Results 1 - 10
of
15
Multi-Cue Pedestrian Classification With Partial Occlusion Handling
"... This paper presents a novel mixture-of-experts framework for pedestrian classification with partial occlusion handling. The framework involves a set of component-based expert classifiers trained on features derived from intensity, depth and motion. To handle partial occlusion, we compute expert weig ..."
Abstract
-
Cited by 55 (7 self)
- Add to MetaCart
(Show Context)
This paper presents a novel mixture-of-experts framework for pedestrian classification with partial occlusion handling. The framework involves a set of component-based expert classifiers trained on features derived from intensity, depth and motion. To handle partial occlusion, we compute expert weights that are related to the degree of visibility of the associated component. This degree of visibility is determined by examining occlusion boundaries, i.e. discontinuities in depth and motion. Occlusion-dependent component weights allow to focus the combined decision of the mixtureof-experts classifier on the unoccluded body parts. In experiments on extensive real-world data sets, with both partially occluded and non-occluded pedestrians, we obtain significant performance boosts over state-of-the-art approaches by up to a factor of four in reduction of false positives at constant detection rates. The dataset is made public for benchmarking purposes. 1.
Salient Object Detection: A Benchmark
"... Abstract. Several salient object detection approaches have been published which have been assessed using different evaluation scores and datasets resulting in discrepancy in model comparison. This calls for a methodological framework to compare existing models and evaluate their pros and cons. We an ..."
Abstract
-
Cited by 51 (2 self)
- Add to MetaCart
(Show Context)
Abstract. Several salient object detection approaches have been published which have been assessed using different evaluation scores and datasets resulting in discrepancy in model comparison. This calls for a methodological framework to compare existing models and evaluate their pros and cons. We analyze benchmark datasets and scoring techniques and, for the first time, provide a quantitative comparison of 35 stateof-the-art saliency detection models. We find that some models perform consistently better than the others. Saliency models that intend to predict eye fixations perform lower on segmentation datasets compared to salient object detection algorithms. Further, we propose combined models which show that integration of the few best models outperforms all models over other datasets. By analyzing the consistency among the best models and among humans for each scene, we identify the scenes where models or humans fail to detect the most salient object. We highlight the current issues and propose future research directions. 1
Higher-Order Correlation Clustering for Image Segmentation
"... For many of the state-of-the-art computer vision algorithms, image segmentation is an important preprocessing step. As such, several image segmentation algorithms have been proposed, however, with certain reservation due to high computational load and many hand-tuning parameters. Correlation cluster ..."
Abstract
-
Cited by 29 (2 self)
- Add to MetaCart
(Show Context)
For many of the state-of-the-art computer vision algorithms, image segmentation is an important preprocessing step. As such, several image segmentation algorithms have been proposed, however, with certain reservation due to high computational load and many hand-tuning parameters. Correlation clustering, a graphpartitioning algorithm often used in natural language processing and document clustering, has the potential to perform better than previously proposed image segmentation algorithms. We improve the basic correlation clustering formulation by taking into account higher-order cluster relationships. This improves clustering in the presence of local boundary ambiguities. We first apply the pairwise correlation clustering to image segmentation over a pairwise superpixel graph and then develop higher-order correlation clustering over a hypergraph that considers higher-order relations among superpixels. Fast inference is possible by linear programming relaxation, and also effective parameter learning framework by structured support vector machine is possible. Experimental results on various datasets show that the proposed higher-order correlation clustering outperforms other state-of-the-art image segmentation algorithms. 1
Design and perceptual validation of performance measures for salient object segmentation
- In POCV
, 2010
"... Empirical evaluation of salient object segmentation methods requires i) a dataset of ground truth object segmen-tations and ii) a performance measure to compare the out-put of the algorithm with the ground truth. In this paper, we provide such a dataset, and evaluate 5 distinct performance measures ..."
Abstract
-
Cited by 24 (2 self)
- Add to MetaCart
(Show Context)
Empirical evaluation of salient object segmentation methods requires i) a dataset of ground truth object segmen-tations and ii) a performance measure to compare the out-put of the algorithm with the ground truth. In this paper, we provide such a dataset, and evaluate 5 distinct performance measures that have been used in the literature practically and psychophysically. Our results suggest that a measure based upon minimal contour mappings is most sensitive to shape irregularities and most consistent with human judge-ments. In fact, the contour mapping measure is as predic-tive of human judgements as human subjects are of each other. Region-based methods, and contour methods such as Hausdorff distances that do not respect the ordering of points on shape boundaries are significantly less consistent with human judgements. We also show that minimal contour mappings can be used as the correspondence paradigm for Precision-Recall analysis. Our findings can provide guid-ance in evaluating the results of segmentation algorithms in the future. 1.
Channel coding for joint colour and depth segmentation
- in Proceedings of DAGM’11
, 2011
"... Abstract. Segmentation is an important preprocessing step in many ap-plications. Compared to colour segmentation, fusion of colour and depth greatly improves the segmentation result. Such a fusion is easy to do by stacking measurements in different value dimensions, but there are better ways. In thi ..."
