Mean Shift Tracking Research Articles

Meanshift Tracking with Kalman Filter and Rotation-Invariant Features

This paper presents an improve Meanshift tracking algorithm based on Kalman filter and Rotation-Invariant Features. Firstly, this paper forecasts the original alternate position using Kalman filter. Secondly, a kind of spatial histogram based on GRA (Gradient Radius Angle, GRA) is introduced, which is a rotation-invariant descriptor combined the information of gradient. At last, this paper searches the scale factor by the normal scale space decomposition technique. Experiments show that the method concerned in this paper has better performances than two improved algorithms.

PageRank Tracker: From Ranking to Tracking

Video object tracking is widely used in many real-world applications, and it has been extensively studied for over two decades. However, tracking robustness is still an issue in most existing methods, due to the difficulties with adaptation to environmental or target changes. In order to improve adaptability, this paper formulates the tracking process as a ranking problem, and the PageRank algorithm, which is a well-known webpage ranking algorithm used by Google, is applied. Labeled and unlabeled samples in tracking application are analogous to query webpages and the webpages to be ranked, respectively. Therefore, determining the target is equivalent to finding the unlabeled sample that is the most associated with existing labeled set. We modify the conventional PageRank algorithm in three aspects for tracking application, including graph construction, PageRank vector acquisition and target filtering. Our simulations with the use of various challenging public-domain video sequences reveal that the proposed PageRank tracker outperforms mean-shift tracker, co-tracker, semiboosting and beyond semiboosting trackers in terms of accuracy, robustness and stability.

Object Tracking by Corrected Background-Weighted Histogram Mean Shift with Sum of Gradient Mode

With a focus on complex environments, the present paper describes a new algorithm in scale changed object tracking through color feature. Mean shift (MS) iterative procedure is the best color-based algorithm to find the location of an object. The algorithm performance is not acceptable once tracking scale changed objects in complex environments. In this paper, the main aim is to improve the MS method, using corrected background-weighted histogram (CBWH) algorithm to reduce the interference of background in target localization. To fit the object scale change, the sum of gradient mode (SGM) is employed. The experimental results show that the proposed method is superior to the traditional mean shift tracking in the following aspects: 1) it provides consistent object tracking throughout the video; 2) it is not influenced by the tracked objects scale changes; 3) it is less prone to the background clutter.

A Robust Object Tracking Approach based on Mean Shift Algorithm

Object tracking has always been a hotspot in the field of computer vision, which has a range of applications in real word. The object tracking is a critical task in many vision applications. The main steps in video analysis are two: detection of interesting moving objects and tracking of such objects from frame to frame. Most of tracking algorithms use pre-defined methods to process. In this study, we introduce the Mean shift tracking algorithm, which is a kind of important no parameters estimation method, then we evaluate the tracking performance of Mean shift algorithm on different video sequences. Experimental results show that the Mean shift tracker is effective and robust tracking method.

An Improved Mean Shift Algorithm for Vehicle Tracking

Classical mean shift tracking algorithm doesnt show good performance when the tracked objects move fast, change in size or pose. This paper proposes an improved mean shift method used for vehicle tracking. Firstly, a position prediction model based on second order auto-regression process is used to find the initial position of mean shift iteration, reduce times of iteration and enhance the tracking accuracy. Secondly, we employ a position search method based on the weight image to improve the tracking result when the result of basic mean shift tracking is not good. The proposed algorithm is tested in a real traffic video to track a vehicle changing in size and pose with more accurate result than basic mean shift tracking algorithm.

Object Tracking Using Improved Meanshift Algorithm Combined with Kalman Filter on Independent Visual Robotic Fish

This Paper Investigates an Improved Meanshift Algorithm Combined with Kalman Filter Aiming at Failure of a Target Tracking in Complex Environment for the Independent Visual Robotic Fish. First,we Need to Establish Kalman Filter Model of Moving Target. then,the Prediction and Renewal Process of Kalman Filter are Applied into the Meanshift Tracking Algorithm. Experimental Results Show that Improved Algorithm can Effectively Improve the Performance of Single Target Tracking in Complex Environment, and Realize Continuous Tracking of a Target. also, it can Obtain more Reliable Tracking Effect, and can be Used for more Complicated Scenes.

