Segmentation of multiple salient closed contours from real images
151
Citation
31
Reference
10
Related Paper
Citation Trend
Abstract:
Using a saliency measure based on the global property of contour closure, we have developed a segmentation method which identifies smooth closed contours bounding objects of unknown shape in real images. The saliency measure incorporates the Gestalt principles of proximity and good continuity that previous methods have also exploited. Unlike previous methods, we incorporate contour closure by finding the eigenvector with the largest positive real eigenvalue of a transition matrix for a Markov process where edges from the image serve as states. Element (i, j) of the transition matrix is the conditional probability that a contour which contains edge j will also contain edge i. We show how the saliency measure, defined for individual edges, can be used to derive a saliency relation, defined for pairs of edges, and further show that strongly-connected components of the graph representing the saliency relation correspond to smooth closed contours in the image. Finally, we report for the first time, results on large real images for which segmentation takes an average of about 10 seconds per object on a general-purpose workstation.Keywords:
Connected component
We present an approach for object segmentation in videos that combines frame-level object detection with concepts from object tracking and motion segmentation. The approach extracts temporally consistent object tubes based on an off-the-shelf detector. Besides the class label for each tube, this provides a location prior that is independent of motion. For the final video segmentation, we combine this information with motion cues. The method overcomes the typical problems of weakly supervised/unsupervised video segmentation, such as scenes with no motion, dominant camera motion, and objects that move as a unit. In contrast to most tracking methods, it provides an accurate, temporally consistent segmentation of each object. We report results on four video segmentation datasets: YouTube Objects, SegTrackv2, egoMotion, and FBMS.
Tracking (education)
Segmentation-based object categorization
Match moving
Cite
Citations (36)
Region growing
Cite
Citations (0)
We propose a new automatic image segmentation method. Color edges in an image are first obtained automatically by combining an improved isotropic edge detector and a fast entropic thresholding technique. After the obtained color edges have provided the major geometric structures in an image, the centroids between these adjacent edge regions are taken as the initial seeds for seeded region growing (SRG). These seeds are then replaced by the centroids of the generated homogeneous image regions by incorporating the required additional pixels step by step. Moreover, the results of color-edge extraction and SRG are integrated to provide homogeneous image regions with accurate and closed boundaries. We also discuss the application of our image segmentation method to automatic face detection. Furthermore, semantic human objects are generated by a seeded region aggregation procedure which takes the detected faces as object seeds.
Centroid
Region growing
Image gradient
Range segmentation
Cite
Citations (576)
Representation
Segmentation-based object categorization
Cite
Citations (7)
Object segmentation is one of the vital tasks in various three-dimensional applications. The paper presents a hybrid object segmentation algorithm to combine intensity segmentation and disparity segmentation in a stereoscopic vision system. First, the disparity maps of the stereo images are estimated using a foreground-based disparity estimation method. Then, the intensity stereo images and their corresponding disparity maps are separately segmented using a region-growing technique. The real segmentation mask can be obtained and the semantic object be extracted by a fusion processing on the intensity and disparity segments. Computer simulations indicate the reliable performance of the proposed algorithm for stereoscopic segmentation.
Segmentation-based object categorization
Computer stereo vision
Cite
Citations (16)
We present an approach for autonomous interactive object segmentation by a humanoid robot. The visual segmentation of unknown objects in a complex scene is an important prerequisite for e.g. object learning or grasping, but extremely difficult to achieve through passive observation only. Our approach uses the manipulative capabilities of humanoid robots to induce motion on the object and thus integrates the robots manipulation and sensing capabilities to segment previously unknown objects. We show that this is possible without any human guidance or pre-programmed knowledge, and that the resulting motion allows for reliable and complete segmentation of new objects in an unknown and cluttered environment. We extend our previous work, which was restricted to textured objects, by devising new methods for the generation of object hypotheses and the estimation of their motion after being pushed by the robot. These methods are mainly based on the analysis of motion of color annotated 3D points obtained from stereo vision, and allow the segmentation of textured as well as non-textured rigid objects. In order to evaluate the quality of the obtained segmentations, they are used to train a simple object recognizer. The approach has been implemented and tested on the humanoid robot ARMAR-III, and the experimental results confirm its applicability on a wide variety of objects even in highly cluttered scenes.
Cite
Citations (30)
We present a method for automatic video region segmentation. The method is based, fundamentally, on motion analysis in image areas showing significant intensity variation. Since motion in these areas can be estimated more accurately than that in smoother areas, segmentation based on such motion information can be more reliable. A frequently encountered problem in automatic video segmentation is that the object boundaries may not be accurately identified: the identified boundaries may extend beyond the actual positions by some distance. We develop an edge delineation method, which combines edge detection and motion analysis, to deal with this problem. Some segmentation examples are provided.
Motion analysis
Segmentation-based object categorization
Cite
Citations (2)
To remedy the over-segmentation problem of marker-based watershed segmentation,an overflow marker-based watershed segmentation algorithm based on edge detection was proposed. Firstly,The phase congruency based edge detection method to get the edge information was used. Then,a regional growth algorithm which based on edge information is used to detect objects with weak boundary and improving the positional accuracy of the objects boundary. Finally,a overflow model for obtaining new markers and growth as above until finish segmentation was proposed. The experimental results on satellite images and aerial images datasets show that the proposed algorithm performs well in retaining the weak boundary and reducing the undesired over-segmentation.
Segmentation-based object categorization
Region growing
Morphological gradient
Cite
Citations (0)
In this paper, we present a novel method called coloring technique for image segmentation. Coloring technique uses the edges detected by the Sobel operator and in many cases successfully identifies the object boundary. This method can be used to eliminate unimportant edges in the background created by clutter and noise while preserving the edges inside the object boundary. The results show that the new method yields superior segmentations compared to conventional segmentation methods.
Machine Vision
Cite
Citations (5)
The task of correctly tracking the body parts is one of the crucial problems in the human body pose modelling. Various factors need to be investigated as the variety of body poses is unlimited and the visual appearance varies according to the environment. The human body can be composed into several parts such as the head, torso, arms and legs. The arms can be considered as the most challenging body part to be tracked since it tends to move fast and usually occluded within other body parts. This paper addresses the problem of extracting the arms which are occluded in the torso part. A wavelet-based skin segmentation method is applied to detect the skin region. The segmentation procedure is performed using six different colour spaces namely the RGB, rgb, HSI, TSL, SCT and CIELAB. The segmentation performances are evaluated on colour component basis. The aim of this paper is to determine the best colour components that are suitable for this segmentation procedure.
Torso
RGB color model
Tracking (education)
Cite
Citations (7)