基于均值漂移和模糊积分融合的高光谱图像分割

In this paper, a Mean Shift algorithm based on Least Square prediction is proposed. Based on the continuity of target's trace, the Least Square Mean Shift (LSMS) algorithm uses the result of Least Square prediction as the initial search center of Mean Shift algorithm. Then, Mean Shift is applied to get the final target position. The computational complexity is reduced by limiting the number of iterations of Mean shift. Experimental results show that, compared with traditional Mean Shift algorithm, the proposed algorithm improves the real-time realization. Meanwhile, it has better performance on fast moving targets and non-linear moving targets.

A sufficient condition for the convergence of the mean shift algorithm with Gaussian kernel

Nowadays object tracking is a challenge in the fields of computer vision, many algorithms are put forward to overcome the issues such as noisy, colored background, and occlusion of object and also illusion which is low and sudden changes in real-time videos, trackers cannot perform well in real-time environment. An efficient algorithm is needed for effective tracing of an object because of variation in position under various conditions. Here, the MS algorithm is used due to its efficiency and performance. MS tracking algorithm is used to obtain the position of an object by using a Kalman filter, therefore, the performance of tracking an object for different videos is evaluated but it does not improve the target localization. The advanced version is developed for tracking and representing the object in different video sequences are MS and CBWH MS using Kalman filter. Therefore, the proposed method is better than the traditional MS track, which results in the constant tracking of an object throughout the video. It does not get influenced by occlusions and less subjected to background cluttering.

A mean shift algorithm has gained special attention in recent years due to its simplicity to enable real-time tracking. However, the traditional mean shift tracking algorithm can fail to track target under occlusions. In this paper we propose a novel technique which alleviates the limitation of mean shift tracking. Our algorithm employs the Kalman filter to estimate the target dynamics information. Moreover, the proposed algorithm performs the background check process to calculate the similarity which expresses how similar to target the background is. We then find the exact target position combining the motion estimation by Kalman filter and the color based estimation by the mean shift algorithm based on the similarity value. Therefore, the proposed algorithm can robustly track targets under several types of occlusion, while the mean shift and mean shift-Kalman filter algorithms fail.

In order to solve the problems of motion blur and fast motion, a new robust object tracking algorithm using the Kernelized Correlation Filters (KCF) and the Mean Shift (MS) algorithm, called KCFMS is presented in this paper. The object tracking process can be described as: First, we give the initial position and size of the object and use the Mean Shift algorithm to obtain the position of the object. Second, the Kernelized Correlation Filtering algorithm is used to obtain the position of the object in the same frame. Third, we use the cross update strategy to update the object models. In order to improve the tracking speed as much as possible, our object tracking algorithm works only over one layer. This hybrid algorithm has a good tracking effect on the target fast motion and motion blur. We present extensive experimental results on a number of challenging sequences in terms of efficiency, accuracy and robustness.

Forests are the main part of the terrestrial ecosystem. Airborne LiDAR is fast, comprehensive, penetrating, and contactless and can depict 3D canopy information with a high efficiency and accuracy. Therefore, it plays an important role in forest ecological protection, tree species recognition, carbon sink calculation, etc. Accurate recognition of individual trees in forests is a key step to various application. In real practice, however, the accuracy of individual tree segmentation (ITS) is often compromised by under-segmentation due to the diverse species, obstruction and understory trees typical of a high-density multistoried mixed forest area. Therefore, this paper proposes an ITS optimization method based on Gaussian mixture model for airborne LiDAR data. First, the mean shift (MS) algorithm is used for the initial ITS of the pre-processed airborne LiDAR data. Next, under-segmented samples are extracted by integrated learning, normally segmented samples are classified by morphological approximation, and the approximate distribution uncertainty of the normal samples is described with a covariance matrix. Finally, the class composition among the under-segmented samples is determined, and the under-segmented samples are re-segmented using Gaussian mixture model (GMM) clustering, in light of the optimal covariance matrix of the corresponding categories. Experiments with two datasets, Trento and Qingdao, resulted in ITS recall of 94% and 96%, accuracy of 82% and 91%, and F-scores of 0.87 and 0.93. Compared with the MS algorithm, our method is more accurate and less likely to under-segment individual trees in many cases. It can provide data support for the management and conservation of high-density multistoried mixed forest areas.

Visual MRI: Merging information visualization and non-parametric clustering techniques for MRI dataset analysis

Digital image processing is an important field in pattern recognition and computer vision, where the process of separating an object with the background acts as one of the crucial roles in executing image processing. This research will talk about mean shift algorithm implementation in processing a set of undersea images to see its effectiveness in separating the background with the object automatically based on pixel distribution and color intensity. How the mean shift algorithm works is by doing a reading process to find the center of a pixel cluster in an image before this algorithm starts to cluster or group pixels with similar characteristics. In this research, a set of image input will be used as a test under mean shift algorithm to give output of an optimal pixel segmentation or grouping, leading to a proof that the mean shift algorithm has the capability to separate a main object from the background, especially in images with intense and high contrast. Even so, in images with less intense and lower contrast, the segmentation is not as accurate. The image input will have to undergo some more pre-processing before the mean shift segmentation is implemented. This research outcome is that the mean shift algorithm is effective for segmenting marine animal images based on colors without having to initialize how many clusters as the conclusion where this method is applicable in many computer vision programs such as object detection or image pattern recognition.

