Improved Mean Shift Algorithm Research Articles

Combining Improved Meanshift and Adaptive Shi-Tomasi Algorithms for a Photovoltaic Panel Segmentation Strategy

To achieve effective and accurate segmentation of photovoltaic panels in various working contexts, this paper proposes a comprehensive image segmentation strategy that integrates an improved Meanshift algorithm and an adaptive Shi-Tomasi algorithm. This approach effectively addresses the challenge of low precision in segmenting target regions and boundary contours in routine photovoltaic panel inspection. Firstly, based on the image information of photovoltaic panels collected under different environments by cameras, an improved Meanshift algorithm based on platform histogram optimization is used for preliminary processing, and images containing target information are cut out; then, the adaptive Shi-Tomasi algorithm is used to extract and screen feature points from the target area; finally, the extracted feature points generate the segmentation contour of the target photovoltaic panel, achieving accurate segmentation of the target area and boundary contour of the photovoltaic panel. Experiments verified that in photovoltaic panel images under different background environments, the method proposed in this paper enhances the accuracy of segmenting the target area and boundary contour of photovoltaic panels.

The Research of Improved Mean-Shift Algorithm used in Rapid Localization of Electromagnetic Objects under Specific Geographical Environment

Background: The need for electromagnetic target positioning has grown increasingly important in recent years, especially in the field of communication, navigation and other electromagnetic fields. Objective: The objective of this study is to find a method for electromagnetic target location in different geographical environment and improve the positioning accuracy of the electromagnetic target in specific geographical environments effectively. Methods: This paper has proposed an improved Mean-shift Algorithm that can be used in the rapid localization of electromagnetic objects under specific geographical environments. The paper also analyses different interference source power prediction algorithms and gives out the analysis results of the different algorithms. Parameter adjustments of mean shift algorithm are also given out, and the related process in detail is presented. Results: Through the suppression jamming source location experiment, the proposed method can be used in the rapid localization of electromagnetic objects under specific geographical environment, and its characteristics are better than other localization algorithms. Conclusion: The proposed algorithm is suitable for the location of the electromagnetic target in a specific geographical environment, and its accuracy is greatly improved compared with the traditional method.

Diagnosis of Idiopathic Premature Ovarian Failure by Color Doppler Ultrasound under the Intelligent Segmentation Algorithm.

The aim of this study was to explore the application value of transvaginal color Doppler ultrasound based on the improved mean shift algorithm in the diagnosis of idiopathic premature ovarian failure (POF). In this study, 80 patients with idiopathic POF were selected and included in the experimental group, and 40 volunteers who underwent health examinations during the same period were selected and included in the control group, who underwent transvaginal Doppler ultrasound examination. At the same time, an improved mean shift algorithm was proposed based on artificial intelligence technology and applied to ultrasound image processing. In addition, the ovarian artery parameters of patients were compared in two groups, including peak systolic flow rate (PSV), diastolic flow rate (EDV), resistance index (RI), and pulsatile index (PI). The results showed that the relative difference degree (RDD) of the segmentation results of the algorithm in this study was significantly lower than that of Snake, Live_wire, and the traditional mean shift algorithm, while the relative overlap degree (ROD) and Dice coefficient were opposite, and the differences were significant (P<0.05). The mediolateral diameter of control group was 2.87±0.31cm, and the anteroposterior diameter was 1.86±0.28 cm; while those were 2.11±0.36 cm and 1.13±0.34 cm, respectively, in the experimental group, showing significant differences between the groups (P<0.05). Of the 80 patients in the experimental group, 132 cases with ovarian arteries were found; among 40 patients in the experimental group, 76 cases were found with ovarian arteries, and the hemodynamic detection rate of the experimental group was significantly lower than that of the control group (P<0.05). The ovarian artery parameters PI, RI, and S/D of the experimental group were significantly higher than those of the control group, and the differences were statistically significant (P<0.05). The results showed that the segmentation results of the improved algorithm in this study were more superior to the segmentation results of other algorithms. The regional information loss of the segmentation results was not serious, and the resolution was higher and the definition was higher. The transvaginal color Doppler ultrasound based on the artificial intelligence segmentation algorithm can clearly show the functional status and hemodynamics of the patient's ovaries. The ovarian artery parameters PI and RI can be used as specific indicators for evaluating the POF.

