An mean shift algorithm with adaptive bandwidth and weight selection for high spatial remotely sensed imagery segmentation

Kernel density estimation (KDE) is a widely used method in geography to study concentration of point pattern data. Geographical networks are 1.5 dimensional spaces with specific characteristics, analyzing events occurring on networks (accidents on roads, leakages of pipes, species along rivers, etc.). In the last decade, they required the extension of spatial KDE. Several versions of Network KDE (NKDE) have been proposed, each with their particular advantages and disadvantages, and are now used on a regular basis. However, scant attention has been given to the temporal extension of NKDE (TNKDE). In practice, when the studied events happen at specific time points and are constrained on a network, the methodologies used by geographers tend to overlook either the network or the temporal dimension. Here we propose a TNKDE based on the recent development of NKDE and the product of kernels. We also adapt classical methods of KDE (Diggle's correction, Abramson's adaptive bandwidth and bandwidth selection by leave‐one‐out maximum likelihood). We also illustrate the method with Montreal road crashes involving a pedestrian between 2016 and 2019.

The traditional mean shift algorithm used fixed kernels or symmetric kernel function, which will cause the target tracking lost or failure. The target tracking algorithm based on mean shift with adaptive bandwidth was proposed. Firstly, the signed distance constraint function was introduced to produce the anisotropic kernel function based on signed distance kernel function. This anisotropic kernel function satisfies that the value of the region function outside the target is zero, which provides accurate tracking window for the target tracking. Secondly, calculate the mean shift window center of anisotropic kernel function template, the theory basis is the sum of vector weights from the sample point in the tracking window to the center point is zero. Thirdly, anisotropic kernel function templates adaptive update implementation by similarity threshold to limit the change of the template between two sequential pictures, so as to realize real-time precise tracking. Finally, the contrast experimental results show that our algorithm has good accuracy and high real time.

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 equally 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.

The vision sensor network is expected to achieve a contact-free wide-area location system without any additional burden on users in intelligent environments. In this article, a tracking algorithm for a location system in an intelligent environment is described. A modified color tracker based on a Kalman filter and a mean shift procedure is proposed in order to improve the robustness for occlusion and rapid movement. To handle the sudden change in object movement, we propose a hybrid tracking algorithm, including an adaptive feedback loop, based on the statistics of color histogram models after the mean-shift process. Experimental results showed that the proposed method achieves more robust tracking of multiple objects than the conventional method.

Mean shift algorithm has grained great success in object tracking domain due to its ease of implementation, real time response and robust tracking performance, however, the fixed kernel bandwidth may cause tracking failure for size changing objects. A novel object tracking algorithm for FLIR imagery is proposed based on mean shift with adaptive bandwidth. The scale invariant feature transform is employed to compute the affine model between the successive frames. Then, the scale and orientation of the kernel can be estimated by the gained parameters. Experiment results verify the effectives and robustness of this extraction algorithm which can improve the tracking performance efficiently.

Particle-based transport models are widely used for simulating the movement of pollutants in environmental systems. Unlike grid-based methods, particles naturally address advective transport without numerical dispersion. However, these models require concentration reconstruction from the discrete particle information. This is computationally demanding in multidimensional problems, posing a challenge for field-scale models requiring frequent reconstruction. Grid Projected Kernel Density Estimation (GPKDE) is a cell-averaged reconstruction with improvements in computational performance compared to classical KDE. Currently, no programs implementing this method are readily integrated into particle simulators, compatible with three-dimensional domains, and particles with unequal weights. This article introduces a Fortran code for general-purpose GPKDE, with modular functionalities facilitating the integration into external software. The program implements locally adaptive kernel bandwidth selection and alternatives for the reconstruction from particles with non-uniform weights. The code is parallelized with the OpenMP library. Numerical test cases demonstrate the program’s applicability and scalability of the parallel implementation.

Diabetes mellitus poses a growing global health concern, particularly in low- and middle-income countries where early detection remains limited, demanding classification models that balance accuracy, interpretability, and adaptability to heterogeneous clinical data. This study proposes and evaluates the Adaptive Kernel Probability Model (AKPM), a novel nonparametric probabilistic classifier designed to enhance diabetes prediction by performing localized kernel density estimation with adaptive bandwidth selection via k-nearest neighbors. Implemented and tested on the Pima Indians Diabetes Dataset, AKPM outperformed conventional classifiers—Naïve Bayes and Gaussian Mixture Models (GMM)—across all evaluation metrics, achieving 87.5% accuracy, 83.3% precision, 76.9% recall, and an F1-score of 80.0% for the diabetic class, alongside 89.3% precision and 92.6% recall for the normal class. These results surpassed GMM (83.0% accuracy, 71.6% F1-score) and Naïve Bayes (80.0% accuracy, 66.6% F1-score), confirming AKPM’s superior capability to detect diabetic cases while minimizing false negatives. Offering transparent posterior inference and a modular design, AKPM emerges as a reliable and interpretable solution for clinical decision support systems and real-world healthcare applications.