Object Tracking Approach based on Mean Shift Algorithm

Object tracking has always been a hotspot in the field of computer vision, which has a range of applications in real world. The object tracking is a critical task in many vision applications. The main steps in video analysis are: detection of interesting moving objects and tracking of such objects from frame to frame. Most of tracking algorithms use pre-defined methods to process. In this paper, we introduce the Mean shift tracking algorithm, which is a kind of important no parameters estimation method, then we evaluate the tracking performance of Mean shift algorithm on different video sequences. Experimental results show that the Mean shift tracker is effective and robust tracking method.

Robust Spatial-Color Feature with New Similarity Measure and Adaptive Template Update for Mean-Shift Tracking

In this paper, we analyze the object tracking task of mean-shift algorithm. A spatial-color and similarity based mean-shift tracking algorithm is proposed. The spatial-color feature is used to replace the color histogram, and an enhanced algorithm is derived by adopting a new similarity measure. We also introduce Lucas-Kanade algorithm to design a template update strategy, propose a template update algorithm for mean-shift. Experimental results show that these two improved mean-shift tracking algorithms have high tracking accuracy and good robustness to the change of appearance of the object.

TH-A-WAB-06: Joint Segmentation and Sequential Registration Based Approach for Computing Artifact-Free ADC Maps From Multiple DWI-MRI Sequences in Liver

Purpose: To develop an automatic method for motion correction and alignment of multiple DWI-MRI image sequences in the liver for computing repeatable, artifact-free ADC maps. Methods: We developed an automatic method that computes artifact-free, repeatable ADC maps by registering multiple b-valued DWI-MRI images of liver. First, various structures of interest are segmented on an arbitrary reference image starting from user drawn lines on those structures. Next, the remaining images are sequentially aligned to the reference by propagating the segmentations from the reference to these images using a mean shift tracking procedure. Sequential alignment registers the closest image to the current reference using B-spline deformable registration. The closest image is the one that minimizes the centroid distance of the individual structures from itself to those in the reference. Following alignment, the closest image is made the new reference and the process repeated until all images are aligned. The ADC map is computed for the aligned images using least squares fitting. Results: We tested our approach on DWI-MRI image sequences of the liver for different patients by aligning and computing ADC maps. Each scan contained 5 different DWI sequences (b=0,50,250,350,500). Regardless of the chosen reference, we found that the motion corrected ADC maps removed artifacts particularly on the boundary of tumors in comparison to conventionally computed ADC maps. Furthermore, we also found that the mean ADC values for the tumors computed using motion correction exhibited significantly less variation compared to the mean ADC values of the same tumors computed without motion correction. Finally, our approach also automatically segments the relevant tumors. Conclusion: Our joint segmentation and motion correction based approach generates artifact-free ADC maps as well as repeatable ADC maps for structures of interest such as tumors located in liver.

Variable Kernel Bandwidth Tracking Algorithm Based on Contourlet Histogram and Information Entropy

In order to solve the problem that traditional mean shift tracking algorithm based on color histogram is easily affected by similar color non-target object and the change of the size of target, a variable kernel bandwidth tracking algorithm is put forward based on contourlet histogram and information entropy. The target is modeled by contourlet histogram, as iterative parameters in mean shift algorithm, and according to the relationship between information entropy and the size of target, a scale-update item is added to mean shift algorithm to track the target that has a change in size. Experimental results show that the proposed tracking algorithm can not only effectively overcome the interference of similar color non-target object in the scene, but also adapt to the changes in target’s size stably, and this algorithm had a good robustness.