Study of Clustering Algorithms in Object Tracking and Image Segmentation

Mean Shift is a kind of clustering algorithm, which is mostly used for target tracking, image segmentation, etc. In order to solve the problem that image information is not effectively utilized because of unclear traffic video images and random jitter between image sequences, this paper has studied how to achieve stability of traffic video images and proposed an improved Mean Shift algorithm about how to conduct object centroid registration in compensation for the deviations in space localization and, on this basis, how to select kernel window width to eliminate the errors in scale positioning. This algorithm gets the tracking effect and computation analysis of improved Mean Shift from the perspective of applications, removes or relieves the impact motion has on imaging, improves the quality of the video image information obtained, automatically adjusts the size of window according to the scale changes of moving object in the image, and effectively enhances the stability and real time of object tracking. Besides, in the postprocessing stage, the superpixel based on the Mean Shift algorithm is applied to further optimize the segmentation result; it is a popular mode-seeking clustering algorithm, which makes Mean Shift method ideal on low-dimensional applications such as image segmentation. Finally, we show promising results for remote sensing image segmentation.

Adoption of Two-Dimensional Ultrasound Gastrointestinal Filling Contrast on Artificial Intelligence Algorithm in Clinical Diagnosis of Gastric Cancer.

This research was aimed to explore the value of gastrointestinal filling contrast-enhanced ultrasound (CEUS) and computed tomography (CT-)-enhanced scanning based on artificial intelligence (AI) algorithm in the evaluation of gastric cancer staging. 102 patients with gastric cancer were selected as the research objects. All of them underwent CEUS of gastrointestinal filling and 64-slice spiral CT before surgery. In addition, an improved mean shift algorithm was proposed based on differential optical flow and deep convolutional neural network (D-CNN), which was applied in image processing. The predicted positive rate (PPR), sensitivity, specificity, and accuracy of gastric cancer in different stages by CEUS and CT were calculated using pathological diagnosis results as the gold standard. 17 patients with T1 stage, 41 patients with T2-T3 stage, and 35 patients with T4 stage were detected by CEUS. 13 patients with T1 stage, 34 patients with T2-T3 stage, and 30 patients with T4 stage were detected by CT enhanced examination. The PPRs of CEUS for T1, T2-T3, and T4 stages of gastric cancer were higher than those of CT enhanced (P < 0.05). The PPR of CEUS for N0 staging of gastric cancer was higher than that of CT enhanced (P < 0.05), and it for N3 staging of gastric cancer was lower than that of CT enhanced (P < 0.05). From the analysis of M staging of gastric cancer, the PPRs of CEUS for M0 and M1 staging of gastric cancer were not statistically different from the PPRs of CT enhanced (P > 0.05). The sensitivity (95.6%), specificity (81.82%), and accuracy (94.12%) of CEUS in assessing resectability were significantly higher than those of CT enhancement (89.01%, 63.67%, and 86.27%, respectively), and the differences were statistically significant (P < 0.05). In summary, CEUS gastrointestinal filling based on the D-CNN algorithm could better improve the display rate of the tissue lesions around the stomach. It also helped to judge the lesion progress, the depth of infiltration, and lymph node metastasis of the lesion. In addition, it had excellent performance in evaluating the resectability of gastric cancer before surgery and had clinical promotion value.