Image segmentation is a very important phase in automatic image analysis. Of the developed techniques for image segmentation, iterative methods have been proven to be one of the most effective algorithms in the literature. Mean shift algorithms is one of the iterative approaches which have been successfully deployed to many applications. However, despite its promising performance, mean shift has shown its weaknesses in convergence in some of the application areas. In this paper, an improved version of the standard mean-shift algorithm using a memory gradient method is proposed and implemented in order to achieve fast convergence rates by integrating mean shift and memory gradient. Experimental results on real images demonstrate that our proposed algorithm not only improves the efficiency of the classical mean shift algorithm, but also achieves better segmentation results.

Although widely used in practice for real time ability, the mean shift algorithm was weak at target model description and was robust for infrared image sequences form motion platform. In order to enhance the adaptability and target description ability of the mean shift algorithm, meanwhile to make up the shortcomings of the nuclear density estimation based on gradation feature, an adaptive Kalman-mean shift algorithm based on multi-feature fusion was proposed. A target description mode based on gradation-edge feature fusion was applied, while a scale updating item of tracking window was used in the mean shift algorithm based on the relation between mutual information and the object scale. Experimental results demonstrate that the adaptability of mean shift algorithm is enhanced by the improved algorithm, which is effectively applied in the tracking problem for the object of scale variance in long time tracking process.

Object detection and tracking under complex environment are challenging because of the disturbances induced by background clutter, illumination changes, occlusions and other factors. The bulk of traditional algorithms basically rely on hand‐crafted features, which are not sufficiently robust to a complex environment. Moreover, the processes of detection and tracking are separated, which leads to the overall efficiency not high. In this study, a novel local probability model (LPM)‐based mean shift (MS) algorithm is proposed to integrate object detection and tracking. The main contributions include: (i) a new framework based on the combination of LPM and MS is established for the integration of object tracking and detection. (ii) For object detection, the training and prediction of LPM are built by stacked denoising autoencoders based deep learning. (iii) For object tracking, an MS tracking algorithm leveraging LPM is modified to improve the tracking efficiency under a complex environment. Experimental results demonstrate that the proposed method is superior to the colour histograms based MS and histograms of oriented gradients based MS in terms of robustness and tracking accuracy.

The classical mean shift (MS) algorithm is the best color-based method for object tracking. However, in the real environment it presents some limitations, especially under the presence of noise, objects with partial and full occlusions in complex environments. In order to deal with these problems, this paper proposes a reliable object tracking algorithm using corrected background-weighted histogram (CBWH) and the Kalman filter (KF) based on the MS method. The experimental results show that the proposed method is superior to the traditional MS tracking in the following aspects: 1) it provides consistent object tracking throughout the video; 2) it is not influenced by the objects with partial and full occlusions; 3) it is less prone to the background clutter.

Accurate segmentation of infrared thermal images is a challenging issue in the breast cancer detection. This paper presents and evaluates novel segmentation method for breast cancer detection using infrared thermal images. The developed segmentation method uses developed segmentation algorithm that is hybrid of Gaussian Mean Shift (GMS) and roulette wheel selection approach. In the first stage of the developed segmentation method, the redundant portions of the infrared thermal image are removed and then, the infrared thermal image is divided into five and six clusters by applying the developed segmentation algorithm. The segmented infrared thermal image is created by multiplying the selected best image of each cluster. This image is used to diagnosis the normal breast from abnormal breast. The proposed method is developed using MATLAB 2017 and infrared thermal images of 64 patients. The results show that the average Dice similarity coefficient, Jaccard index and Hausdorff distance in the proposed segmentation method are 91.81%, 84.86%, and 4.87, respectively. The comparison results demonstrate that using the proposed segmentation method can improve the performance of the Computer-Aided-Detection (CAD) system compared to the CAD systems that use the Mean Shift (MS) and Fuzzy C-Means (FCM) segmentation algorithms.

Much research has been conducted recently relating to ubiquitous intelligent computing. Ubiquitous intelligence-enabled techniques, such as clustering and image segmentation, have focused on the development of intelligence methodologies. In this paper, a simultaneous mode-seeking and clustering algorithm called the Generalized Transport Mean Shift (GTMS) was introduced. The data points were designated as the ‘transporter–trailer’ characteristic. The important concept of transportation was used to solve the problem of redundant computations of mode-seeking algorithms. The time complexity of the GTMS algorithm is much lower than that of the Mean Shift (MS) algorithm. This means it is able to be used in a problem that has a very high data point, in particular, the segmentation of images containing the green vegetation. The proposed algorithm was tested on clustering and image-segmentation problems. The experimental results showed that the GTMS algorithm improves upon the existing algorithms in terms of both accuracy and time consumption. The GTMS algorithm’s highest speed is also 333.98 times faster than that of the standard MS algorithm. The redundancy computation can be reduced by omitting more than 90% of the data points at the third iteration of the mode-seeking process. This is because GTMS algorithm mainly reduces the data in the mode-seeking process. Thus, use of the GTMS algorithm would allow for the building of an intelligent portable device for surveying green vegetables in a ubiquitous environment.

A Mean shift algorithm is a clustering & unsupervised algorithm. It is also called as “Mode seeking Algorithm”. A mean-shift algorithm used for image processing and also in computer vision. It doesn't require specified clusters like k-mean. Basically it has two types BMS & MS. By studying these two, it looks like BMS is slightly better than MS because it changes the dataset in each iteration with computed value. It's nonparametric algorithm and it can control no. of the cluster because the mean shift is much slower and much time complex and output depend on windows size. (Windows size is trivial). The BMS is an accelerated version which uses the original data only in the first step, then re-smoothes previous estimates. A BMS does not predefined shape on data cluster. To overcome such a situation, we can use the BMS and K-Medoid algorithm because k-medoid is partitioning technique of a cluster. It has better scalability for the larger datasets and much efficient so using these two we can build mean shift algorithm faster than before.