The results of a study noise filtering in temperature time series measuring channels using basic frequency filtering algorithms are presented. The study was carried out from the perspective of high frequency random noise suppression. Temperature time series filtering was compared using sliding window procedures with adaptive bandwidth selection, median sliding window, and Baxter-King band-pass approximation. Experimental comparative analysis of filtering efficiency was carried out using the statistical programming language R and open libraries with sliding regression methods. The recorders of surface atmosphere parameters were ultrasonic meteorological stations located at the test site of IMKES SB RAS.

Laser-induced Breakdown spectroscopy quantitative analysis method via adaptive analytical line selection and relevance vector machine regression model

It has been shown that integrating multiple cues will increase the reliability and robustness of a vision system in situations that no single cue is reliable. In this paper, we propose a method by fusing multiple cues (i.e., the color cue and the edge cue). In contrast to previous work, we propose a novel shape similarity measure which includes the spatial distribution of, the number of, and the gradient intensity of the edge points. We integrate this shape similarity measure with our recently proposed SMOG-based color similarity measure in the framework of particle filter (PF). Experimental results demonstrate the high robustness and effectiveness of our method in handling appearance changes, cluttered background, moving camera, and occlusions.

As the variance of the statistics of ultrasonic data in a homogeneous tissue may be rather large and the statistics of different tissues may be very similar, a new filtering approach is proposed to enhance the contrast in ultrasonic images. It is based on the Variable Bandwidth Mean Shift algorithm adapted to the specificities of ultrasonic data. A fully automatic adaptive bandwidth selection in both range and spatial domains is described. Our method was compared to a Variable Bandwidth Mean Shift algorithm based on an adaptive range scale selection and a fixed spatial scale parameter. The results show the superiority of our method.

A novel approach is developed to solve a problem of varying bandwidth selection for filtering a signal given with an additive noise. The approach is based on the intersection of confidence intervals (ICI) rule and gives the algorithm, which is simple to implement and adaptive to unknown smoothness of the signal.

Evaluation of regression models and Bayes-Ensemble Regressor technique for non-intrusive load monitoring

The use of echocardiography ventricle segmentation can obtain ventricular volume parameters, and it is helpful to evaluate cardiac function. However, the ultrasound images have the characteristics of high noise and difficulty in segmentation, bringing huge workload to segment the object region manually. Meanwhile, the automatic segmentation technology cannot guarantee the segmentation accuracy. In order to solve this problem, a novel algorithm framework is proposed to segment the ventricle. Firstly, faster region-based convolutional neural network is used to locate the object to get the region of interest. Secondly, K-means is used to pre-segment the image; then a mean shift with adaptive bandwidth of kernel function is proposed to segment the region of interest. Finally, the region growing algorithm is used to get the object region. By this framework, ventricle is obtained automatically without manual localization. Experiments prove that this framework can segment the object accurately, and the algorithm of adaptive mean shift is more stable and accurate than the mean shift with fixed bandwidth on quantitative evaluation. These results show that the method in this paper is helpful for automatic segmentation of left ventricle in echocardiography.

One of the common methods for measuring distance is to use a camera and image processing algorithm, such as an eye and brain. Mechanical stereo vision uses two cameras to shoot the same object and analyzes the disparity of the stereo vision. One of the most robust methods to calculate disparity is the well-known census transform, which has the problem of conversion window selection. In this paper, three methods are proposed to improve the performance of the census transform. The first one uses a low-pass band of the wavelet to reduce the computation loading and a high-pass band of the wavelet to modify the disparity. The main idea of the second method is the adaptive size selection of the conversion window by edge information. The third proposed method is to apply the adaptive window size to the previous sparse census transform. In the experiments, two indexes, percentage of bad matching pixels (PoBMP) and root mean squared (RMS), are used to evaluate the performance with the known ground truth data. According to the results, the computation required can be reduced by the multiresolution feature of the wavelet transform. The accuracy is also improved with the modified disparity processing. Compared with previous methods, the number of operation points is reduced by the proposed adaptive window size method.