Prompt Frequency Stabilization of Ultra-Stable Laser via Improved Mean Shift Algorithm

In many scientific fields, the continuous operation of ultra-stable lasers is crucial for applications. To speed up the frequency stabilization process in case of the occurence of unexpected interruptions, a prompt frequency stabilization approach based on an improved mean shift algorithm is proposed and verified with a homemade laser system. We developed a double-loop feedback controller to steer the laser frequency with fast and slow channels, respectively. In this study, an improved mean shift algorithm is utilized to intelligently search for the transmission signal, which involves adaptively updating the sliding window radius and incorporating a Gaussian kernel function to update the shift vector. The number of lock points on the left and right sides of the central point determines the scanning direction to search for the transmission signal quickly. The laser is intentionally interrupted 306 times within 10,000 s to evaluate the relocking performance. The median auto-locking time of the laser is improved from 16 s to 4 s. By beating with another ultra-stable laser system, the laser frequency instability is measured to be less than 2.1×10−14 and the linewidth is 5 Hz. This work improves the adaptation and relocking ability of the ultra-stable laser in a complex environment.

Robust Face Tracking using Improved Mean Shift Algorithm

Face tracking is important system for robotic. The problem is that it is less resistant to occlusion and noise. Robust face tracking algorithm in this paper using improved mean shift algorithm is proposed. This algorithm consist of face detection and tracking. The face identification is done by the Viola-Jones algorithm. Then, Mean Shift algorithm is done to track face as a target and improve robustness from occlusion. CBWH is added in face as target to reduce noise. The experimental results prove that it is robust from noise background and occlusion..

Improved Mean Shift Algorithm for Maximizing Clustering Accuracy

Clustering is a machine learning method that can group similar data points. Mean Shift (MS) is a fixed window-based clustering algorithm, which calculates the number of clusters automatically but cannot guarantee the convergence of the algorithm. The main drawback of the Mean Shift Algorithm is that the algorithm requires to set a stopping criterion (threshold point) otherwise all clusters move towards one cluster and fixed bandwidth is used here. It cannot define the upper bound of iteration numbers and need to set the iteration numbers. This paper proposed a new Mean Shift Algorithm, called Improved Mean Shift (IMS) algorithm, which overcomes the all defined pitfalls of Mean Shift Algorithm. The IMS process KD-tree data structure was used to sort the dataset and all data points as initial cluster centroids without a random selection of initial centroids. In each iteration, it shifts the variable bandwidth sliding window to the actual data point nearest to the mean using k-nearest neighbours (kNN) algorithm and finds the number of clusters automatically. Also, this paper handles the missing values using Mean Imputation (MI). The IMS algorithm produces better results than the Mean Shift Algorithm on both synthetic and real datasets.

Visual Detection and Tracking Based on Fusion Saliency

In order to improve the ability of target tracking effectively, an improved MeanShift algorithm is proposed in this paper. The algorithm combines the saliency map from the computer and from the human vision through Kinect, so that it can obtain the fusion saliency. Then an image segmentation algorithm is adopted to get the target, which is modelled for an improved MeanShift tracking framework. Experimental results show that the algorithm can significantly improve the accuracy.

A New Human Eye Tracking Algorithm of Optimized TLD Based on Improved Mean-Shift

In this paper, an improved Mean-shift algorithm was integrated with standard tracking–learning–detection (TLD) model tracker for improving the tracking effects of standard TLD model and enhancing the anti-occlusion capability and the recognition capability of similar objectives. The target region obtained by the improved Mean-shift algorithm and the target region obtained by the TLD model tracker are integrated to achieve favorable tracking effects. Then the optimized TLD tracking system was applied to human eye tracking. In the tests, the model can be self-adopted to partial occlusion, such as eye-glasses, closed eyes and hand occlusion. And the roll angle can approach 90[Formula: see text], raw angle can approach 45[Formula: see text] and pitch angle can approach 60[Formula: see text]. In addition, the model never mistakenly transfers the tracking region to another eye (similar target on the same face) in longtime tracking. Experimental results indicate that: (1) the optimized TLD model shows sound tracking stability even when targets are partially occluded or rotated; (2) tracking speed and accuracy are superior to those of the standard TLD and some mainstream tracking methods. In summary, the optimized TLD model show higher robustness, stability and better responding to complex eye tracking requirement.

