Mean Shift Tracking Algorithm Research Articles

The Research of Moving Target Detection and Tracking System Based on DM6437

In order to enhance the rapidity and the accuracy of moving target detection and tracking, and improve the speed of the algorithm on the DSP (digital signal processor), an active visual tracking system was designed based on the gaussian mixture background model and Meanshift algorithm on DM6437. The system use the VLIB library developed by TI, and through the method of gaussian mixture background model to detect the moving objects and use the Meanshift tracking algorithm based on color features to track the target in RGB space. Finally, the system is tested on the hardware platform, and the system is verified to be quickness and accuracy.

ROI image retrieval based on multiple features of mean shift and expectation–maximisation

In this paper, a novel region of interest (ROI) query method is proposed for image retrieval by combining a mean shift tracking (MST) algorithm and an improved expectation–maximisation (EM)-like (IEML) method. In the proposed combination, the MST is used to seek the initial location of the target candidate model and then IEML is used to adaptively change the location and scale of the target candidate model to include the relevant region and exclude the irrelevant region as far as possible. In order to improve the performance and effectiveness using IEML to track the target candidate model, a new similarity measure is built based on spatial and colour features and a new image retrieval framework for this new environment is proposed. Extensive experiments confirm that compared with the latest developed approaches, such as the generalized Hough transform (GHT) and EM-like tracking methods, our method can provide a much better performance in effectiveness. On the other hand, for the IEML, the new similarity measure model also substantially decreases computational complexity and improves the precision tracking of the target candidate model. Compared with the conventional ROI-based image retrieval methods, the most significant highlight is that the proposed method can directly find the target candidate model in the candidate image without pre-segmentation in advance.

Target tracking based on foreground probability

According to the mean shift tracking algorithm, weights are used to reduce the background interference. However, weights also weaken the representation of the target at the same time. In order to r...

A multimodal approach for individual tracking of people and their belongings

In this study, a fully automatic surveillance system for indoor environments which is capable of tracking multiple objects using both visible and thermal band images is proposed. These two modalities are fused to track people and the objects they carry separately using their heat signatures and the owners of the belongings are determined. Fusion of complementary information from different modalities (for example, thermal images are not affected by shadows and there is no thermal reflection or halo effect in visible images) is shown to result in better object detection performance. We use adaptive background modeling and local intensity operation for object detection and the mean-shift tracking algorithm for fully automatic tracking. Trackers are refreshed to resolve potential problems which may occur due to the changes in object’s size, shape and to handle occlusion-split and to detect newly emerging objects as well as objects that leave the scene. The proposed scheme is applied to the abandoned object detection problem and the results are compared with the state of art methods. The results show that the proposed method facilitate individual tracking of objects for various applications, and provide lower false alarm rates compared to the state of art methods when applied to the abandoned object detection problem.

Fiducial marker and marker-less soft-tissue detection using fast MV fluoroscopy on a new generation EPID: investigating the influence of pulsing artifacts and artifact suppression techniques.

Because frame rates on current clinical available electronic portal imaging devices (EPID's) are limited to 7.5 Hz, a new commercially available PerkinElmer EPID (XRD 1642 AP19) with a maximum frame rate of 30 Hz and a new scintillator (Kyokko PI200) with improved sensitivity (light output) for megavolt (MV) irradiation was evaluated. In this work, the influence of MV pulse artifacts and pulsing artifact suppression techniques on fiducial marker and marker-less detection of a lung lesion was investigated, because target localization is an important component of uncertainty in geometrical verification of real-time tumor tracking. Visicoil™ markers with a diameter of 0.05 and 0.075 cm were used for MV marker tracking with a frame rate of, respectively, 7.5, 15, and 30 Hz. A 30 Hz readout of the detector was obtained by a 2 × 2 pixel binning, reducing spatial resolution. Static marker detection was conducted in function of increasing phantom thickness. Additionally, marker-less tracking was conducted and compared with the ground-truth fiducial marker motion. Performance of MV target detection was investigated by comparing the least-square sine wave fit of the detected marker positions with the predefined sine wave motion. For fiducial marker detection, a Laplacian-of-Gaussian enhancement was applied after which normalized cross correlation was used to find the most probable marker position. Marker-less detection was performed by using the scale and orientation adaptive mean shift tracking algorithm. For each MV fluoroscopy, a free running (FR-nF) (ignoring MV pulsing during readout) acquisition mode was compared with two acquisition modes intending to reduce MV pulsing artifacts, i.e., combined wavelet-FFT filtering (FR-wF) and electronic readout synchronized with respect to MV pulses. A 0.05 cm Visicoil marker resulted in an unacceptable root-mean square error (RMSE) > 0.2 cm with a maximum frame rate of 30 Hz during FR-nF readout. With a 30 Hz synchronized readout (S-nF) and during 15 Hz readout (independent of readout mode), RMSE was submillimeter for a static 0.05 cm Visicoil. A dynamic 0.05 cm Visicoil was not detectable on the XRD 1642 AP19, despite a fast synchronized readout. For a 0.075 cm Visicoil, deviations of sine wave motion were submillimeter (RMSE < 0.08 cm), independent of the acquisition mode (FR, S). For marker-less tumor detection, FR-nF images resulted in RMSE > 0.3 cm, while for MV fluoroscopy in S-mode RMSE < 0.1 cm for 15 Hz and RMSE < 0.16 cm for 30 Hz. Largest consistency in target localization was experienced during 15 Hz S-nF readout. In general, marker contrast decreased in function of higher frame rates, which was detrimental for marker detection success. In this work, Visicoils with a thickness of 0.075 cm were showing best results for a 15 Hz frame rate, while non-MV compatible 0.05 cm Visicoil markers were not visible on the new EPID with improved sensitivity compared to EPID models based on a Kodak Lanex Fast scintillator. No noticeable influence of pulsing artifacts on the detection of a 0.075 cm Visicoil was observed, while a synchronized readout provided most reliable detection of a marker-less soft-tissue structure.

