Markerless tracking of respiration-induced tumor motion in kilo-voltage (kV) fluoroscopic image sequence is still a challenging task in real time image- guided radiation therapy (IGRT). Most of existing markerless tra...
详细信息
Markerless tracking of respiration-induced tumor motion in kilo-voltage (kV) fluoroscopic image sequence is still a challenging task in real time image- guided radiation therapy (IGRT). Most of existing markerless tracking methods are based on a template matching technique or its extensions that are frequently sensitive to non-rigid tumor deformation and involve expensive computation. This paper presents a kernel-based method that is capable of tracking tumor motion in kV fluoroscopic image sequence with robust performance and low computational cost. The proposed tracking system consists of the following three steps. To enhance the contrast of kV fluoroscopic image, we firstly utilize a histogram equalization to transform the intensities of original images to a wider dynamical intensity range. A tumor target in the first frame is then represented by using a histogram-based feature vector. Subsequently, the target tracking is then formulated by maximizing a Bhattacharyya coefficient that measures the similarity between the tumor target and its candidates in the subsequent frames. The numerical solution for maximizing the Bhattacharyya coefficient is performed by a mean-shiftalgorithm. The proposed method was evaluated by using four clinical kV fluoroscopic image sequences. For comparison, we also implement four conventional template matching-based methods and compare their performance with our proposed method in terms of the tracking accuracy and computational cost. Experimental results demonstrated that the proposed method is superior to conventional template matching-based methods.
Object tracking is to search the most similar parts to targets in video sequences. Among the various tracking algorithms, meanshift tracking algorithm has become popular due to its simplicity, efficiency and good per...
详细信息
ISBN:
(纸本)9783037854471
Object tracking is to search the most similar parts to targets in video sequences. Among the various tracking algorithms, meanshift tracking algorithm has become popular due to its simplicity, efficiency and good performance. This paper focused on meanshift tracking algorithm, which is a modeling mechanism based on statistical probability density function. In practice, when the background of the tracking and characteristics of the target are similar, pixels of background occupy a large proportion in the histogram. The traditional meanshift cannot adapt to the mutative scene. meanwhile, if there is block or disappearance, the result is not exact. Three algorithms were given for above difficulties. A weighted template background was established, that can highlight the features of target and improve real-time. Then this paper presented a selective mechanism to update the target model. Every component is updated based on the contribution to the target model. Finally, the Kalman filter was combined with mean shift algorithm We saw the prediction points of Kalman filter as the initial point, carried out the meanshift iteration and then updated Kalman filter using the ultimate location. Extensive experimental results illustrated excellent agreement with these methods.
Important information concerning a multivariate data set, such as clusters and modal regions, is contained in the derivatives of the probability density function. Despite this importance, nonparametric estimation of h...
详细信息
Important information concerning a multivariate data set, such as clusters and modal regions, is contained in the derivatives of the probability density function. Despite this importance, nonparametric estimation of higher order derivatives of the density functions have received only relatively scant attention. Kernel estimators of density functions are widely used as they exhibit excellent theoretical and practical properties, though their generalization to density derivatives has progressed more slowly due to the mathematical intractabilities encountered in the crucial problem of bandwidth (or smoothing parameter) selection. This paper presents the first fully automatic, data-based bandwidth selectors for multivariate kernel density derivative estimators. This is achieved by synthesizing recent advances in matrix analytic theory which allow mathematically and computationally tractable representations of higher order derivatives of multivariate vector valued functions. The theoretical asymptotic properties as well as the finite sample behaviour of the proposed selectors are studied. In addition, we explore in detail the applications of the new data-driven methods for two other statistical problems: clustering and bump hunting. The introduced techniques are combined with the mean shift algorithm to develop novel automatic, nonparametric clustering procedures which are shown to outperform mixture-model cluster analysis and other recent nonparametric approaches in practice. Furthermore, the advantage of the use of smoothing parameters designed for density derivative estimation for feature significance analysis for bump hunting is illustrated with a real data example.
Lung cancer has been the largest cause of cancer deaths worldwide with an overall 5-year survival rate of only 15%. Its symptoms can be found exclusively in advanced stages where the chances for patients to survive ar...
详细信息
Lung cancer has been the largest cause of cancer deaths worldwide with an overall 5-year survival rate of only 15%. Its symptoms can be found exclusively in advanced stages where the chances for patients to survive are very low, thus making the mortality rate the highest among all other types of cancer. The present work deals with the attempt to design computer-aided detection or diagnosis (CAD) systems for early detection of lung cancer based on the analysis of sputum color images. The aim is to reduce the false negative rate and to increase the true positive rate as much as possible. The early detection of lung cancer from sputum images is a challenging problem, due to both the structure of the cancer cells and the stained method which are employed in the formulation of the sputum cells. We present here a framework for the extraction and segmentation of sputum cells in sputum images using, respectively, a threshold classifier, a Bayesian classification and meanshift segmentation. Our methods are validated and compared with other competitive techniques via a series of experimentation conducted with a data set of 100 images. The extraction and segmentation results will be used as a base for a CAD system for early detection of lung cancer which will improve the chances of survival for the patient.
This paper selects the target tracking algorithm suitable for specific target environment: using mean shift algorithm based on space edge direction histogram at initialization, selecting tracking algorithm based on bl...