A novel method of natural landmark extraction and description for vSLAM

Landmark extraction and matching is a key part of vSLAM. In this paper, a method of landmark extraction and its description based on three-dimensional (3D) information of feature points is proposed. The robot obtains images from its environment via binocular vision, building 3D information of feature points under left camera coordinate system. Then, it uses the method based on improved mean shift algorithm to extract natural landmarks and construct its descriptor, which can be used in fast matching of two landmarks. This method can extract natural landmarks from unstructured environments and tolerate relatively low accuracy of pose estimation. It is suitable for navigation system of a mobile robot running in a complex environment. vSLAM experiments showed its effectiveness.

A novel method of natural landmark extraction and description for vSLAM

Landmark extraction and matching is a key part of vSLAM. In this paper, a method of landmark extraction and its description based on three-dimensional 3D information of feature points is proposed. The robot obtains images from its environment via binocular vision, building 3D information of feature points under left camera coordinate system. Then, it uses the method based on improved mean shift algorithm to extract natural landmarks and construct its descriptor, which can be used in fast matching of two landmarks. This method can extract natural landmarks from unstructured environments and tolerate relatively low accuracy of pose estimation. It is suitable for navigation system of a mobile robot running in a complex environment. vSLAM experiments showed its effectiveness.

Automatic tracking of neural stem cells in sequential digital images

Neural stem cells are the cells that give rise to the main cell types of the nervous system. Due to their varying size and shape, and random movement, the tracking of these cells in suspension in video sequences is challenging. This paper develops an automatic tracking system for neural stem cells. The system first detects and localizes cells in the image sequence, followed by a feature extraction step for the subsequent cell tracking. Then, the system tracks inactive cells using an improved mean shift algorithm, divisive cells through a context-based technique, and active cells by means of dynamic local prediction (DLP) and gray prediction (GP) algorithms. Experimental results show that the proposed system not only improves the accuracy of fast moving tracking, but also constructs accurately the trajectories of the cell movement and reduces the iterations during the center searching.

Segmentation of high spatial resolution remote sensing images of mountainous areas based on the improved mean shift algorithm

Using conventional Mean Shift Algorithm to segment high spatial resolution Remote sensing images of mountainous areas usually leads to an unsatisfactory result, due to its rich texture information. In this paper, we propose an improved Mean Shift Algorithm in consideration of the characteristics of these images. First, images were classified into several homogeneous color regions and texture regions by conducting variance detection on the color space. Next, each homogeneous color region was directly segmented to generate the preliminary results by applying the Mean Shift Algorithm. For each texture region, we conduct a high-dimensional feature space by extracting information such as color, texture and shape comprehensively, and work out a proper bandwidth according to the normalized distribution density. Then the bandwidth variable Mean Shift Algorithm was applied to obtain segmentation results by conducting the patternclassification in feature space. Last, the final results were obtained by merging these regions by means of the constructed cost functions and removing the over-segmented regions from the merged regions. It has been experimentally segmented on the high spatial resolution remote sensing images collected by Quickbird and Unmanned Aerial Vehicle (UAV). We put forward an approach to evaluatethe segmentation results by using the segmentation matching index(SMI). This takes into consideration both the area and the spectrum. The experimental results suggest that the improved Mean Shift Algorithm outperforms the conventional one in terms of accuracy of segmentation.