Abstract
-
Cited by 5 (1 self)
- Add to MetaCart
(Show Context)
Abstract. Segmentation is an important preprocessing step in many ap-plications. Compared to colour segmentation, fusion of colour and depth greatly improves the segmentation result. Such a fusion is easy to do by stacking measurements in different value dimensions, but there are better ways. In this paper we perform fusion using the channel representation, and demonstrate how a state-of-the-art segmentation algorithm can be modified to use channel values as inputs. We evaluate segmentation re-sults on data collected using the Microsoft Kinect peripheral for Xbox 360, using the superparamagnetic clustering algorithm. Our experiments show that depth gradients are more useful than depth values for segmen-tation, and that channel coding both colour and depth gradients makes tuned parameter settings generalise better to novel images. 1
Detecting Spatiotemporal Structure Boundaries: Beyond Motion Discontinuities
- Proc. Asian Conf. Computer Vision
, 2009
"... Abstract. The detection of motion boundaries has been and remains a longstanding challenge in computer vision. In this paper, the recovery of motion boundaries is recast in a broader scope, as focus is placed on the more general problem of detecting spacetime structure boundaries, where motion boun ..."
Abstract
-
Cited by 4 (3 self)
- Add to MetaCart
(Show Context)
Abstract. The detection of motion boundaries has been and remains a longstanding challenge in computer vision. In this paper, the recovery of motion boundaries is recast in a broader scope, as focus is placed on the more general problem of detecting spacetime structure boundaries, where motion boundaries constitute a special case. This recasting allows uniform consideration of boundaries between a wider class of spacetime patterns than previously considered in the literature, both coherent motion as well as additional dynamic patterns. Examples of dynamic patterns beyond standard motion that are encompassed by the proposed approach include, flicker, transparency and various dynamic textures (e.g., scintillation). Toward this end, a novel representation and method for detecting these boundaries in raw image sequence data are presented. Central to the representation is the description of oriented spacetime structure in a distributed manner. Empirical evaluation of the proposed boundary detector on challenging natural imagery suggests its efficacy.
Image Segmentation Using Higher-Order Correlation Clustering
, 2014
"... In this paper, a hypergraph-based image segmentation framework is formulated in a supervised manner for many high-level computer vision tasks. To consider short- and long-range dependency among various regions of an image and also to incorporate wider selection of features, a higher-order correlati ..."
Abstract
-
Cited by 3 (0 self)
- Add to MetaCart
In this paper, a hypergraph-based image segmentation framework is formulated in a supervised manner for many high-level computer vision tasks. To consider short- and long-range dependency among various regions of an image and also to incorporate wider selection of features, a higher-order correlation clustering (HO-CC) is incorporated in the framework. Correlation clustering (CC), which is a graph-partitioning algorithm, was recently shown to be effective in a number of applications such as natural language processing, document clustering, and image segmentation. It derives its partitioning result from a pairwise graph by optimizing a global objective function such that it simultaneously maximizes both intra-cluster similarity and inter-cluster dissimilarity. In the HO-CC, the pairwise graph which is used in the CC is generalized to a hypergraph which can alleviate local boundary ambiguities that can occur in the CC. Fast inference is possible by linear programming relaxation, and effective parameter learning by structured support vector machine is also possible by incorporating a decomposable structured loss function. Experimental results on various datasets show that the proposed HO-CC outperforms other state-of-the-art image segmentation algorithms. The HO-CC framework is therefore an efficient and flexible image segmentation framework.
A Methodological Survey and Proposed Algorithm on Image Segmentation using Genetic Algorithm
"... This literature review attempts to provide a brief overview of some of the most common image segmentation techniques. It discusses Edge detection technique, Thresholding technique, Region growing based technique, Watershed technique, Compression based method, Histogram based segmentation and Graph p ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
(Show Context)
This literature review attempts to provide a brief overview of some of the most common image segmentation techniques. It discusses Edge detection technique, Thresholding technique, Region growing based technique, Watershed technique, Compression based method, Histogram based segmentation and Graph partitioning method. With the growing research on image segmentation, it has become important to categorise the research outcomes and provide readers with an overview of the existing segmentation techniques in each category. In this paper different method of implementing genetic algorithm has been reviewed. Finally, summaries and review of research work on wrapper approach for image segmentation techniques has been represented. General Terms Image processing, image segmentation, image classification, genetic algorithm, wrapper approach, object detection.
A Fuzzy Set Approach for Edge Detection
"... Image segmentation is one of the most studied problems in image analysis, computer vision, pattern recognition etc. Edge detection is a discontinuity based approach used for image segmentation. An edge detection using fuzzy set is proposed here, where an image is considered as a fuzzy set and pixels ..."
Abstract
-
Cited by 1 (1 self)
- Add to MetaCart
Image segmentation is one of the most studied problems in image analysis, computer vision, pattern recognition etc. Edge detection is a discontinuity based approach used for image segmentation. An edge detection using fuzzy set is proposed here, where an image is considered as a fuzzy set and pixels are taken as elements of fuzzy set. The proposed approach converts the color image to a partially segmented image; finally an edge detector is convolved over the partially segmented image to obtain an edged image. The approach is implemented using MATLAB 7.11. (R2010b). In this paper, an attempt is made to evaluate edge detection using ground truth for quantitative and qualitative comparison. 30 BSD (Berkeley Segmentation Database) images and respective ground truths are used for experimentation. Performance parameters used are PSNR (dB) and Performance ratio (PR) of true to false edges. Experimental results shows that the proposed approach gives higher PSNR and PR values when compared with Canny’s edge detection algorithm under almost all scenarios. The proposed approach reduces false edge detection and identification of double edges are minimum.