详细信息
ISBN:
(纸本)9783037858646
This paper selects the target tracking algorithm suitable for specific target environment: using mean shift algorithm based on space edge direction histogram at initialization, selecting tracking algorithm based on block when there is a shelter. On the basis of algorithm analysis and software experiment and studying of TI Company's TMS320DM642 DSP chip internal structure and development process, these two algorithms researched in this paper were transplanted to DSP platform and a series of optimization were been made to the algorithms codes after transplanted,implementing target tracking and identified via DSP development board instead of PC.
The task of interactive image segmentation has attracted a significant attention in recent years. The ultimate goal is to extract an object with as few user interactions as possible. In this paper, we present SUPERCUT...
详细信息
ISBN:
(纸本)9781479923410
The task of interactive image segmentation has attracted a significant attention in recent years. The ultimate goal is to extract an object with as few user interactions as possible. In this paper, we present SUPERCUT, a novel interactive algorithm for foreground object extraction and segmentation in images. In the algorithm, the mean shift algorithm with a boundary confidence prior is introduced to efficiently pre-segment the original image into super-pixels with precise boundary. Secondly, a Bayes decision theory is introduced to model and cluster the super-pixels so as to obtain an initial effective classification of super-pixels. To achieve a more accurate object segmentation result, a boundary refinement using Interactive rectangle box with GMM learning is adopted. Experimental results on a benchmark data set show that the proposed framework is highly effective and can accurately segment a wide variety of natural images with ease.
Real-time human detection and tracking is a vast, challenging and important field of research. It has wide range of applications in human recognition, human computer interaction (HCI), video surveillance etc. The rese...
详细信息
ISBN:
(纸本)9781479922741;9781479922758
Real-time human detection and tracking is a vast, challenging and important field of research. It has wide range of applications in human recognition, human computer interaction (HCI), video surveillance etc. The research for biometric authentication of a person has reached far but the real-time tracking of human beings has not gained much importance. Tracking of human being can be used as a prior step in biometric face recognition. Keeping continuous track of person will allow to identify person at any time. The system consist of two parts first human detection and secondly tracking. Human detection step is split into face detection and eye detection. Face is a vital part of human being represent most important information about the individual. Eyes are the important biometric feature used in person identification. Face detection is done using skin color based methods. Y CbCr color model is used to detect skin regions as it represents intensity and color information separately. For eye region detection projection function and pixel count methods are used. Finally the mean shift algorithm and kalman filter algorithm is used for tracking.
Contemporary research is developing techniques to tracking objects in videos using color features, and the meanshift (MS) algorithm is one of the best. This known algorithm is employed to find the location of an obje...
详细信息
Contemporary research is developing techniques to tracking objects in videos using color features, and the meanshift (MS) algorithm is one of the best. This known algorithm is employed to find the location of an object, in image sequence, by using a coefficient called the Bhattacharyya coefficient. This coefficient is calculated through an object tracking algorithm to present the similarity in appearance between an object and its candidate model, where the best representation of an object is acquired, once this is could be maximized. However, the MS algorithm performance is confounded by color clutter in background, various illuminations, occlusion types and other related limitations. Because of such effects, the algorithm necessarily decreases the value of the Bhattacharyya coefficient, indicating reduced certainty in the object tracking. In the present research, an improved convex kernel function is proposed to overcome the partial occlusion. Afterwards, in order to improve the MS algorithm against the low saturation and also sudden light, changes are made from motion information of the desired sequence. By using both the color feature and the motion information simultaneously, the capability of the MS algorithm is correspondingly increased, in the present approach. Moreover, by assuming a constant speed for the object, a robust estimator, i.e., the Kalman filter, is realized to solve the full occlusion problem. At the end, experimental results on various videos verify that the proposed method has an optimum performance in real-time object tracking, while the result of the original MS algorithm may be unsatisfied. (c) 2012 ISA. Published by Elsevier Ltd. All rights reserved.
This study describes a method for tracking objects through scale and occlusion. The technique presented is based on the mean shift algorithm, which provides an efficient way to track objects based on their colour char...
详细信息
This study describes a method for tracking objects through scale and occlusion. The technique presented is based on the mean shift algorithm, which provides an efficient way to track objects based on their colour characteristics. A novel and efficient method is derived for tracking through changes in the target scale, where an object of interest moves away or towards the camera and therefore appears to change size in the image plane. The method works by interleaving spatial meanshift iterations with scale iterations. It is shown that this method is considerably more efficient than other methods and possesses other advantages too. It is also demonstrated that the Bhattacharyya coefficient, a histogram similarity metric that is used in the meanshift framework, can be used to reliably detect when target occlusion occurs. In such situations, the motion of an object can be extrapolated to give an accurate estimate of its position. This is used as the basis of a technique for tracking through occlusion. Experimental results are presented on data from various scenarios.
Human objects Segmentation is one of key problems of visual analysis. In this paper, a novel touched human objects segmentation based on mean shift algorithm is proposed. At first, Video images is preprocessed and for...
详细信息
ISBN:
(纸本)9780769534985
Human objects Segmentation is one of key problems of visual analysis. In this paper, a novel touched human objects segmentation based on mean shift algorithm is proposed. At first, Video images is preprocessed and foreground objects (BLOB) is obtained, model of human object is built according to statistical characteristics of body surface. Then, a few of points picked equably from BLOB is taken as seeds, and local mode centroids were calculated by mean-shift iterative process. At last, number of categories is automatic acquisition based on clustering algorithm, and human objects is segmentation according to result of clustering. The experiment based on PETS 2006 Database prove this method is feasible and precisely.
暂无评论