New Object Detection, Tracking, and Recognition Approaches for Video Surveillance Over Camera Network

Object detection and tracking are two fundamental tasks in multicamera surveillance. This paper proposes a framework for achieving these tasks in a nonoverlapping multiple camera network. A new object detection algorithm using mean shift (MS) segmentation is introduced, and occluded objects are further separated with the help of depth information derived from stereo vision. The detected objects are then tracked by a new object tracking algorithm using a novel Bayesian Kalman filter with simplified Gaussian mixture (BKF-SGM). It employs a Gaussian mixture (GM) representation of the state and noise densities and a novel direct density simplifying algorithm for avoiding the exponential complexity growth of conventional Kalman filters (KFs) using GM. When coupled with an improved MS tracker, a new BKF-SGM with improved MS algorithm with more robust tracking performance is obtained. Furthermore, a nontraining-based object recognition algorithm is employed to support object tracking over nonoverlapping network. Experimental results show that: 1) the proposed object detection algorithm yields improved segmentation results over conventional object detection methods and 2) the proposed tracking algorithm can successfully handle complex scenarios with good performance and low arithmetic complexity. Moreover, the performance of both nontraining- and training-based object recognition algorithms can be improved using our detection and tracking results as input.

An Improved Mean Shift Algorithm for Target Tracking

Mean Shift algorithm is a non-parametric kernel density estimation based on the color histogram. It is a traditional algorithm of target tracking and is wildly used in the video monitoring for its simple calculation and lower time complexity. But it is inapplicable to the target that moves fast. In view of the fact, we propose a novel algorithm combining the bandwidth trial with the traditional algorithm in this paper. It is utilized to solve the problem of fast moving target tracking by comparing the Bhattacharyya coe‐cients to change the bandwidth of the kernel function automatically. Results of experiments indicate that the proposed algorithm not only can track the target more accurately, but also reduce the number of iteration.

A Moving Target Tracking Method Based on Improved Meanshift Algorithm

A Moving Target Tracking Method Based on Improved Meanshift Algorithm

Improved motion information-based infrared dim target tracking algorithms

Accurate and fast tracking of infrared (IR) dim target has very important meaning for infrared precise guidance, early warning, video surveillance, etc. However, under complex backgrounds, such as clutter, varying illumination, and occlusion, the traditional tracking method often converges to a local maximum and loses the real infrared target. To cope with these problems, three improved tracking algorithm based on motion information are proposed in this paper, namely improved mean shift algorithm, improved Optical flow method and improved Particle Filter method. The basic principles and the implementing procedure of these modified algorithms for target tracking are described. Using these algorithms, the experiments on some real-life IR and color images are performed. The whole algorithm implementing processes and results are analyzed, and those algorithms for tracking targets are evaluated from the two aspects of subjective and objective. The results prove that the proposed method has satisfying tracking effectiveness and robustness. Meanwhile, it has high tracking efficiency and can be used for real-time tracking.

Research on Embedded System with Implementation of a Moving Object Tracking Algorithm Based on Improved Meanshift on DM6437

To improve the real-time performance of the meanshift algorithm in the embedded system, an improved meanshift algorithm for tracking moving target is proposed in this paper. In order to reduce the influence of background pixel in a target model, the target model is build by using the target model of continuous frames; to reduce the times of iteration, a kalman filter is used to predict the position of moving object in the current frame; to improve the accuracy of the target model, it is updated in real-time. At last, the improved algorithm is realized on a DM6437 platform and the experimental results show that the improved algorithm can track moving objects effectively.

Average Population Density Estimation in Rail Transit Stations Based on Video Statistical Analysis

This article describes the use of the average population density estimation methods based on video statistical analysis, and mainly discussed the research and application of the air conditioning energy-efficient system in the subway. The distributed intelligent control system in the subway station platform captured video images by more than one camera sensors, according to the computer image processing methods, for example it have the unique advantages for the fuzzy neural network to model the human nervous system in fuzzy information processing. This article used the improved Meanshift algorithm based on pixel energy to capture the moving target in the video. This method can legitimately divide the crowd by achieving the image intelligent analysis data, and whats more, it can help to get the estimation of population density.