3D video components generation using object tracking technique

2D-to-3D conversion that would be a solution of the lack of 3D contents has been a worthy and challenging research field. In this paper, we propose a computer interactive conversion method to capture components which is used to generate 3D sequences. First, we divide the key frame into foreground and background, and then label the objects by convenient computer interactive operation. Depth information of objects is labeled after segmentation. Second, we use object tracking technique which synthesizes the advantages of kernel-based mean shift tracker and contour tracker to accomplish object depth capture for non-key frame. Finally, all the 3D information is prepared to render 3D sequences. After all, we propose our future work direction: a 2D-to-3D system which can generate 3D sequence interactively.

Mean Shift Tracking with Advanced Background-Weighted Histogram

Tracking objects in videos using mean shift technique has brought to public attention. In background-weighted histogram (BWH) algorithm proposed by Kernel-Based Object tracking attempts to reduce the interference of background target localization in mean shift tracking. However, in this paper we prove that the weights assigned to pixels in the target candidate region by BWH are proportional to those without background information, i.e. BWH does not introduce any new information because the mean shift iteration formula is invariant to the scale transformation of weights. We then propose an Advanced BWH (ABWH) formula by transforming only the target model but not the target candidate model. The ABWH scheme can effectively reduce background’s interference in target localization and for the target not well initialized, it can still robustly track the object, which is hard to achieve by the conventional target representation and it lead to faster convergence and more accurate localization than the usual target representation in mean shift tracking.

Scale and Orientation Adaptive Moving Object Tracking in a Sequence of Imageries

Object tracking has been researched for many years as an important topic in machine learning, robot vision and many other fields. Over the years, various tracking methods are proposed and developed in order to gain a better tracking effect. Among them the mean-shift algorithm turns out to be robust and accurate compared other algorithms after different kinds of tests. But due to its limitations, the changes in scale and rotational motion of an object cannot be effectively processed. This problem occurs when the object of interest moves towards or away from the video camera. Improving over the previously proposed method such as scale and orientation adaptive mean shift tracking, which performs well with scaling change but not for the rotation, in this paper, the proposed method modifies the continuously adaptive mean shift tracking method so that it can handle effectively for changes in size and rotation in motion, simultaneously. The simulation results yield a successful tracking of moving objects even when the object undergoes scaling in size and rotation in motion in comparison to the conventional ones.

Video event description in scene context

Video event description is an important research topic in video analysis with a vast amount of applications, such as visual surveillance, video retrieval, video annotation, video database indexing, and interactive system. In this paper, we present a framework for automated video event description, which features fused with the context knowledge to provide accurate and reliable event description. The processing framework is designed to describe the event and recognize objects activities composed of four components: object detection, classification, tracking, and semantic event description. Our contribution is to integrate the contextual cues into these components to facilitate the semantic video event description. Furthermore, in the tracking part, a novel adaptive shape kernel based mean shift tracking algorithm is proposed to improve object tracking performance under object deformation and background clutter. In the experiments, we show attractive experimental results, highlighting the system efficiency and tracking capability by using our video event description system on a real-world video for video event understanding application.

Power system insulator condition monitoring automation using mean shift tracker-FIS combined approach

Within the hierarchy of power system, distribution system automation plays a crucial role to provide reliable service to customers. Though initially computer aided automation started as substation monitoring system (SMS) just for monitoring some key parameters such as voltage and currents of different components in a substation, the technological advancement has enabled to have access to more features from components of the entire distribution system. Since the distribution system has expanded to cater power to even remote locations, thus for reliable power supply, insulator condition monitoring automation plays an important role because the failure of insulator either causes complete disruption of power or reduction of system voltage leading to heavy power losses. This paper presents a methodology for condition monitoring automation of insulators by a combined approach using mean shift tracker and fuzzy inference system (FIS) and the case studies validate the efficacy of the methodology.