Variable Background Frame Difference Technology Research

When the target and background in the high speed change, moving target detection. The traditional easily lost, not accurate. This paper presents a variable background frame difference method, and makes use of the MeanShift tracking algorithm simulation application. The method can detect moving objects in complex environment, and real-time tracking, can quickly and accurately detect and track when the background and target are scale, rotation, no rules of large displacement changes.

Mean-Shift 法を用いた移動物体追跡におけるヒストグラム分解能の動的選択

Mean-Shift 法を用いた移動物体追跡におけるヒストグラム分解能の動的選択

A Fast Object Tracking Approach in Vision Application

Object tracking has always been a hot issue in vision application, its application area include video surveillance, human-machine, virtual reality and so on. 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.

Mean-shift跟踪算法及其在光电跟踪系统中的应用

Mean-shift跟踪算法及其在光电跟踪系统中的应用

带宽自适应的均值漂移红外目标跟踪算法

For the fixed-bandwidth windows,the tracking target will be lost in traditional mean shift algorithm with target scale changed.To solve this problem,an adaptive-bandwidth mean shift tracking algorithm was proposed.The shape features were extracted under the algorithm in the framework of mean shift,the bandwidth was adjusted adaptively based on target shape motions,and the target template was updated.Experimental results indicate that the proposed algorithm can track the target with scale changed and improve the target tracking precision effectively.

The Improvement of Mean - Shift Algorithm in the Video of Global Visual Robotic Fish in Tracking Moving Targets

The tracking effect is not good for the faster track with Mean Shift tracking algorithm when the difference is not obvious between the track target and background pixels in the video of global visual robotic fish.To solve the difficulty of tracking drastically moving targets in this paper, determining the position of moving targets in the next frame through comparing with two bc coefficients which have been set when the Epanechnikov has been selected core to estimate is indeed. The experimental results show the proposed algorithm can track the moving targets efficiently and precisely in video,and also can meet high real-time situation with small calculation.

Research on Target Tracking Algorithm Based on Particle Filter and Mean-Shift

Since Mean-Shift tracking algorithm always falls into local extreme value when the target was sheltered and the particle filter tracking algorithm has huge calculation and degeneracy phenomenon, a new target tracking algorithm based on Mean-Shift and Particle Filter combination is proposed in this paper. First, this paper introduces the basic theory of Mean-Shift and Particle Filter tracking algorithm, and then presents the new target tracking which the Mean-Shift iteration embeds Particle Filter algorithm. Experiment results show that the algorithm needs less computation, while the real-time tracking has been guaranteed, robustness has been improved and the tracking results has been greatly increased.

Corrected Background-weighted Histogram Mean Shift Tracking Algorithm Based on Adaptive Bandwidth

The CBWH (corrected background-weighted histogram) scheme can effectively reduce backgrounds interference in target localization. But it still has the problem of scale and spatial localization inaccuracy. To solve the above issues, we proposed a method which generates a color probability distribution by taking advantage of the targets salient features. In the binary image, we calculate the invariant moment and thus to resize the tracking window of the next frame. A simple background-weighted model updating method is adopted to adapt to the complex background in tracking. Experimental results show that the proposed algorithm improves the robustness of object tracking by self-adaptive kernel-bandwidth updating.

Efficient Multi-Target Tracking Based on Meanshift and PNN

Multi-target tracking is one of the basic and difficult tasks in video analysis and understanding. This paper proposed an efficient tracking algorithm based on meanshift algorithm and PNN (Probability Neural Network) background model. Firstly, PNN detection results were used to initialize targets for meanshift tracking. Secondly, in the succeeding frames, every target was matched to detected regions before tracking. At last, only targets which couldnt match with new regions need tracking with meanshift tracking algorithm. Experimental results show that mean search steps for every target were dramatically reduced compare with original mean shift tracking algorithm.

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.

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.