temporally reinforced by a strong inter-frame coherence. Traditional approaches simply regard pixel motions as another prior in the MRF-MAP framework. Since pixel pre-grouping is inefficiently performed on every frame, the strong correlation between inter-frame groupings is largely underutilized. We exploit the inter-frame correlation to propagate trustworthy groupings from the previous frame. A preceding graph is constructed and labeled for the previous frame. It is temporally propagated to the current frame and validated by similarity measures. All unlabeled subgraphs are spatially aggregated for the final grouping. Experimental results show that the proposed approach is highly efficient for spatio-temporal segmentation. It makes good use of temporal correlation and produces satisfactory grouping results. 1.
CONTRIBUTION TO THE ASSESSMENT OF SEGMENTATION QUALITY FOR REMOTE SENSING APPLICATIONS
"... Within object-oriented or segment-based classification approaches the segmentation step is decisive, because the results form the basis for the following classification. Despite known investigations and approaches of quality evaluation for segmentations, the question of how to access this quality wi ..."
Abstract
-
Cited by 6 (0 self)
- Add to MetaCart
(Show Context)
Within object-oriented or segment-based classification approaches the segmentation step is decisive, because the results form the basis for the following classification. Despite known investigations and approaches of quality evaluation for segmentations, the question of how to access this quality with respect to remote sensing applications is not yet completely answered. This contribution therefore addresses this topic. 1
ON EVALUATING METRICS FOR VIDEO SEGMENTATION ALGORITHMS
"... Evaluation is a central issue in the design, implementation, and performance assessment of all systems. Recently, a number of metrics have been proposed to assess the performance of segmentation algorithms for image and video data. This paper provides an overview of state of the art metrics proposed ..."
Abstract
-
Cited by 6 (1 self)
- Add to MetaCart
(Show Context)
Evaluation is a central issue in the design, implementation, and performance assessment of all systems. Recently, a number of metrics have been proposed to assess the performance of segmentation algorithms for image and video data. This paper provides an overview of state of the art metrics proposed so-far, and introduces a new and efficient such metric. Doing so, subjective experiments are carried out to derive a perceptual metric. As a result, it also provides a comparison of performance of segmentation assessment metrics for different video object segmentation techniques. 1.