A Scale Adaptive Mean-Shift Tracking Algorithm for Robot Vision

The Mean-Shift (MS) tracking algorithm is an efficient tracking algorithm. However, it does not work very well when the scale of a tracking target changes, or targets are occluded in the movements. In this paper, we propose a scale-adaptive Mean-Shift tracking algorithm (SAMSHIFT) to solve these problems. In SAMSHIFT, the corner matching is employed to calculate the affine structure between adjacent frames. The scaling factors are obtained based on the affine structure. Three target candidates, generated by the affine transformation, the Mean Shift and the Mean Shift with resizing by the scaling factors, respectively, are applied in each iteration to improve the tracking performance. By selecting the best candidate among the three, we can effectively improve the scale adaption and the robustness to occlusion. We have evaluated our algorithm in a PC and a mobile robot. The experimental results show that SAMSHIFT is well adaptive to scale changing and robust to partial occlusion, and the tracking speed is fast enough for real-time tracking applications in robot vision.

Local Similarity Number and its Application to Object Tracking

In this paper, we present a tracking technique utilizing a simple saliency visual descriptor. Initially, we define a visual descriptor named local similarity pattern that mimics the famous texture operator local binary patterns. The key difference is that it assigns each pixel a code based on the similarity to the neighbouring pixels. Later, we simplify this descriptor to a local saliency operator which counts the number of similar pixels in a neighbourhood. We name this operator local similarity number ( LSN). We apply the local similarity number operator to measure the amount of saliency in a target patch and model the target. The proposed tracking algorithm uses a joint saliency-colour histogram to represent the target in a mean-shift tracking framework. We will show that the proposed saliency-colour target representation outperforms texture-colour where texture modelled by local binary patterns and colour target representation techniques are used.

An Image Tracking Method Based on Color Co-Occurrence Histograms

Aiming at the result of Mean-Shift tracking method is not satisfactory when color of the target is similar to the back ground or another similar object is close to the target, a real- time target tracking method combined with Mean shift and color co-occurrence histograms (CCH) was proposed in this paper. The method used CCH to represent target model of the Mean-Shift. And then the Mean-Shift was used to locate the target position. Moreover, the studied model updating strategy based on multi-scale CCH and the similarity measure of Bhattacharyya value is constructed in the method. Experiments in the complex environment were done. The results show that the proposed method has more accurate target locating and better robustness than the traditional Mean-Shift.

A More Robust Mean Shift Tracker on Joint Color-CLTP Histogram

A more robust mean shift tracker using the joint of color and Completed Local Ternary Pattern (CLTP) histogram is proposed. CLTP is a generalization of Local Binary Pattern (LBP) which can be applied to obtain texture features that are more discriminant and less sensitive to noise. The joint of color and CLTP histogram based target representation can exploit the target structural information efficiently. To reduce the interference of background in target localization, a corrected background-weighted histogram and background update mechanism are adapted to decrease the weights of both prominent background color and texture features similar to the target object. Comparative experimental results on various challenging videos demonstrate that the proposed tracker performs favorably against several variants of state-of-the-art mean shift tracker when heavy occlusions and complex background changes exist.

A novel framework for motion segmentation and tracking by clustering incomplete trajectories

In this paper, we present a framework for visual object tracking based on clustering trajectories of image key points extracted from an image sequence. The main contribution of our method is that the trajectories are automatically extracted from the image sequence and they are provided directly to a model-based clustering approach. In most other methodologies, the latter constitutes a difficult part since the resulting feature trajectories have a short duration, as the key points disappear and reappear due to occlusion, illumination, viewpoint changes and noise. We present here a sparse, translation invariant regression mixture model for clustering trajectories of variable length. The overall scheme is converted into a maximum a posteriori approach, where the Expectation–Maximization (EM) algorithm is used for estimating the model parameters. The proposed method detects the different objects in the input image sequence by assigning each trajectory to a cluster, and simultaneously provides their motion. Numerical results demonstrate the ability of the proposed method to offer more accurate and robust solutions in comparison with other tracking approaches, such as the mean shift tracker, the camshift tracker and the Kalman filter.